From ff1193d8c313f06b2050d51c3e3bf87818ae5929 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Tue, 25 Aug 2026 12:48:34 +0000 Subject: [PATCH] chore(release): bump version to 1.48.0 (minor) (#11542) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --- Cargo.lock | 12 +- Cargo.toml | 2 +- .../src/canonical/data/canonical_models.json | 23449 ++++++++++++++-- .../src/canonical/data/provider_metadata.json | 109 +- ui/desktop/package.json | 2 +- 5 files changed, 20552 insertions(+), 3022 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index ae2d5304a..f86dd1efc 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -5183,7 +5183,7 @@ dependencies = [ [[package]] name = "goose" -version = "1.47.0" +version = "1.48.0" dependencies = [ "agent-client-protocol", "agent-client-protocol-http", @@ -5321,7 +5321,7 @@ dependencies = [ [[package]] name = "goose-acp-macros" -version = "1.47.0" +version = "1.48.0" dependencies = [ "quote", "syn 3.0.3", @@ -5343,7 +5343,7 @@ dependencies = [ [[package]] name = "goose-cli" -version = "1.47.0" +version = "1.48.0" dependencies = [ "agent-client-protocol", "anstream", @@ -5470,7 +5470,7 @@ dependencies = [ [[package]] name = "goose-mcp" -version = "1.47.0" +version = "1.48.0" dependencies = [ "anyhow", "base64 0.23.1", @@ -5610,7 +5610,7 @@ dependencies = [ [[package]] name = "goose-test" -version = "1.47.0" +version = "1.48.0" dependencies = [ "clap", "serde_json", @@ -5618,7 +5618,7 @@ dependencies = [ [[package]] name = "goose-test-support" -version = "1.47.0" +version = "1.48.0" dependencies = [ "axum", "env-lock", diff --git a/Cargo.toml b/Cargo.toml index cc0888bc4..bcf7c6086 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -8,7 +8,7 @@ resolver = "2" [workspace.package] edition = "2021" -version = "1.47.0" +version = "1.48.0" rust-version = "1.94.1" authors = ["AAIF "] license = "Apache-2.0" diff --git a/crates/goose-provider-types/src/canonical/data/canonical_models.json b/crates/goose-provider-types/src/canonical/data/canonical_models.json index 8199e77ba..5ed5c4025 100644 --- a/crates/goose-provider-types/src/canonical/data/canonical_models.json +++ b/crates/goose-provider-types/src/canonical/data/canonical_models.json @@ -5948,6 +5948,90 @@ "output": 999990 } }, + { + "id": "agentrouter/claude-opus-4.8", + "name": "Claude Opus 4.8", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01", + "release_date": "2026-05-28", + "last_updated": "2026-05-28", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "agentrouter/claude-opus-5", + "name": "Claude Opus 5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-05", + "release_date": "2026-07-24", + "last_updated": "2026-07-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "agentrouter/gpt-5.6-sol", + "name": "GPT-5.6 Sol", + "family": "gpt-sol", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1050000, + "output": 128000 + } + }, { "id": "ai-router/gpt-5.4", "name": "GPT-5.4", @@ -8574,6 +8658,36 @@ "output": 128000 } }, + { + "id": "aki-io/deepseek-v4-flash-0731-284b", + "name": "DeepSeek V4 Flash 0731", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-07-31", + "last_updated": "2026-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.1 + }, + "limit": { + "context": 1048576, + "output": 81920 + } + }, { "id": "aki-io/gemma4-26b", "name": "Gemma 4 26B A4B IT", @@ -8654,41 +8768,14 @@ "open_weights": true, "cost": { "input": 0.86, - "output": 3.0 + "output": 3.0, + "cache_read": 0.18 }, "limit": { "context": 262144, "output": 81920 } }, - { - "id": "aki-io/minimax-m2.5-230b", - "name": "MiniMax-M2.5", - "family": "minimax", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-02-12", - "last_updated": "2026-02-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.25, - "output": 1.2 - }, - "limit": { - "context": 196608, - "output": 65536 - } - }, { "id": "aki-io/mistral4-119b", "name": "Mistral Small 4", @@ -8748,6 +8835,36 @@ "output": 32768 } }, + { + "id": "aki-io/qwen3.8-27b", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 2.2, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "alibaba-cn/MiniMax-M2.5", "name": "MiniMax-M2.5", @@ -9761,7 +9878,9 @@ "open_weights": false, "cost": { "input": 0.115, - "output": 0.287 + "output": 0.287, + "cache_read": 0.012, + "cache_write": 0.144 }, "limit": { "context": 1000000, @@ -18643,6 +18762,37 @@ "output": 131072 } }, + { + "id": "amazon-bedrock/xai.grok-4.6", + "name": "Grok 4.6", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-01", + "release_date": "2026-08-12", + "last_updated": "2026-08-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.2, + "output": 6.6, + "cache_read": 0.55 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, { "id": "amazon-bedrock/zai.glm-4.7", "name": "GLM-4.7", @@ -18749,9 +18899,9 @@ }, "open_weights": true, "cost": { - "input": 1.05, - "output": 4.4, - "cache_read": 0.2, + "input": 0.6, + "output": 2.0, + "cache_read": 0.15, "cache_write": 0.0 }, "limit": { @@ -18941,9 +19091,9 @@ }, "open_weights": true, "cost": { - "input": 1.05, - "output": 4.4, - "cache_read": 0.2, + "input": 0.6, + "output": 2.0, + "cache_read": 0.15, "cache_write": 0.0 }, "limit": { @@ -21194,6 +21344,39 @@ "output": 128000 } }, + { + "id": "azure-cognitive-services/claude-opus-4.7", + "name": "Claude Opus 4.7", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "azure-cognitive-services/claude-opus-4.8", "name": "Claude Opus 4.8", @@ -23369,6 +23552,39 @@ "output": 128000 } }, + { + "id": "azure/claude-opus-4.7", + "name": "Claude Opus 4.7", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "azure/claude-opus-4.8", "name": "Claude Opus 4.8", @@ -25793,7 +26009,7 @@ }, { "id": "baseten/deepseek-ai/DeepSeek-V4-Flash", - "name": "Deepseek V4 Flash 0731", + "name": "DeepSeek V4 Flash 0731", "family": "deepseek-flash", "attachment": false, "reasoning": true, @@ -25818,12 +26034,12 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 384000 } }, { "id": "baseten/deepseek-ai/DeepSeek-V4-Pro", - "name": "Deepseek V4 Pro", + "name": "DeepSeek V4 Pro", "family": "deepseek-thinking", "attachment": false, "reasoning": true, @@ -26813,9 +27029,9 @@ }, "open_weights": true, "cost": { - "input": 0.4, - "output": 3.0, - "cache_read": 0.039999999999999994 + "input": 0.35, + "output": 2.75, + "cache_read": 0.03499999999999999 }, "limit": { "context": 262144, @@ -26873,9 +27089,9 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.013999999999999999 + "input": 0.44, + "output": 1.32, + "cache_read": 0.04399999999999999 }, "limit": { "context": 1048576, @@ -30109,7 +30325,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -30118,7 +30334,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.32, "output": 3.96, @@ -30621,6 +30837,36 @@ "output": 32768 } }, + { + "id": "cloudflare-workers-ai/@cf/qwen/qwen3.8-27b", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 3.2, + "cache_read": 0.05 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "cloudflare-workers-ai/@cf/qwen/qwq-32b", "name": "Qwq 32B", @@ -31229,7 +31475,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31261,7 +31508,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31293,7 +31541,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31325,7 +31574,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31357,7 +31607,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31389,7 +31640,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31421,7 +31673,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31453,7 +31706,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31485,7 +31739,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31517,7 +31772,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -31757,7 +32013,8 @@ "input": [ "text", "image", - "audio" + "audio", + "pdf" ], "output": [ "text" @@ -31823,7 +32080,8 @@ "input": [ "text", "image", - "audio" + "audio", + "pdf" ], "output": [ "text" @@ -31889,7 +32147,8 @@ "input": [ "text", "image", - "audio" + "audio", + "pdf" ], "output": [ "text" @@ -31954,7 +32213,8 @@ "input": [ "text", "image", - "audio" + "audio", + "pdf" ], "output": [ "text" @@ -32278,7 +32538,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32309,7 +32570,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32340,7 +32602,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32371,7 +32634,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32402,7 +32666,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32526,7 +32791,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32557,7 +32823,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32588,7 +32855,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32596,10 +32864,10 @@ }, "open_weights": false, "cost": { - "input": 1.1, - "output": 6.599, - "cache_read": 0.11, - "cache_write": 1.38 + "input": 0.219, + "output": 1.32, + "cache_read": 0.022, + "cache_write": 0.275 }, "limit": { "context": 1050000, @@ -32620,7 +32888,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32652,7 +32921,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32660,10 +32930,10 @@ }, "open_weights": false, "cost": { - "input": 2.749, - "output": 16.498, - "cache_read": 0.275, - "cache_write": 3.437 + "input": 2.2, + "output": 13.199, + "cache_read": 0.219, + "cache_write": 2.749 }, "limit": { "context": 1050000, @@ -32855,7 +33125,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -32886,7 +33157,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -33150,8 +33422,8 @@ "open_weights": true, "cost": { "input": 0.296, - "output": 1.087, - "cache_read": 0.03 + "output": 1.186, + "cache_read": 0.075 }, "limit": { "context": 196680, @@ -33306,7 +33578,7 @@ { "id": "cortecs/mistral-7b-instruct-v0.2", "name": "mistral-7b-instruct-v0.2", - "attachment": false, + "attachment": true, "reasoning": false, "tool_call": false, "temperature": false, @@ -33314,7 +33586,8 @@ "last_updated": "2025-05-26", "modalities": { "input": [ - "text" + "text", + "pdf" ], "output": [ "text" @@ -33535,7 +33808,7 @@ { "id": "cortecs/mixtral-8x7B-instruct-v0.1", "name": "Mixtral 8x7B Instruct v0.1", - "attachment": false, + "attachment": true, "reasoning": true, "tool_call": false, "temperature": true, @@ -33544,7 +33817,8 @@ "last_updated": "2023-12-11", "modalities": { "input": [ - "text" + "text", + "pdf" ], "output": [ "text" @@ -33600,7 +33874,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -33628,7 +33903,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -33686,7 +33962,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -33796,7 +34073,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -34477,98 +34755,6 @@ "output": 262144 } }, - { - "id": "crof/glm-4.7", - "name": "GLM-4.7", - "family": "glm", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-04", - "release_date": "2025-12-22", - "last_updated": "2025-12-22", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.25, - "output": 1.1, - "cache_read": 0.05, - "cache_write": 0.0 - }, - "limit": { - "context": 202752, - "output": 202752 - } - }, - { - "id": "crof/glm-4.7-flash", - "name": "GLM-4.7-Flash", - "family": "glm-flash", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-04", - "release_date": "2026-01-19", - "last_updated": "2026-01-19", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.04, - "output": 0.3, - "cache_read": 0.008, - "cache_write": 0.0 - }, - "limit": { - "context": 202752, - "output": 131072 - } - }, - { - "id": "crof/glm-5", - "name": "GLM-5", - "family": "glm", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-02-12", - "last_updated": "2026-02-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.48, - "output": 1.9, - "cache_read": 0.1, - "cache_write": 0.0 - }, - "limit": { - "context": 202752, - "output": 202752 - } - }, { "id": "crof/glm-5.1", "name": "GLM-5.1", @@ -34741,69 +34927,6 @@ "output": 229376 } }, - { - "id": "crof/kimi-k2.5", - "name": "Kimi K2.5", - "family": "kimi-k2", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": false, - "knowledge": "2025-01", - "release_date": "2026-01", - "last_updated": "2026-01", - "modalities": { - "input": [ - "text", - "image", - "video" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.35, - "output": 1.7, - "cache_read": 0.07 - }, - "limit": { - "context": 262144, - "output": 262144 - } - }, - { - "id": "crof/kimi-k2.5-lightning", - "name": "Kimi K2.5 (Lightning)", - "family": "kimi-k2", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": false, - "release_date": "2026-02-06", - "last_updated": "2026-02-06", - "modalities": { - "input": [ - "text", - "image", - "video" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 1.0, - "output": 3.0, - "cache_read": 0.2 - }, - "limit": { - "context": 131072, - "output": 32768 - } - }, { "id": "crof/kimi-k2.6", "name": "Kimi K2.6", @@ -34960,36 +35083,6 @@ "output": 131072 } }, - { - "id": "crof/minimax-m2.5", - "name": "MiniMax-M2.5", - "family": "minimax", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-02-12", - "last_updated": "2026-02-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.11, - "output": 0.95, - "cache_read": 0.02, - "cache_write": 0.375 - }, - "limit": { - "context": 204800, - "output": 131072 - } - }, { "id": "crof/qwen3.5-397b-a17b", "name": "Qwen3.5 397B-A17B", @@ -35086,6 +35179,37 @@ "output": 262144 } }, + { + "id": "crof/qwen3.8-27b", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 2.1, + "cache_read": 0.06 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "crossmodel/anthropic/claude-fable-5", "name": "Claude Fable 5", @@ -35341,6 +35465,37 @@ "output": 384000 } }, + { + "id": "crossmodel/deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.405, + "output": 1.215, + "cache_read": 0.0135, + "cache_write": 0.405 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "crossmodel/deepseek/deepseek-v4-pro", "name": "DeepSeek V4 Pro", @@ -36718,6 +36873,36 @@ "output": 128000 } }, + { + "id": "crossmodel/z-ai/glm-5.3", + "name": "GLM-5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 4.4, + "cache_read": 0.3, + "cache_write": 1.2 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "crusoe/deepseek-ai/DeepSeek-V3", "name": "DeepSeek V3 0324", @@ -38870,6 +39055,36 @@ "output": 131072 } }, + { + "id": "deepinfra/Qwen/Qwen3.8-27B", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 3.0, + "cache_read": 0.04 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "deepinfra/Qwen/Qwen3.8-Max", "name": "Qwen3.8 Max", @@ -39974,6 +40189,36 @@ "output": 384000 } }, + { + "id": "deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.0028 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "deepseek/deepseek-v4-pro", "name": "DeepSeek V4 Pro", @@ -39983,7 +40228,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -39992,7 +40237,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.435, "output": 0.87, @@ -41069,8 +41314,8 @@ }, "open_weights": true, "cost": { - "input": 0.75, - "output": 2.4, + "input": 1.0, + "output": 3.2, "cache_read": 0.2 }, "limit": { @@ -41098,7 +41343,7 @@ }, "open_weights": true, "cost": { - "input": 0.975, + "input": 1.3, "output": 4.3, "cache_read": 0.26 }, @@ -41186,8 +41431,8 @@ }, "open_weights": true, "cost": { - "input": 0.375, - "output": 2.025, + "input": 0.5, + "output": 2.7, "cache_read": 0.203 }, "limit": { @@ -41217,8 +41462,8 @@ }, "open_weights": true, "cost": { - "input": 0.76, - "output": 3.2, + "input": 0.95, + "output": 4.0, "cache_read": 0.19 }, "limit": { @@ -41396,8 +41641,8 @@ }, "open_weights": true, "cost": { - "input": 0.225, - "output": 0.9, + "input": 0.3, + "output": 1.2, "cache_read": 0.06 }, "limit": { @@ -41673,8 +41918,8 @@ }, "open_weights": true, "cost": { - "input": 0.165, - "output": 0.3575, + "input": 0.3, + "output": 0.65, "cache_read": 0.06 }, "limit": { @@ -42167,9 +42412,9 @@ }, "open_weights": false, "cost": { - "input": 0.2, - "output": 1.2, - "cache_read": 0.02 + "input": 0.1, + "output": 0.6, + "cache_read": 0.01 }, "limit": { "context": 1050000, @@ -42198,9 +42443,9 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2 }, "limit": { "context": 1050000, @@ -42229,9 +42474,9 @@ }, "open_weights": false, "cost": { - "input": 2.0, - "output": 12.0, - "cache_read": 0.2 + "input": 1.0, + "output": 6.0, + "cache_read": 0.1 }, "limit": { "context": 1050000, @@ -42612,8 +42857,8 @@ }, "open_weights": true, "cost": { - "input": 0.3025, - "output": 1.925, + "input": 0.55, + "output": 3.5, "cache_read": 0.111 }, "limit": { @@ -42623,9 +42868,9 @@ }, { "id": "digitalocean/qwen3.8-max", - "name": "Qwen3.8-2.4T-A95B", + "name": "Qwen3.8-Max", "family": "qwen", - "attachment": false, + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, @@ -42633,7 +42878,9 @@ "last_updated": "2026-08-03", "modalities": { "input": [ - "text" + "text", + "image", + "video" ], "output": [ "text" @@ -42646,7 +42893,7 @@ "cache_read": 0.2 }, "limit": { - "context": 262144, + "context": 1000000, "output": 262144 } }, @@ -43074,6 +43321,33 @@ "output": 262144 } }, + { + "id": "echo/echo", + "name": "Echo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-19", + "last_updated": "2026-08-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 50.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "edenai/amazon/moonshot.kimi-k2-thinking", "name": "Kimi K2 Thinking", @@ -43133,62 +43407,6 @@ "output": 262144 } }, - { - "id": "edenai/amazon/nvidia.nemotron-nano-9b-v2", - "name": "Nemotron Nano 9B v2", - "family": "nemotron", - "attachment": false, - "reasoning": true, - "tool_call": false, - "temperature": true, - "release_date": "2025-08-18", - "last_updated": "2025-08-18", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.06, - "output": 0.23 - }, - "limit": { - "context": 128000, - "output": 131072 - } - }, - { - "id": "edenai/amazon/nvidia.nemotron-nano-9b-v2@us", - "name": "Nemotron Nano 9B v2 (US)", - "family": "nemotron", - "attachment": false, - "reasoning": true, - "tool_call": false, - "temperature": true, - "release_date": "2025-08-18", - "last_updated": "2025-08-18", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.06, - "output": 0.23 - }, - "limit": { - "context": 128000, - "output": 131072 - } - }, { "id": "edenai/amazon/zai.glm-4.7-flash", "name": "GLM-4.7-Flash", @@ -43834,7 +44052,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -43843,7 +44061,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.32, "output": 3.96, @@ -44321,10 +44539,10 @@ "family": "deepseek-thinking", "attachment": false, "reasoning": true, - "tool_call": false, + "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -44333,7 +44551,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.3, "output": 2.6, @@ -44696,35 +44914,6 @@ "output": 256000 } }, - { - "id": "edenai/deepinfra/tencent/Hy3", - "name": "Hy3", - "family": "Hy", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-07-06", - "last_updated": "2026-07-06", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.14, - "output": 0.58, - "cache_read": 0.035 - }, - "limit": { - "context": 262144, - "output": 64000 - } - }, { "id": "edenai/deepinfra/thinkingmachines/Inkling", "name": "Inkling", @@ -44897,6 +45086,36 @@ ] }, "open_weights": true, + "cost": { + "input": 0.44, + "output": 1.32, + "cache_read": 0.014 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, + { + "id": "edenai/deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, "cost": { "input": 0.22, "output": 0.66, @@ -44928,12 +45147,12 @@ }, "open_weights": true, "cost": { - "input": 0.66, - "output": 1.98, - "cache_read": 0.022 + "input": 1.32, + "output": 3.96, + "cache_read": 0.044 }, "limit": { - "context": 1048576, + "context": 1000000, "output": 384000 } }, @@ -44958,9 +45177,9 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.028 + "input": 0.22, + "output": 0.66, + "cache_read": 0.007 }, "limit": { "context": 1048576, @@ -44976,7 +45195,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -44985,7 +45204,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.32, "output": 3.96, @@ -45814,10 +46033,10 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075, - "cache_write": 0.041667 + "input": 1.5, + "output": 7.5, + "cache_read": 0.15, + "cache_write": 0.083333 }, "limit": { "context": 1048576, @@ -45849,10 +46068,10 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075, - "cache_write": 0.041667 + "input": 1.5, + "output": 7.5, + "cache_read": 0.15, + "cache_write": 0.083333 }, "limit": { "context": 1048576, @@ -46003,8 +46222,8 @@ }, "open_weights": true, "cost": { - "input": 0.753545, - "output": 0.753545 + "input": 0.75816, + "output": 0.75816 }, "limit": { "context": 128000, @@ -46031,8 +46250,8 @@ }, "open_weights": true, "cost": { - "input": 0.173895, - "output": 0.753545 + "input": 0.17496, + "output": 0.75816 }, "limit": { "context": 131072, @@ -46206,8 +46425,8 @@ }, "open_weights": true, "cost": { - "input": 1.0, - "output": 3.0 + "input": 0.3, + "output": 0.9 }, "limit": { "context": 256000, @@ -46299,7 +46518,7 @@ "output": 5.0 }, "limit": { - "context": 131072, + "context": 262144, "output": 16384 } }, @@ -46488,6 +46707,36 @@ "output": 131072 } }, + { + "id": "edenai/nebius/deepseek-ai/DeepSeek-V4-Flash", + "name": "DeepSeek V4 Flash 0731", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-07-31", + "last_updated": "2026-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.14 + }, + "limit": { + "context": 1048576, + "output": 384000 + } + }, { "id": "edenai/nebius/meta-llama/Llama-3.3-70B-Instruct", "name": "Llama-3.3-70B-Instruct", @@ -46543,7 +46792,7 @@ "cache_read": 1.0 }, "limit": { - "context": 8000, + "context": 1048576, "output": 128000 } }, @@ -46572,7 +46821,7 @@ "cache_read": 0.3 }, "limit": { - "context": 8000, + "context": 262144, "output": 262144 } }, @@ -46628,10 +46877,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.0, + "output": 20.0, + "cache_read": 0.4, + "cache_write": 5.0 }, "limit": { "context": 1050000, @@ -47389,10 +47638,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.0, + "output": 20.0, + "cache_read": 0.4, + "cache_write": 5.0 }, "limit": { "context": 1050000, @@ -47881,9 +48130,8 @@ }, "open_weights": true, "cost": { - "input": 0.2, - "output": 0.4, - "cache_read": 0.04 + "input": 0.176, + "output": 0.528 }, "limit": { "context": 1000000, @@ -47899,7 +48147,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -47908,10 +48156,10 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { - "input": 1.32, - "output": 3.96 + "input": 0.627, + "output": 1.881 }, "limit": { "context": 1000000, @@ -48370,6 +48618,38 @@ "output": 131072 } }, + { + "id": "edenai/qwen/qwen3.8-27b", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.1, + "cache_write": 0.625 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, { "id": "edenai/qwen/qwen3.8-max", "name": "Qwen3.8 Max", @@ -48452,8 +48732,8 @@ }, "open_weights": true, "cost": { - "input": 0.46372, - "output": 0.927441 + "input": 0.46656, + "output": 0.93312 }, "limit": { "context": 256000, @@ -48480,8 +48760,8 @@ }, "open_weights": true, "cost": { - "input": 0.173895, - "output": 0.69558 + "input": 0.17496, + "output": 0.69984 }, "limit": { "context": 128000, @@ -48509,8 +48789,8 @@ }, "open_weights": true, "cost": { - "input": 1.043371, - "output": 1.043371 + "input": 1.04976, + "output": 1.04976 }, "limit": { "context": 128000, @@ -48578,36 +48858,6 @@ "output": 262144 } }, - { - "id": "edenai/tensorx/qwen/qwen3.8-27b", - "name": "Qwen3.8 27B", - "family": "qwen", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-08-14", - "last_updated": "2026-08-14", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.4, - "output": 2.4, - "cache_read": 0.1 - }, - "limit": { - "context": 262144, - "output": 32768 - } - }, { "id": "edenai/together_ai/deepseek-ai/DeepSeek-V4-Flash", "name": "DeepSeek V4 Flash 0731", @@ -48647,7 +48897,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -48656,7 +48906,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.32, "output": 3.96, @@ -49383,10 +49633,10 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075, - "cache_write": 0.041667 + "input": 1.5, + "output": 7.5, + "cache_read": 0.15, + "cache_write": 0.083333 }, "limit": { "context": 1048576, @@ -49418,10 +49668,10 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075, - "cache_write": 0.041667 + "input": 1.5, + "output": 7.5, + "cache_read": 0.15, + "cache_write": 0.083333 }, "limit": { "context": 1048576, @@ -49453,10 +49703,10 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075, - "cache_write": 0.041667 + "input": 1.5, + "output": 7.5, + "cache_read": 0.15, + "cache_write": 0.083333 }, "limit": { "context": 1048576, @@ -49488,10 +49738,10 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075, - "cache_write": 0.041667 + "input": 1.5, + "output": 7.5, + "cache_read": 0.15, + "cache_write": 0.083333 }, "limit": { "context": 1048576, @@ -49958,6 +50208,35 @@ "output": 131072 } }, + { + "id": "edenai/zai/glm-5.3", + "name": "GLM-5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "edenai/zai/glm-5v-turbo", "name": "GLM-5V-Turbo", @@ -50170,6 +50449,37 @@ "output": 32768 } }, + { + "id": "empiriolabs/glm-4-6v-flash", + "name": "GLM 4.6V Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, { "id": "empiriolabs/glm-4.5-flash", "name": "GLM 4.5 Flash", @@ -50286,6 +50596,35 @@ "output": 131072 } }, + { + "id": "empiriolabs/glm-5.3", + "name": "GLM 5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 1.4 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "empiriolabs/kimi-k2-6", "name": "Kimi K2.6", @@ -56066,10 +56405,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 2.5, + "output": 15.0, + "cache_read": 0.25, + "cache_write": 3.125 }, "limit": { "context": 1050000, @@ -57414,6 +57753,39 @@ "output": 131072 } }, + { + "id": "google-vertex-anthropic/claude-fable-5@default", + "name": "Claude Fable 5", + "family": "claude-fable", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 50.0, + "cache_read": 1.0, + "cache_write": 12.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "google-vertex-anthropic/claude-haiku-4.5", "name": "Claude Haiku 4.5", @@ -57810,6 +58182,39 @@ "output": 128000 } }, + { + "id": "google-vertex/claude-fable-5@default", + "name": "Claude Fable 5", + "family": "claude-fable", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 50.0, + "cache_read": 1.0, + "cache_write": 12.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "google-vertex/claude-haiku-4.5", "name": "Claude Haiku 4.5", @@ -58228,7 +58633,8 @@ "open_weights": true, "cost": { "input": 0.6, - "output": 1.7 + "output": 1.7, + "cache_read": 0.06 }, "limit": { "context": 163840, @@ -58292,8 +58698,7 @@ "cost": { "input": 0.3, "output": 2.5, - "cache_read": 0.075, - "cache_write": 0.383 + "cache_read": 0.03 }, "limit": { "context": 1048576, @@ -58515,7 +58920,8 @@ "open_weights": false, "cost": { "input": 2.0, - "output": 120.0 + "output": 120.0, + "cache_read": 0.2 }, "limit": { "context": 65536, @@ -58548,7 +58954,8 @@ "open_weights": false, "cost": { "input": 0.5, - "output": 60.0 + "output": 60.0, + "cache_read": 0.05 }, "limit": { "context": 131072, @@ -58784,9 +59191,9 @@ }, "open_weights": false, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "limit": { "context": 1048576, @@ -58864,9 +59271,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-19", - "last_updated": "2026-05-19", + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "modalities": { "input": [ "text", @@ -58898,9 +59305,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-07", - "last_updated": "2026-05-07", + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", "modalities": { "input": [ "text", @@ -59005,7 +59412,8 @@ "open_weights": true, "cost": { "input": 0.6, - "output": 2.5 + "output": 2.5, + "cache_read": 0.06 }, "limit": { "context": 262144, @@ -59061,7 +59469,8 @@ "open_weights": true, "cost": { "input": 0.07, - "output": 0.25 + "output": 0.25, + "cache_read": 0.007 }, "limit": { "context": 131072, @@ -59119,7 +59528,8 @@ "open_weights": true, "cost": { "input": 0.6, - "output": 2.2 + "output": 2.2, + "cache_read": 0.06 }, "limit": { "context": 200000, @@ -59960,9 +60370,9 @@ }, "open_weights": false, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "limit": { "context": 1048576, @@ -60073,9 +60483,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-19", - "last_updated": "2026-05-19", + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "modalities": { "input": [ "text", @@ -60090,9 +60500,9 @@ }, "open_weights": false, "cost": { - "input": 1.5, - "output": 9.0, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "limit": { "context": 1048576, @@ -60107,9 +60517,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-07", - "last_updated": "2026-05-07", + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", "modalities": { "input": [ "text", @@ -60124,9 +60534,9 @@ }, "open_weights": false, "cost": { - "input": 0.25, - "output": 1.5, - "cache_read": 0.025 + "input": 0.3, + "output": 2.5, + "cache_read": 0.03 }, "limit": { "context": 1048576, @@ -64519,75 +64929,15 @@ } }, { - "id": "hetzner/DeepSeek-V4-Flash", - "name": "DeepSeek V4 Flash 0731", - "family": "deepseek-flash", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-05", - "release_date": "2026-07-31", - "last_updated": "2026-07-31", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0, - "output": 0.0, - "cache_read": 0.0 - }, - "limit": { - "context": 512000, - "output": 384000 - } - }, - { - "id": "hetzner/GLM-5.2-NVFP4", - "name": "GLM-5.2 NVFP4", - "family": "glm", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-06-13", - "last_updated": "2026-06-13", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0, - "output": 0.0, - "cache_read": 0.0 - }, - "limit": { - "context": 512000, - "output": 131072 - } - }, - { - "id": "hetzner/Kimi-K2.7-Code", - "name": "Kimi K2.7 Code", - "family": "kimi-k2", + "id": "hetzner/Qwen/Qwen3.6-35B-A3B-FP8", + "name": "Qwen3.6 35B A3B FP8", + "family": "qwen", "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, - "knowledge": "2025-01", - "release_date": "2026-06-12", - "last_updated": "2026-06-12", + "temperature": true, + "release_date": "2026-04-17", + "last_updated": "2026-04-17", "modalities": { "input": [ "text", @@ -64609,15 +64959,15 @@ } }, { - "id": "hetzner/Qwen/Qwen3.6-35B-A3B-FP8", - "name": "Qwen3.6 35B A3B FP8", + "id": "hetzner/Qwen3.8-27B", + "name": "Qwen3.8-27B", "family": "qwen", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-04-17", - "last_updated": "2026-04-17", + "release_date": "2026-08-14", + "last_updated": "2026-08-14", "modalities": { "input": [ "text", @@ -66594,6 +66944,35 @@ "output": 131072 } }, + { + "id": "huggingface/zai-org/GLM-4.6V-Flash", + "name": "GLM-4.6V-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, { "id": "huggingface/zai-org/GLM-4.7", "name": "GLM-4.7", @@ -66819,9 +67198,9 @@ }, "open_weights": true, "cost": { - "input": 0.124, - "output": 0.42, - "cache_write": 0.062 + "input": 0.11, + "output": 0.408, + "cache_write": 0.055 }, "limit": { "context": 256000, @@ -66848,9 +67227,9 @@ }, "open_weights": true, "cost": { - "input": 0.8, - "output": 2.582, - "cache_write": 0.4 + "input": 0.86, + "output": 2.784, + "cache_write": 0.43 }, "limit": { "context": 202752, @@ -66877,12 +67256,12 @@ }, "open_weights": true, "cost": { - "input": 1.52432, - "output": 4.79072, - "cache_read": 0.283088 + "input": 1.332, + "output": 4.312, + "cache_write": 0.666 }, "limit": { - "context": 202800, + "context": 202750, "output": 3276 } }, @@ -66890,7 +67269,7 @@ "id": "hyper/glm-5.2", "name": "GLM-5.2", "family": "glm", - "attachment": false, + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, @@ -66898,7 +67277,8 @@ "last_updated": "2026-07-22", "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -66906,12 +67286,12 @@ }, "open_weights": true, "cost": { - "input": 1.4, - "output": 4.4, - "cache_read": 0.28 + "input": 1.52432, + "output": 4.79072, + "cache_read": 0.152432 }, "limit": { - "context": 1000000, + "context": 1048576, "output": 32768 } }, @@ -66935,12 +67315,12 @@ }, "open_weights": true, "cost": { - "input": 0.16332, - "output": 0.65328, - "cache_read": 0.015243 + "input": 0.178, + "output": 0.68, + "cache_write": 0.089 }, "limit": { - "context": 131072, + "context": 128072, "output": 13107 } }, @@ -66965,9 +67345,9 @@ }, "open_weights": true, "cost": { - "input": 0.51, - "output": 2.7, - "cache_write": 0.255 + "input": 0.5444, + "output": 2.855, + "cache_write": 0.2722 }, "limit": { "context": 262144, @@ -66996,9 +67376,9 @@ }, "open_weights": true, "cost": { - "input": 0.95, - "output": 4.0, - "cache_read": 0.16 + "input": 1.03436, + "output": 4.3552, + "cache_read": 0.174208 }, "limit": { "context": 262000, @@ -67027,12 +67407,12 @@ }, "open_weights": true, "cost": { - "input": 0.95, - "output": 4.0, - "cache_read": 0.19 + "input": 1.03436, + "output": 4.3552, + "cache_read": 0.206872 }, "limit": { - "context": 256000, + "context": 262000, "output": 16000 } }, @@ -67057,13 +67437,13 @@ }, "open_weights": true, "cost": { - "input": 3.0, - "output": 15.0, - "cache_read": 0.3 + "input": 3.2664, + "output": 16.332, + "cache_read": 0.32664 }, "limit": { "context": 1048576, - "output": 131072 + "output": 16000 } }, { @@ -70276,36 +70656,6 @@ "output": 8192 } }, - { - "id": "inceptron/MiniMaxAI/MiniMax-M2.5", - "name": "MiniMax M2.5", - "family": "minimax", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-02-12", - "last_updated": "2026-02-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.22, - "output": 0.9, - "cache_read": 0.05, - "cache_write": 0.0 - }, - "limit": { - "context": 196608, - "output": 196608 - } - }, { "id": "inceptron/deepseek-ai/DeepSeek-V4-Flash", "name": "DeepSeek V4 Flash 0731", @@ -70359,7 +70709,7 @@ }, "open_weights": true, "cost": { - "input": 0.6, + "input": 0.57, "output": 3.41, "cache_read": 0.2, "cache_write": 0.0 @@ -70393,7 +70743,7 @@ "cost": { "input": 0.67, "output": 3.4, - "cache_read": 0.17, + "cache_read": 0.19, "cache_write": 0.0 }, "limit": { @@ -75283,34 +75633,6 @@ "output": 64000 } }, - { - "id": "kilo/ai21/jamba-large-1.7", - "name": "AI21: Jamba Large 1.7", - "family": "jamba", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2025-08-08", - "last_updated": "2025-08-08", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 2.0, - "output": 8.0 - }, - "limit": { - "context": 256000, - "output": 4096 - } - }, { "id": "kilo/aion-labs/aion-2.0", "name": "AionLabs: Aion-2.0", @@ -76648,34 +76970,6 @@ "output": 64000 } }, - { - "id": "kilo/deepcogito/cogito-v2.1-671b", - "name": "Deep Cogito: Cogito v2.1 671B", - "family": "cogito", - "attachment": false, - "reasoning": true, - "tool_call": false, - "temperature": true, - "release_date": "2025-11-13", - "last_updated": "2025-11-13", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 1.25 - }, - "limit": { - "context": 128000, - "output": 32768 - } - }, { "id": "kilo/deepseek/deepseek-chat", "name": "DeepSeek Chat", @@ -76731,7 +77025,7 @@ }, "limit": { "context": 163840, - "output": 65536 + "output": 163840 } }, { @@ -76759,8 +77053,8 @@ "cache_read": 0.135 }, "limit": { - "context": 163840, - "output": 32768 + "context": 161000, + "output": 161000 } }, { @@ -76845,8 +77139,8 @@ "cache_read": 0.135 }, "limit": { - "context": 163840, - "output": 163840 + "context": 131072, + "output": 32768 } }, { @@ -76876,7 +77170,7 @@ }, "limit": { "context": 163840, - "output": 65536 + "output": 163840 } }, { @@ -76938,18 +77232,19 @@ } }, { - "id": "kilo/deepseek/deepseek-v4-flash:discounted", - "name": "DeepSeek: DeepSeek V4 Flash 0731 (lowest price)", - "family": "deepseek", - "attachment": false, + "id": "kilo/deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2025-08-26", - "last_updated": "2025-08-26", + "release_date": "2026-08-21", + "last_updated": "2026-08-21", "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -76957,9 +77252,9 @@ }, "open_weights": false, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.0028 + "input": 0.22, + "output": 0.66, + "cache_read": 0.007 }, "limit": { "context": 1048576, @@ -76992,36 +77287,7 @@ "cache_read": 0.135 }, "limit": { - "context": 1048576, - "output": 384000 - } - }, - { - "id": "kilo/deepseek/deepseek-v4-pro:discounted", - "name": "DeepSeek: DeepSeek V4 Pro 0813 (lowest price)", - "family": "deepseek", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2025-08-26", - "last_updated": "2025-08-26", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.435, - "output": 0.87, - "cache_read": 0.003625 - }, - "limit": { - "context": 1048576, + "context": 1024000, "output": 384000 } }, @@ -77490,7 +77756,7 @@ }, "limit": { "context": 65536, - "output": 66000 + "output": 65536 } }, { @@ -77728,10 +77994,10 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075, - "cache_write": 0.041667 + "input": 1.5, + "output": 7.5, + "cache_read": 0.15, + "cache_write": 0.083333 }, "limit": { "context": 1048576, @@ -77903,8 +78169,8 @@ }, "open_weights": true, "cost": { - "input": 0.07, - "output": 0.34 + "input": 0.042, + "output": 0.22 }, "limit": { "context": 262144, @@ -78115,64 +78381,6 @@ "output": 50000 } }, - { - "id": "kilo/inclusionai/ling-2.6-1t", - "name": "inclusionAI: Ling-2.6-1T", - "family": "ling", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2026-04-23", - "last_updated": "2026-04-23", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.3, - "output": 2.5, - "cache_read": 0.06 - }, - "limit": { - "context": 262144, - "output": 32768 - } - }, - { - "id": "kilo/inclusionai/ling-2.6-flash", - "name": "inclusionAI: Ling-2.6-flash", - "family": "ling", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2026-04-21", - "last_updated": "2026-04-21", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.1, - "output": 0.3, - "cache_read": 0.02 - }, - "limit": { - "context": 262144, - "output": 32768 - } - }, { "id": "kilo/inclusionai/ling-3.0-flash", "name": "Ling-3.0-flash", @@ -78202,35 +78410,6 @@ "output": 32768 } }, - { - "id": "kilo/inclusionai/ring-2.6-1t", - "name": "inclusionAI: Ring-2.6-1T", - "family": "ring", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-05-08", - "last_updated": "2026-05-08", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.3, - "output": 2.5, - "cache_read": 0.06 - }, - "limit": { - "context": 262144, - "output": 65536 - } - }, { "id": "kilo/kilo-auto/balanced", "name": "Auto Balanced", @@ -78496,7 +78675,7 @@ "output": 0.0 }, "limit": { - "context": 128000, + "context": 65536, "output": 8192 } }, @@ -78557,6 +78736,35 @@ "output": 262144 } }, + { + "id": "kilo/meituan/longcat-2.0-free", + "name": "Meituan: LongCat 2.0 (free)", + "family": "longcat", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1048756, + "output": 131072 + } + }, { "id": "kilo/meta-llama/llama-3.1-70b-instruct", "name": "Meta: Llama 3.1 70B Instruct", @@ -78810,7 +79018,7 @@ "open_weights": true, "cost": { "input": 0.3, - "output": 1.2, + "output": 1.1, "cache_read": 0.04 }, "limit": { @@ -78884,6 +79092,39 @@ "output": 1048576 } }, + { + "id": "kilo/meta/muse-spark-1.2-contributor", + "name": "Meta: Muse Spark 1.2 Contributor", + "family": "muse", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.2, + "cache_read": 0.002 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, { "id": "kilo/microsoft/phi-4", "name": "Microsoft: Phi 4", @@ -79107,8 +79348,8 @@ "cache_read": 0.03 }, "limit": { - "context": 196608, - "output": 196608 + "context": 200000, + "output": 128000 } }, { @@ -79136,7 +79377,7 @@ "cache_read": 0.06 }, "limit": { - "context": 204800, + "context": 196608, "output": 131072 } }, @@ -79201,6 +79442,37 @@ "output": 51200 } }, + { + "id": "kilo/mistralai/devstral", + "name": "Devstral 2", + "family": "devstral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-09", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.44, + "output": 2.2, + "cache_read": 0.044 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "kilo/mistralai/ministral-14b", "name": "Mistral: Ministral 3 14B 2512", @@ -79263,18 +79535,17 @@ }, { "id": "kilo/mistralai/ministral-8b", - "name": "Mistral: Ministral 3 8B 2512", + "name": "Mistral: Ministral 8B", "family": "ministral", - "attachment": true, + "attachment": false, "reasoning": false, - "tool_call": true, + "tool_call": false, "temperature": true, - "release_date": "2025-12-02", - "last_updated": "2025-12-02", + "release_date": "2024-10-17", + "last_updated": "2024-10-17", "modalities": { "input": [ - "text", - "image" + "text" ], "output": [ "text" @@ -79282,13 +79553,12 @@ }, "open_weights": false, "cost": { - "input": 0.15, - "output": 0.15, - "cache_read": 0.015 + "input": 0.11, + "output": 0.11 }, "limit": { - "context": 262144, - "output": 32768 + "context": 128000, + "output": 128000 } }, { @@ -79434,8 +79704,9 @@ }, "open_weights": true, "cost": { - "input": 0.019, - "output": 0.03 + "input": 0.165, + "output": 0.165, + "cache_read": 0.0165 }, "limit": { "context": 131072, @@ -79581,11 +79852,12 @@ }, "open_weights": false, "cost": { - "input": 0.09375, - "output": 0.25 + "input": 0.11, + "output": 0.33, + "cache_read": 0.011 }, "limit": { - "context": 256000, + "context": 128000, "output": 16384 } }, @@ -80082,7 +80354,7 @@ "cost": { "input": 0.05, "output": 0.2, - "cache_read": 0.03 + "cache_read": 0.025 }, "limit": { "context": 262144, @@ -81445,10 +81717,42 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.0, + "output": 20.0, + "cache_read": 0.4, + "cache_write": 5.0 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5.6-sol-discounted", + "name": "OpenAI: GPT-5.6 Sol (50% off)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 15.0, + "cache_read": 0.25, + "cache_write": 3.125 }, "limit": { "context": 1050000, @@ -81478,10 +81782,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.0, + "output": 20.0, + "cache_read": 0.4, + "cache_write": 5.0 }, "limit": { "context": 1050000, @@ -82666,8 +82970,8 @@ "output": 0.52 }, "limit": { - "context": 131072, - "output": 8192 + "context": 40960, + "output": 16384 } }, { @@ -83280,7 +83584,7 @@ }, "limit": { "context": 262144, - "output": 81920 + "output": 262144 } }, { @@ -83340,7 +83644,7 @@ }, "limit": { "context": 262144, - "output": 65536 + "output": 262144 } }, { @@ -83370,7 +83674,7 @@ }, "limit": { "context": 262144, - "output": 65536 + "output": 262144 } }, { @@ -83520,8 +83824,8 @@ "output": 2.7 }, "limit": { - "context": 131072, - "output": 131072 + "context": 262144, + "output": 81920 } }, { @@ -83768,8 +84072,8 @@ "cache_write": 2.5 }, "limit": { - "context": 1000000, - "output": 262144 + "context": 1048576, + "output": 131072 } }, { @@ -83794,9 +84098,10 @@ }, "open_weights": true, "cost": { - "input": 0.45, - "output": 3.2, - "cache_read": 0.05 + "input": 0.425, + "output": 2.55, + "cache_read": 0.085, + "cache_write": 0.53125 }, "limit": { "context": 262144, @@ -83979,13 +84284,14 @@ }, { "id": "kilo/sakana/sakana-namazu", - "name": "Sakana: Sakana Namazu", + "name": "Sakana Namazu", + "family": "sakana-namazu", "attachment": true, "reasoning": true, "tool_call": true, "temperature": false, - "release_date": "2026-08-11", - "last_updated": "2026-08-11", + "release_date": "2026-08-03", + "last_updated": "2026-08-03", "modalities": { "input": [ "text", @@ -84220,20 +84526,20 @@ } }, { - "id": "kilo/stealth/gpt-5.6-sol", - "name": "Stealth: GPT-5.6 Sol (20% off)", - "family": "gpt", + "id": "kilo/stealth/ox-alpha", + "name": "Ox Alpha", + "family": "alpha", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2025-08-26", - "last_updated": "2025-08-26", + "release_date": "2026-08-20", + "last_updated": "2026-08-20", "modalities": { "input": [ "text", "image", - "pdf" + "video" ], "output": [ "text" @@ -84241,14 +84547,12 @@ }, "open_weights": false, "cost": { - "input": 4.0, - "output": 24.0, - "cache_read": 0.4, - "cache_write": 5.0 + "input": 0.0, + "output": 0.0 }, "limit": { - "context": 1050000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { @@ -84399,6 +84703,90 @@ "output": 131072 } }, + { + "id": "kilo/tencent/hy-mt2-1.8b", + "name": "Tencent: Hy-MT2-1.8B", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-08-20", + "last_updated": "2026-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.044, + "output": 0.177 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "kilo/tencent/hy-mt2-30b-a3b", + "name": "Tencent: Hy-MT2-30B-A3B", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-08-20", + "last_updated": "2026-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.074, + "output": 0.295 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "kilo/tencent/hy-mt2-7b", + "name": "Tencent: Hy-MT2-7B", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-08-19", + "last_updated": "2026-08-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.074, + "output": 0.295 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, { "id": "kilo/tencent/hy3", "name": "Hy3", @@ -84592,8 +84980,8 @@ "output": 0.4 }, "limit": { - "context": 1024000, - "output": 1024000 + "context": 32768, + "output": 32768 } }, { @@ -84658,6 +85046,66 @@ "output": 262144 } }, + { + "id": "kilo/thinkingmachines/inkling-small:free", + "name": "Thinking Machines: Inkling Small (free)", + "family": "ling", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-30", + "last_updated": "2026-07-30", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 262144 + } + }, + { + "id": "kilo/thinkingmachines/inkling:free", + "name": "Thinking Machines: Inkling (free)", + "family": "ling", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-15", + "last_updated": "2026-07-15", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 262144 + } + }, { "id": "kilo/undi95/remm-slerp-l2-13b", "name": "ReMM SLERP 13B", @@ -84682,7 +85130,7 @@ }, "limit": { "context": 6144, - "output": 6144 + "output": 4096 } }, { @@ -85317,8 +85765,8 @@ "cache_read": 0.26 }, "limit": { - "context": 200000, - "output": 128000 + "context": 202752, + "output": 202752 } }, { @@ -85347,19 +85795,19 @@ }, "limit": { "context": 1048576, - "output": 131072 + "output": 262144 } }, { - "id": "kilo/z-ai/glm-5.2:free", - "name": "Z.ai: GLM 5.2 (free)", + "id": "kilo/z-ai/glm-5.3", + "name": "GLM-5.3", "family": "glm", "attachment": false, "reasoning": true, - "tool_call": false, + "tool_call": true, "temperature": true, - "release_date": "2026-06-13", - "last_updated": "2026-06-13", + "release_date": "2026-08-14", + "last_updated": "2026-08-14", "modalities": { "input": [ "text" @@ -85368,14 +85816,15 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 0.0, - "output": 0.0 + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 }, "limit": { - "context": 128000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { @@ -85558,13 +86007,13 @@ }, "open_weights": false, "cost": { - "input": 0.0783, - "output": 0.1566, - "cache_read": 0.01566 + "input": 0.035, + "output": 0.12, + "cache_read": 0.01 }, "limit": { - "context": 262144, - "output": 262144 + "context": 1048576, + "output": 1048576 } }, { @@ -85688,10 +86137,10 @@ }, "open_weights": false, "cost": { - "input": 2.5, - "output": 15.0, - "cache_read": 0.25, - "cache_write": 3.125 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -85760,6 +86209,35 @@ "output": 500000 } }, + { + "id": "kilo/~z-ai/glm", + "name": "Z.ai: GLM Latest", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-19", + "last_updated": "2026-08-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "kimi-for-coding/k3", "name": "Kimi K3", @@ -85889,6 +86367,36 @@ "output": 32768 } }, + { + "id": "kosmik/qwen/qwen3.8-27b", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 2.2, + "cache_read": 0.09 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "kuae-cloud-coding-plan/GLM-4.7", "name": "GLM-4.7", @@ -86042,6 +86550,11325 @@ "output": 524288 } }, + { + "id": "llmgateway-providers/alibaba/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (Alibaba Cloud)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.4, + "cache_read": 0.04 + }, + "limit": { + "context": 1000000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/alibaba/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (Alibaba Cloud)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.4, + "output": 4.8, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/alibaba/glm-5", + "name": "GLM-5 (Alibaba Cloud)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.573, + "output": 2.58 + }, + "limit": { + "context": 202752, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/alibaba/glm-5.2", + "name": "GLM-5.2 (Alibaba Cloud)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.28 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/alibaba/kimi-k2.5", + "name": "Kimi K2.5 (Alibaba Cloud)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.574, + "output": 3.011 + }, + "limit": { + "context": 262144, + "output": 98304 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen-coder-plus", + "name": "Qwen Coder Plus (Alibaba Cloud)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2024-09-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.502, + "output": 1.004 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen-flash", + "name": "Qwen Flash (Alibaba Cloud)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.01, + "cache_write": 0.0625 + }, + "limit": { + "context": 1000000, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen-max", + "name": "Qwen Max (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-04-03", + "last_updated": "2025-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.6, + "output": 6.4 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen-omni-turbo", + "name": "Qwen Omni Turbo (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-01-19", + "last_updated": "2025-03-26", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen-plus", + "name": "Qwen Plus (Alibaba Cloud)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01-25", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.2, + "cache_read": 0.08, + "cache_write": 0.5 + }, + "limit": { + "context": 131072, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3-coder-flash", + "name": "Qwen3 Coder Flash (Alibaba Cloud)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.5, + "cache_read": 0.06, + "cache_write": 0.375 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3-coder-plus", + "name": "Qwen3 Coder Plus (Alibaba Cloud)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.2, + "cache_write": 1.25 + }, + "limit": { + "context": 1000000, + "output": 66000 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3-max", + "name": "Qwen3 Max (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 6.0, + "cache_read": 0.24, + "cache_write": 1.5 + }, + "limit": { + "context": 256000, + "output": 32800 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3-vl-flash", + "name": "Qwen3 VL Flash (Alibaba Cloud)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3-vl-plus", + "name": "Qwen3 VL Plus (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.6, + "cache_read": 0.04, + "cache_write": 0.25 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3.6-35b-a3b", + "name": "Qwen3.6 35B A3B (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-17", + "last_updated": "2026-04-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.375, + "output": 2.25 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3.6-flash", + "name": "Qwen3.6 Flash (Alibaba Cloud)", + "family": "qwen3.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-27", + "last_updated": "2026-04-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.05, + "cache_write": 0.3125 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3.6-max-preview", + "name": "Qwen3.6 Max Preview (Alibaba Cloud)", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-04-20", + "last_updated": "2026-04-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.3, + "output": 7.8, + "cache_read": 0.13 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3.6-plus", + "name": "Qwen3.6 Plus (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05, + "cache_write": 0.625 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3.7-flash", + "name": "Qwen3.7 Flash (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-15", + "last_updated": "2026-07-15", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.03, + "output": 0.13, + "cache_read": 0.006, + "cache_write": 0.0375 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3.7-max", + "name": "Qwen3.7 Max (Alibaba Cloud)", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-21", + "last_updated": "2026-05-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 7.5, + "cache_read": 0.5, + "cache_write": 3.125 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3.7-plus", + "name": "Qwen3.7 Plus (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-06-02", + "last_updated": "2026-06-02", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6, + "cache_read": 0.08, + "cache_write": 0.5 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen3.8-max", + "name": "Qwen3.8 Max (Alibaba Cloud)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.25, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/alibaba/qwen35-397b-a17b", + "name": "Qwen3.5 397B A17B (Alibaba Cloud)", + "family": "qwen3.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-fable-5", + "name": "Claude Fable 5 (Anthropic)", + "family": "claude-fable", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 50.0, + "cache_read": 1.0, + "cache_write": 12.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-haiku-4.5", + "name": "Claude Haiku 4.5 (Anthropic)", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-opus-4.5", + "name": "Claude Opus 4.5 (Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-11-01", + "last_updated": "2025-11-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-opus-4.6", + "name": "Claude Opus 4.6 (Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05-31", + "release_date": "2026-02-05", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-opus-4.7", + "name": "Claude Opus 4.7 (Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-opus-4.8", + "name": "Claude Opus 4.8 (Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01", + "release_date": "2026-05-28", + "last_updated": "2026-05-28", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-opus-5", + "name": "Claude Opus 5 (Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-05", + "release_date": "2026-07-24", + "last_updated": "2026-07-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5 (Anthropic)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6 (Anthropic)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-17", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/anthropic/claude-sonnet-5", + "name": "Claude Sonnet 5 (Anthropic)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-30", + "last_updated": "2026-06-30", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-fable-5", + "name": "Claude Fable 5 (AWS Bedrock)", + "family": "claude-fable", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 50.0, + "cache_read": 1.0, + "cache_write": 12.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-haiku-4.5", + "name": "Claude Haiku 4.5 (AWS Bedrock)", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-opus-4.1", + "name": "Claude Opus 4.1 (AWS Bedrock)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-opus-4.5", + "name": "Claude Opus 4.5 (AWS Bedrock)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-11-01", + "last_updated": "2025-11-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-opus-4.6", + "name": "Claude Opus 4.6 (AWS Bedrock)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05-31", + "release_date": "2026-02-05", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-opus-4.7", + "name": "Claude Opus 4.7 (AWS Bedrock)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-opus-4.8", + "name": "Claude Opus 4.8 (AWS Bedrock)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01", + "release_date": "2026-05-28", + "last_updated": "2026-05-28", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-opus-5", + "name": "Claude Opus 5 (AWS Bedrock)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-05", + "release_date": "2026-07-24", + "last_updated": "2026-07-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5 (AWS Bedrock)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6 (AWS Bedrock)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-17", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/claude-sonnet-5", + "name": "Claude Sonnet 5 (AWS Bedrock)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-30", + "last_updated": "2026-06-30", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/grok-4.3", + "name": "Grok 4.3 (AWS Bedrock)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-30", + "last_updated": "2026-04-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/grok-4.6", + "name": "Grok 4.6 (AWS Bedrock)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-01", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.5 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/llama-3.1-70b-instruct", + "name": "Llama 3.1 70B Instruct (AWS Bedrock)", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 128000, + "output": 2048 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/llama-4-maverick-17b-instruct", + "name": "Llama 4 Maverick 17B Instruct (AWS Bedrock)", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.24, + "output": 0.97 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "llmgateway-providers/aws-bedrock/llama-4-scout-17b-instruct", + "name": "Llama 4 Scout 17B Instruct (AWS Bedrock)", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.17, + "output": 0.66 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "llmgateway-providers/aws-mantle/gpt-5.6-luna", + "name": "GPT-5.6 Luna (AWS Mantle)", + "family": "gpt-luna", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 1.32, + "cache_read": 0.022, + "cache_write": 0.275 + }, + "limit": { + "context": 278528, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-mantle/gpt-5.6-sol", + "name": "GPT-5.6 Sol (AWS Mantle)", + "family": "gpt-sol", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.5, + "output": 33.0, + "cache_read": 0.55, + "cache_write": 6.875 + }, + "limit": { + "context": 278528, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/aws-mantle/gpt-5.6-terra", + "name": "GPT-5.6 Terra (AWS Mantle)", + "family": "gpt-terra", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.2, + "output": 13.2, + "cache_read": 0.22, + "cache_write": 2.75 + }, + "limit": { + "context": 278528, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure-ai-foundry/grok-4.1-fast-non-reasoning", + "name": "Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "llmgateway-providers/azure-ai-foundry/grok-4.1-fast-reasoning", + "name": "Grok 4.1 Fast Reasoning (Azure AI Foundry)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "llmgateway-providers/azure-ai-foundry/grok-4.3", + "name": "Grok 4.3 (Azure AI Foundry)", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-30", + "last_updated": "2026-04-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 20000, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/azure-anthropic/claude-fable-5", + "name": "Claude Fable 5 (Azure Anthropic)", + "family": "claude-fable", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 50.0, + "cache_read": 1.0, + "cache_write": 12.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure-anthropic/claude-opus-4.6", + "name": "Claude Opus 4.6 (Azure Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05-31", + "release_date": "2026-02-05", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure-anthropic/claude-opus-4.7", + "name": "Claude Opus 4.7 (Azure Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure-anthropic/claude-opus-4.8", + "name": "Claude Opus 4.8 (Azure Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01", + "release_date": "2026-05-28", + "last_updated": "2026-05-28", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure-anthropic/claude-opus-5", + "name": "Claude Opus 5 (Azure Anthropic)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-05", + "release_date": "2026-07-24", + "last_updated": "2026-07-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure-anthropic/claude-sonnet-5", + "name": "Claude Sonnet 5 (Azure Anthropic)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-30", + "last_updated": "2026-06-30", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-3.5-turbo", + "name": "GPT-3.5 Turbo (Azure)", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2021-09-01", + "release_date": "2023-03-01", + "last_updated": "2023-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 16385, + "output": 4096 + } + }, + { + "id": "llmgateway-providers/azure/gpt-4", + "name": "GPT-4 (Azure)", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-11", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 60.0 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/azure/gpt-4-turbo", + "name": "GPT-4 Turbo (Azure)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 30.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "llmgateway-providers/azure/gpt-4.1", + "name": "GPT-4.1 (Azure)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/azure/gpt-4.1-mini", + "name": "GPT-4.1 Mini (Azure)", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6, + "cache_read": 0.1 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/azure/gpt-4.1-nano", + "name": "GPT-4.1 Nano (Azure)", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.025 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/azure/gpt-4o", + "name": "GPT-4o (Azure)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-08-06", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5", + "name": "GPT-5 (Azure)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5-mini", + "name": "GPT-5 Mini (Azure)", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5-nano", + "name": "GPT-5 Nano (Azure)", + "family": "gpt-nano", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.005 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.1", + "name": "GPT-5.1 (Azure)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.1-codex", + "name": "GPT-5.1 Codex (Azure)", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 400000, + "output": 272000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.1-codex-mini", + "name": "GPT-5.1 Codex mini (Azure)", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.2", + "name": "GPT-5.2 (Azure)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.2-codex", + "name": "GPT-5.2 Codex (Azure)", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.2-pro", + "name": "GPT-5.2 Pro (Azure)", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 21.0, + "output": 168.0 + }, + "limit": { + "context": 400000, + "output": 272000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.3-codex", + "name": "GPT-5.3 Codex (Azure)", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.4", + "name": "GPT-5.4 (Azure)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 15.0, + "cache_read": 0.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.4-mini", + "name": "GPT-5.4 Mini (Azure)", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 4.5, + "cache_read": 0.075 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.4-nano", + "name": "GPT-5.4 Nano (Azure)", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.25, + "cache_read": 0.02 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.4-pro", + "name": "GPT-5.4 Pro (Azure)", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 180.0 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.5", + "name": "GPT-5.5 (Azure)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.6-luna", + "name": "GPT-5.6 Luna (Azure)", + "family": "gpt-luna", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.2, + "cache_read": 0.02, + "cache_write": 0.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.6-sol", + "name": "GPT-5.6 Sol (Azure)", + "family": "gpt-sol", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-5.6-terra", + "name": "GPT-5.6 Terra (Azure)", + "family": "gpt-terra", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/azure/gpt-oss-120b", + "name": "GPT OSS 120B (Azure)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/azure/o1", + "name": "o1 (Azure)", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2024-12-05", + "last_updated": "2024-12-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 60.0, + "cache_read": 7.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "llmgateway-providers/azure/o3", + "name": "o3 (Azure)", + "family": "o", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "llmgateway-providers/azure/o3-mini", + "name": "o3 Mini (Azure)", + "family": "o-mini", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2024-12-20", + "last_updated": "2025-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "llmgateway-providers/azure/o4-mini", + "name": "o4 Mini (Azure)", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.275 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "llmgateway-providers/baidu/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (Baidu)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.028 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/baidu/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (Baidu)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.69, + "output": 3.38, + "cache_read": 0.14 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/baidu/glm-5", + "name": "GLM-5 (Baidu)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/baidu/glm-5.1", + "name": "GLM-5.1 (Baidu)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-07", + "last_updated": "2026-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/baidu/glm-5.2", + "name": "GLM-5.2 (Baidu)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/baidu/kimi-k2.6", + "name": "Kimi K2.6 (Baidu)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0, + "cache_read": 0.16 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/bytedance/deepseek-v3.2", + "name": "DeepSeek V3.2 (ByteDance)", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 0.42, + "cache_read": 0.056 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/bytedance/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (ByteDance)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.44, + "output": 1.32, + "cache_read": 0.014 + }, + "limit": { + "context": 1048576, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/bytedance/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (ByteDance)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.32, + "output": 3.96, + "cache_read": 0.044 + }, + "limit": { + "context": 1048576, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/bytedance/glm-4.7", + "name": "GLM-4.7 (ByteDance)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/bytedance/glm-5.2", + "name": "GLM-5.2 (ByteDance)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1024000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/bytedance/gpt-oss-120b", + "name": "GPT OSS 120B (ByteDance)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.5, + "cache_read": 0.02 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/bytedance/seed-1.6-250615", + "name": "Seed 1.6 (250615) (ByteDance)", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-25", + "last_updated": "2025-06-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.05 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "llmgateway-providers/bytedance/seed-1.6-250915", + "name": "Seed 1.6 (250915) (ByteDance)", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.05 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "llmgateway-providers/bytedance/seed-1.6-flash-250715", + "name": "Seed 1.6 Flash (250715) (ByteDance)", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-26", + "last_updated": "2025-07-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.3, + "cache_read": 0.015 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "llmgateway-providers/bytedance/seed-1.8-251228", + "name": "Seed 1.8 (251228) (ByteDance)", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-18", + "last_updated": "2025-12-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.05 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "llmgateway-providers/canopywave/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (CanopyWave)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.03 + }, + "limit": { + "context": 1000000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/canopywave/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (CanopyWave)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.74, + "output": 3.48, + "cache_read": 0.01 + }, + "limit": { + "context": 1000000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/canopywave/glm-5.2", + "name": "GLM-5.2 (CanopyWave)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 200000, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/canopywave/kimi-k2.6", + "name": "Kimi K2.6 (CanopyWave)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0, + "cache_read": 0.16 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/canopywave/kimi-k3", + "name": "Kimi K3 (CanopyWave)", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, + { + "id": "llmgateway-providers/cerebras/gemma-4-31b-it", + "name": "Gemma 4 31B IT (Cerebras)", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.99, + "output": 1.49 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/cerebras/glm-4.7", + "name": "GLM-4.7 (Cerebras)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.25, + "output": 2.75 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/cerebras/gpt-oss-120b", + "name": "GPT OSS 120B (Cerebras)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 0.75 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/cerebras/llama-3.3-70b-instruct", + "name": "Llama 3.3 70B Instruct (Cerebras)", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.85, + "output": 1.2 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "llmgateway-providers/cerebras/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507 (Cerebras)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-21", + "last_updated": "2025-07-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.2 + }, + "limit": { + "context": 262000, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/deepinfra/deepseek-v3.2", + "name": "DeepSeek V3.2 (DeepInfra)", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.26, + "output": 0.38, + "cache_read": 0.13 + }, + "limit": { + "context": 160000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/deepinfra/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (DeepInfra)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.18, + "cache_read": 0.016 + }, + "limit": { + "context": 1000000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/deepinfra/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (DeepInfra)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.3, + "output": 2.6, + "cache_read": 0.1 + }, + "limit": { + "context": 1048576, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/deepinfra/gemma-4-26b-a4b-it", + "name": "Gemma 4 26B A4B IT (DeepInfra)", + "family": "gemma", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.34 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/deepinfra/gemma-4-31b-it", + "name": "Gemma 4 31B IT (DeepInfra)", + "family": "gemma", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.38 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/deepinfra/glm-5.1", + "name": "GLM-5.1 (DeepInfra)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-07", + "last_updated": "2026-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.05, + "output": 3.5, + "cache_read": 0.205 + }, + "limit": { + "context": 198000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/deepinfra/hy3", + "name": "Hy3 (DeepInfra)", + "family": "Hy", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-06", + "last_updated": "2026-07-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.58, + "cache_read": 0.035 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/deepinfra/kimi-k2.5", + "name": "Kimi K2.5 (DeepInfra)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 2.25, + "cache_read": 0.07 + }, + "limit": { + "context": 256000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/deepinfra/ling-3.0-flash", + "name": "InclusionAI Ling 3.0 Flash (DeepInfra)", + "family": "ling", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-02", + "last_updated": "2026-08-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.18, + "cache_read": 0.012 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/deepinfra/mimo-v2.5", + "name": "MiMo V2.5 (DeepInfra)", + "family": "mimo", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.08 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/deepinfra/mimo-v2.5-pro", + "name": "MiMo V2.5 Pro (DeepInfra)", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/deepinfra/nemotron-3-ultra-550b", + "name": "Nemotron 3 Ultra 550B (DeepInfra)", + "family": "nemotron", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.2, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/deepinfra/qwen3-vl-235b-a22b-instruct", + "name": "Qwen3 VL 235B A22B Instruct (DeepInfra)", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.88, + "cache_read": 0.11 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/deepinfra/qwen3-vl-30b-a3b-instruct", + "name": "Qwen3 VL 30B A3B Instruct (DeepInfra)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-05", + "last_updated": "2025-10-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/deepinfra/qwen3.5-9b", + "name": "Qwen3.5 9B (DeepInfra)", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-23", + "last_updated": "2026-02-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.15 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/deepseek/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (DeepSeek)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.0028 + }, + "limit": { + "context": 1050000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/deepseek/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (DeepSeek)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.435, + "output": 0.87, + "cache_read": 0.003625 + }, + "limit": { + "context": 1050000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/embercloud/glm-4.5", + "name": "GLM-4.5 (EmberCloud)", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 131000, + "output": 96000 + } + }, + { + "id": "llmgateway-providers/embercloud/glm-4.5-air", + "name": "GLM-4.5 Air (EmberCloud)", + "family": "glm-air", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.85, + "cache_read": 0.025 + }, + "limit": { + "context": 131000, + "output": 96000 + } + }, + { + "id": "llmgateway-providers/embercloud/glm-4.7", + "name": "GLM-4.7 (EmberCloud)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.38, + "output": 1.98, + "cache_read": 0.19 + }, + "limit": { + "context": 200000, + "output": 131000 + } + }, + { + "id": "llmgateway-providers/embercloud/glm-4.7-flash", + "name": "GLM-4.7 Flash (EmberCloud)", + "family": "glm-flash", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 200000, + "output": 131000 + } + }, + { + "id": "llmgateway-providers/embercloud/glm-5", + "name": "GLM-5 (EmberCloud)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.72, + "output": 2.3, + "cache_read": 0.144 + }, + "limit": { + "context": 203000, + "output": 131000 + } + }, + { + "id": "llmgateway-providers/embercloud/glm-5.1", + "name": "GLM-5.1 (EmberCloud)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-07", + "last_updated": "2026-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.931, + "output": 2.93, + "cache_read": 0.173 + }, + "limit": { + "context": 203000, + "output": 131000 + } + }, + { + "id": "llmgateway-providers/embercloud/glm-5.2", + "name": "GLM-5.2 (EmberCloud)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.26, + "output": 3.96, + "cache_read": 0.234 + }, + "limit": { + "context": 203000, + "output": 131000 + } + }, + { + "id": "llmgateway-providers/embercloud/kimi-k2.5", + "name": "Kimi K2.5 (EmberCloud)", + "family": "kimi-k2", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.405, + "output": 1.98, + "cache_read": 0.225 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/embercloud/qwen3-coder-next", + "name": "Qwen3 Coder Next (EmberCloud)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2026-02-03", + "last_updated": "2026-02-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.108, + "output": 0.675, + "cache_read": 0.06 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/fireworks/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (Fireworks AI)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.028 + }, + "limit": { + "context": 1048576, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/fireworks/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (Fireworks AI)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.32, + "output": 3.96, + "cache_read": 0.044 + }, + "limit": { + "context": 1048576, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/fireworks/kimi-k3", + "name": "Kimi K3 (Fireworks AI)", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 + }, + "limit": { + "context": 1040384, + "output": 1040384 + } + }, + { + "id": "llmgateway-providers/fireworks/kimi-k3-fast", + "name": "Kimi K3 Fast (Fireworks AI)", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 4.5, + "output": 22.5, + "cache_read": 0.45 + }, + "limit": { + "context": 1040384, + "output": 1040384 + } + }, + { + "id": "llmgateway-providers/gonka24/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (Gonka24)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.075, + "output": 0.175, + "cache_read": 0.0155 + }, + "limit": { + "context": 390000, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/gonka24/kimi-k2.6", + "name": "Kimi K2.6 (Gonka24)", + "family": "kimi-k2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 1.137, + "cache_read": 0.048 + }, + "limit": { + "context": 262144, + "output": 98304 + } + }, + { + "id": "llmgateway-providers/gonka24/minimax-m2.7", + "name": "MiniMax M2.7 (Gonka24)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.32, + "cache_read": 0.017 + }, + "limit": { + "context": 204800, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-2.5-flash", + "name": "Gemini 2.5 Flash (Google AI Studio)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-2.5-flash-lite", + "name": "Gemini 2.5 Flash Lite (Google AI Studio)", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-2.5-pro", + "name": "Gemini 2.5 Pro (Google AI Studio)", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-3-flash-preview", + "name": "Gemini 3 Flash (Preview) (Google AI Studio)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite (Google AI Studio)", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-07", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.025, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro (Preview) (Google AI Studio)", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-3.5-flash", + "name": "Gemini 3.5 Flash (Google AI Studio)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-19", + "last_updated": "2026-05-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 9.0, + "cache_read": 0.15, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-3.5-flash-lite", + "name": "Gemini 3.5 Flash Lite (Google AI Studio)", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-3.6-flash", + "name": "Gemini 3.6 Flash (Google AI Studio)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-3.7-flash", + "name": "Gemini 3.7 Flash (Google AI Studio)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-ai-studio/gemini-pro", + "name": "Gemini Pro Latest (Google AI Studio)", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-27", + "last_updated": "2026-02-27", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-2.5-flash", + "name": "Gemini 2.5 Flash (Google Vertex AI)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-2.5-flash-lite", + "name": "Gemini 2.5 Flash Lite (Google Vertex AI)", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-2.5-pro", + "name": "Gemini 2.5 Pro (Google Vertex AI)", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-3-flash-preview", + "name": "Gemini 3 Flash (Preview) (Google Vertex AI)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite (Google Vertex AI)", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-07", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.025, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro (Preview) (Google Vertex AI)", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-3.5-flash", + "name": "Gemini 3.5 Flash (Google Vertex AI)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-19", + "last_updated": "2026-05-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 9.0, + "cache_read": 0.15, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-3.5-flash-lite", + "name": "Gemini 3.5 Flash Lite (Google Vertex AI)", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-3.6-flash", + "name": "Gemini 3.6 Flash (Google Vertex AI)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/google-vertex/gemini-3.7-flash", + "name": "Gemini 3.7 Flash (Google Vertex AI)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/groq/gpt-oss-120b", + "name": "GPT OSS 120B (Groq)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.75 + }, + "limit": { + "context": 131072, + "output": 32766 + } + }, + { + "id": "llmgateway-providers/groq/gpt-oss-20b", + "name": "GPT OSS 20B (Groq)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.5 + }, + "limit": { + "context": 131072, + "output": 32766 + } + }, + { + "id": "llmgateway-providers/iceberg/gemini-3-flash-preview", + "name": "Gemini 3 Flash (Preview) (Iceberg)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "llmgateway-providers/iceberg/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro (Preview) (Iceberg)", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/iceberg/gemini-3.6-flash", + "name": "Gemini 3.6 Flash (Iceberg)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075, + "cache_write": 0.08333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/inference.net/llama-3.2-11b-instruct", + "name": "Llama 3.2 11B Instruct (Inference.net)", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.33 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/meta/muse-spark-1.1", + "name": "Muse Spark 1.1 (Meta)", + "family": "muse", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-08", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 4.25, + "cache_read": 0.15 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/meta/muse-spark-1.2", + "name": "Muse Spark 1.2 (Meta)", + "family": "muse", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-05", + "last_updated": "2026-08-05", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 4.25, + "cache_read": 0.15 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-m2", + "name": "MiniMax M2 (MiniMax)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.0, + "cache_read": 0.03 + }, + "limit": { + "context": 196608, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-m2.1", + "name": "MiniMax M2.1 (MiniMax)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.1 + }, + "limit": { + "context": 196608, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-m2.1-lightning", + "name": "MiniMax M2.1 Lightning (MiniMax)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.48 + }, + "limit": { + "context": 196608, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-m2.5", + "name": "MiniMax M2.5 (MiniMax)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 204800, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-m2.5-highspeed", + "name": "MiniMax M2.5 Highspeed (MiniMax)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-13", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.4, + "cache_read": 0.03 + }, + "limit": { + "context": 204800, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-m2.7", + "name": "MiniMax M2.7 (MiniMax)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.06 + }, + "limit": { + "context": 204800, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-m2.7-highspeed", + "name": "MiniMax M2.7 Highspeed (MiniMax)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.4, + "cache_read": 0.06 + }, + "limit": { + "context": 204800, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-m3", + "name": "MiniMax M3 (MiniMax)", + "family": "minimax", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.4, + "cache_read": 0.12 + }, + "limit": { + "context": 512000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/minimax/minimax-text-01", + "name": "MiniMax Text 01 (MiniMax)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-15", + "last_updated": "2025-01-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.1 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/mistral/codestral", + "name": "Codestral (Mistral AI)", + "family": "codestral", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "llmgateway-providers/mistral/devstral", + "name": "Devstral 2 (Mistral AI)", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-09", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/mistral/ministral-14b", + "name": "Ministral 14B (Mistral AI)", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-02", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/mistral/ministral-3b", + "name": "Ministral 3B (Mistral AI)", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-02", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/mistral/ministral-8b", + "name": "Ministral 8B (Mistral AI)", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-02", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/mistral/mistral-large", + "name": "Mistral Large 3 (Mistral AI)", + "family": "mistral-large", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2024-11-01", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/mistral/mistral-small", + "name": "Mistral Small 3.2 (Mistral AI)", + "family": "mistral-small", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-06-20", + "last_updated": "2025-06-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/moonshot/kimi-k2.5", + "name": "Kimi K2.5 (Moonshot AI)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/moonshot/kimi-k2.6", + "name": "Kimi K2.6 (Moonshot AI)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0, + "cache_read": 0.16 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/moonshot/kimi-k2.7-code", + "name": "Kimi K2.7 Code (Moonshot AI)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0, + "cache_read": 0.19 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/moonshot/kimi-k2.7-code-highspeed", + "name": "Kimi K2.7 Code Highspeed (Moonshot AI)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.9, + "output": 8.0, + "cache_read": 0.38 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/moonshot/kimi-k3", + "name": "Kimi K3 (Moonshot AI)", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, + { + "id": "llmgateway-providers/nebius/cosmos3-super-reasoner", + "name": "Cosmos 3 Super Reasoner (Nebius AI)", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/nebius/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (Nebius AI)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.75, + "output": 3.5 + }, + "limit": { + "context": 1048576, + "output": 384000 + } + }, + { + "id": "llmgateway-providers/nebius/gemma-3-27b", + "name": "Gemma 3 27B (Nebius AI)", + "family": "gemma", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-12", + "last_updated": "2025-03-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 110000, + "output": 110000 + } + }, + { + "id": "llmgateway-providers/nebius/glm-5.1", + "name": "GLM-5.1 (Nebius AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-07", + "last_updated": "2026-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/nebius/glm-5.2", + "name": "GLM-5.2 (Nebius AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/nebius/gpt-oss-120b", + "name": "GPT OSS 120B (Nebius AI)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/nebius/hermes-4-405b", + "name": "Hermes 4 405B (Nebius AI)", + "family": "hermes", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/nebius/hermes-4-70b", + "name": "Hermes 4 70B (Nebius AI)", + "family": "hermes", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.13, + "output": 0.4 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/nebius/kimi-k2.6", + "name": "Kimi K2.6 (Nebius AI)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/nebius/kimi-k2.7-code", + "name": "Kimi K2.7 Code (Nebius AI)", + "family": "kimi-k2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/nebius/kimi-k3", + "name": "Kimi K3 (Nebius AI)", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, + { + "id": "llmgateway-providers/nebius/llama-3.1-nemotron-ultra-253b", + "name": "Llama 3.1 Nemotron Ultra 253B (Nebius AI)", + "family": "nemotron", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-07", + "last_updated": "2025-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 1.8 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/nebius/llama-3.3-70b-instruct", + "name": "Llama 3.3 70B Instruct (Nebius AI)", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.4 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "llmgateway-providers/nebius/minicpm-v-4.5", + "name": "MiniCPM-V 4.5 (Nebius AI)", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.658, + "output": 1.11 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/nebius/minimax-m2.5", + "name": "MiniMax M2.5 (Nebius AI)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 196608, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/nebius/minimax-m3", + "name": "MiniMax M3 (Nebius AI)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 1048576, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/nebius/nemotron-3-nano-30b", + "name": "Nemotron 3 Nano 30B (Nebius AI)", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-15", + "last_updated": "2025-12-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.24 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/nebius/nemotron-3-nano-omni", + "name": "Nemotron 3 Nano Omni (Nebius AI)", + "family": "nemotron", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-28", + "last_updated": "2026-04-28", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.24 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/nebius/nemotron-3-super-120b", + "name": "Nemotron 3 Super 120B (Nebius AI)", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-11", + "last_updated": "2026-03-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/nebius/nemotron-3-ultra-550b", + "name": "Nemotron 3 Ultra 550B (Nebius AI)", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.0 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, + { + "id": "llmgateway-providers/nebius/qwen2-5-vl-72b-instruct", + "name": "Qwen2.5 VL 72B Instruct (Nebius AI)", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.75 + }, + "limit": { + "context": 32000, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/nebius/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507 (Nebius AI)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-21", + "last_updated": "2025-07-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 262000, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/nebius/qwen3-30b-a3b-instruct", + "name": "Qwen3 30B A3B Instruct 2507 (Nebius AI)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 262000, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/nebius/qwen3-32b", + "name": "Qwen3 32B (Nebius AI)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 40960, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/nebius/qwen3-next-80b-a3b-thinking", + "name": "Qwen3 Next 80B A3B Thinking (Nebius AI)", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/deepseek-v3.2", + "name": "DeepSeek V3.2 (NovitaAI)", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.269, + "output": 0.4, + "cache_read": 0.1345 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/novita/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (NovitaAI)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.028 + }, + "limit": { + "context": 1050000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/novita/ernie-4.5-vl-424b-a47b", + "name": "ERNIE 4.5 VL 424B A47B (NovitaAI)", + "family": "ernie", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-06-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.42, + "output": 1.25 + }, + "limit": { + "context": 123000, + "output": 16000 + } + }, + { + "id": "llmgateway-providers/novita/gemma-4-26b-a4b-it", + "name": "Gemma 4 26B A4B IT (NovitaAI)", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.4 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/gemma-4-31b-it", + "name": "Gemma 4 31B IT (NovitaAI)", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.4 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/glm-4.5v", + "name": "GLM-4.5V (NovitaAI)", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8, + "cache_read": 0.11 + }, + "limit": { + "context": 65536, + "output": 16000 + } + }, + { + "id": "llmgateway-providers/novita/glm-4.6", + "name": "GLM-4.6 (NovitaAI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/glm-4.6v", + "name": "GLM-4.6V (NovitaAI)", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9, + "cache_read": 0.055 + }, + "limit": { + "context": 131072, + "output": 16000 + } + }, + { + "id": "llmgateway-providers/novita/glm-4.7", + "name": "GLM-4.7 (NovitaAI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 204800, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/novita/glm-5", + "name": "GLM-5 (NovitaAI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 202800, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/glm-5.1", + "name": "GLM-5.1 (NovitaAI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-07", + "last_updated": "2026-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.38, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/glm-5.2", + "name": "GLM-5.2 (NovitaAI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/hy3", + "name": "Hy3 (NovitaAI)", + "family": "Hy", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-06", + "last_updated": "2026-07-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.58, + "cache_read": 0.035 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/novita/kimi-k2", + "name": "Kimi K2 (NovitaAI)", + "family": "kimi-k2", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-11", + "last_updated": "2025-07-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.57, + "output": 2.3 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/kimi-k2.6", + "name": "Kimi K2.6 (NovitaAI)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 3.4, + "cache_read": 0.16 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/novita/kimi-k2.7-code", + "name": "Kimi K2.7 Code (NovitaAI)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0, + "cache_read": 0.19 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/novita/kimi-k3", + "name": "Kimi K3 (NovitaAI)", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, + { + "id": "llmgateway-providers/novita/ling-3.0-flash", + "name": "InclusionAI Ling 3.0 Flash (NovitaAI)", + "family": "ling", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-02", + "last_updated": "2026-08-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.18, + "cache_read": 0.012 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/llama-3-70b-instruct", + "name": "Llama 3 70B Instruct (NovitaAI)", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-18", + "last_updated": "2024-04-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.51, + "output": 0.74 + }, + "limit": { + "context": 8192, + "output": 8000 + } + }, + { + "id": "llmgateway-providers/novita/llama-3.2-3b-instruct", + "name": "Llama 3.2 3B Instruct (NovitaAI)", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2024-09-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.03, + "output": 0.05 + }, + "limit": { + "context": 32768, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/novita/llama-3.3-70b-instruct", + "name": "Llama 3.3 70B Instruct (NovitaAI)", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.135, + "output": 0.4 + }, + "limit": { + "context": 131072, + "output": 120000 + } + }, + { + "id": "llmgateway-providers/novita/llama-4-maverick-17b-instruct", + "name": "Llama 4 Maverick 17B Instruct (NovitaAI)", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.85 + }, + "limit": { + "context": 1048576, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/novita/llama-4-scout-17b-instruct", + "name": "Llama 4 Scout 17B Instruct (NovitaAI)", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.18, + "output": 0.59 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/mimo-v2.5", + "name": "MiMo V2.5 (NovitaAI)", + "family": "mimo", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.168, + "output": 0.336, + "cache_read": 0.0034 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/mimo-v2.5-pro", + "name": "MiMo V2.5 Pro (NovitaAI)", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.522, + "output": 1.044, + "cache_read": 0.0043 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/minimax-m2.1", + "name": "MiniMax M2.1 (NovitaAI)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/minimax-m2.5", + "name": "MiniMax M2.5 (NovitaAI)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 204800, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/novita/minimax-m2.7", + "name": "MiniMax M2.7 (NovitaAI)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.06 + }, + "limit": { + "context": 204800, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-235b-a22b-fp8", + "name": "Qwen3 235B A22B FP8 (NovitaAI)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-28", + "last_updated": "2025-04-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 40960, + "output": 20000 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507 (NovitaAI)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-21", + "last_updated": "2025-07-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.58 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22B Thinking 2507 (NovitaAI)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 3.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-coder-30b-a3b-instruct", + "name": "Qwen3 Coder 30B A3B Instruct (NovitaAI)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.27 + }, + "limit": { + "context": 160000, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct (NovitaAI)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.38, + "output": 1.55 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-max", + "name": "Qwen3 Max (NovitaAI)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.845, + "output": 3.38 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-next-80b-a3b-instruct", + "name": "Qwen3 Next 80B A3B Instruct (NovitaAI)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.5 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-vl-235b-a22b-instruct", + "name": "Qwen3 VL 235B A22B Instruct (NovitaAI)", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.5 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-vl-235b-a22b-thinking", + "name": "Qwen3 VL 235B A22B Thinking (NovitaAI)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.98, + "output": 3.95 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/qwen3-vl-30b-a3b-instruct", + "name": "Qwen3 VL 30B A3B Instruct (NovitaAI)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-05", + "last_updated": "2025-10-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.7 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/novita/qwen3.6-35b-a3b", + "name": "Qwen3.6 35B A3B (NovitaAI)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-17", + "last_updated": "2026-04-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.248, + "output": 1.485 + }, + "limit": { + "context": 262144, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/novita/qwen3.7-max", + "name": "Qwen3.7 Max (NovitaAI)", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-21", + "last_updated": "2026-05-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 3.75, + "cache_read": 0.25 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/novita/qwen3.8-max", + "name": "Qwen3.8 Max (NovitaAI)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.25 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/novita/qwen35-397b-a17b", + "name": "Qwen3.5 397B A17B (NovitaAI)", + "family": "qwen3.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 262144, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-3.5-turbo", + "name": "GPT-3.5 Turbo (OpenAI)", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2021-09-01", + "release_date": "2023-03-01", + "last_updated": "2023-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 16385, + "output": 4096 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4", + "name": "GPT-4 (OpenAI)", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-11", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 60.0 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4-turbo", + "name": "GPT-4 Turbo (OpenAI)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 30.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4.1", + "name": "GPT-4.1 (OpenAI)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4.1-mini", + "name": "GPT-4.1 Mini (OpenAI)", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6, + "cache_read": 0.1 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4.1-nano", + "name": "GPT-4.1 Nano (OpenAI)", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.025 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4o", + "name": "GPT-4o (OpenAI)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-08-06", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4o-mini", + "name": "GPT-4o Mini (OpenAI)", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.075 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4o-mini-transcribe", + "name": "GPT-4o Mini Transcribe (OpenAI)", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-20", + "last_updated": "2025-03-20", + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 5.0 + }, + "limit": { + "context": 16000, + "output": 2000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-4o-transcribe", + "name": "GPT-4o Transcribe (OpenAI)", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-20", + "last_updated": "2025-03-20", + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0 + }, + "limit": { + "context": 16000, + "output": 2000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5", + "name": "GPT-5 (OpenAI)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5-mini", + "name": "GPT-5 Mini (OpenAI)", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5-nano", + "name": "GPT-5 Nano (OpenAI)", + "family": "gpt-nano", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.005 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5-pro", + "name": "GPT-5 Pro (OpenAI)", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-10-06", + "last_updated": "2025-10-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 120.0 + }, + "limit": { + "context": 400000, + "output": 272000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.1", + "name": "GPT-5.1 (OpenAI)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.2", + "name": "GPT-5.2 (OpenAI)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.2-pro", + "name": "GPT-5.2 Pro (OpenAI)", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 21.0, + "output": 168.0 + }, + "limit": { + "context": 400000, + "output": 272000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.3-codex", + "name": "GPT-5.3 Codex (OpenAI)", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.4", + "name": "GPT-5.4 (OpenAI)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 15.0, + "cache_read": 0.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.4-mini", + "name": "GPT-5.4 Mini (OpenAI)", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 4.5, + "cache_read": 0.075 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.4-nano", + "name": "GPT-5.4 Nano (OpenAI)", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.25, + "cache_read": 0.02 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.4-pro", + "name": "GPT-5.4 Pro (OpenAI)", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 180.0 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.5", + "name": "GPT-5.5 (OpenAI)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.5-pro", + "name": "GPT-5.5 Pro (OpenAI)", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 180.0 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.6-luna", + "name": "GPT-5.6 Luna (OpenAI)", + "family": "gpt-luna", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.2, + "cache_read": 0.02, + "cache_write": 0.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.6-sol", + "name": "GPT-5.6 Sol (OpenAI)", + "family": "gpt-sol", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/gpt-5.6-terra", + "name": "GPT-5.6 Terra (OpenAI)", + "family": "gpt-terra", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/openai/o1", + "name": "o1 (OpenAI)", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2024-12-05", + "last_updated": "2024-12-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 60.0, + "cache_read": 7.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "llmgateway-providers/openai/o3", + "name": "o3 (OpenAI)", + "family": "o", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "llmgateway-providers/openai/o3-mini", + "name": "o3 Mini (OpenAI)", + "family": "o-mini", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2024-12-20", + "last_updated": "2025-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "llmgateway-providers/openai/o4-mini", + "name": "o4 Mini (OpenAI)", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.275 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "llmgateway-providers/permafrost/kimi-k3", + "name": "Kimi K3 (Permafrost)", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.6 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, + { + "id": "llmgateway-providers/perplexity/sonar", + "name": "Sonar (Perplexity)", + "family": "sonar", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 1.0 + }, + "limit": { + "context": 130000, + "output": 4096 + } + }, + { + "id": "llmgateway-providers/perplexity/sonar-pro", + "name": "Sonar Pro (Perplexity)", + "family": "sonar-pro", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/perplexity/sonar-reasoning-pro", + "name": "Sonar Reasoning Pro (Perplexity)", + "family": "sonar-reasoning", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "llmgateway-providers/quartz/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro (Preview) (Quartz)", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/ranoai/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (RanoAI)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.028 + }, + "limit": { + "context": 1000000, + "output": 393216 + } + }, + { + "id": "llmgateway-providers/runware/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (Runware)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.076, + "output": 0.153, + "cache_read": 0.014 + }, + "limit": { + "context": 1048576, + "output": 384000 + } + }, + { + "id": "llmgateway-providers/runware/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (Runware)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.961, + "output": 1.922, + "cache_read": 0.079 + }, + "limit": { + "context": 1048576, + "output": 384000 + } + }, + { + "id": "llmgateway-providers/runware/gemma-4-31b-it", + "name": "Gemma 4 31B IT (Runware)", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.102, + "output": 0.297, + "cache_read": 0.012 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/runware/glm-5.2", + "name": "GLM-5.2 (Runware)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 2.55, + "cache_read": 0.16 + }, + "limit": { + "context": 1024000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/runware/gpt-oss-120b", + "name": "GPT OSS 120B (Runware)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.032, + "output": 0.14, + "cache_read": 0.032 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/runware/kimi-k2.6", + "name": "Kimi K2.6 (Runware)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.05, + "cache_read": 0.13 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/sakana/fugu-ultra", + "name": "Fugu Ultra (Sakana AI)", + "family": "fugu", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-06-15", + "last_updated": "2026-06-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, + { + "id": "llmgateway-providers/scx-ai-gp/glm-5.2", + "name": "GLM-5.2 (SCX.ai)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 1.784, + "cache_read": 0.111 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/scx-ai-gp/glm-5.2-fast", + "name": "GLM-5.2 Turbo (SCX.ai)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.99, + "output": 6.16, + "cache_read": 0.4 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/scx-ai-gp/qwen3.8-max", + "name": "Qwen3.8 Max (SCX.ai)", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.815, + "output": 5.4461, + "cache_read": 0.21, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/scx-ai/gemma-4-31b-it", + "name": "Gemma 4 31B IT (SCX.ai (Turbo))", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.91 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/scx-ai/gpt-oss-120b", + "name": "GPT OSS 120B (SCX.ai (Turbo))", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.17, + "output": 0.55 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/scx-ai/llama-4-maverick-17b-instruct", + "name": "Llama 4 Maverick 17B Instruct (SCX.ai (Turbo))", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.53, + "output": 1.62 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/scx-ai/minimax-m2.7", + "name": "MiniMax M2.7 (SCX.ai (Turbo))", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.48, + "output": 1.79, + "cache_read": 0.05 + }, + "limit": { + "context": 196608, + "output": 196608 + } + }, + { + "id": "llmgateway-providers/scx-ai/qwen3-32b", + "name": "Qwen3 32B (SCX.ai (Turbo))", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.36, + "output": 0.87 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "llmgateway-providers/together-ai/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (Together AI)", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.03 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "llmgateway-providers/together-ai/deepseek-v4-pro", + "name": "DeepSeek V4 Pro (Together AI)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.32, + "output": 3.96, + "cache_read": 0.13 + }, + "limit": { + "context": 1048576, + "output": 163840 + } + }, + { + "id": "llmgateway-providers/together-ai/gemma-4-31b-it", + "name": "Gemma 4 31B IT (Together AI)", + "family": "gemma", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.39, + "output": 0.97 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/together-ai/glm-4.7", + "name": "GLM-4.7 (Together AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 2.0 + }, + "limit": { + "context": 202752, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/together-ai/gpt-oss-120b", + "name": "GPT OSS 120B (Together AI)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/together-ai/gpt-oss-20b", + "name": "GPT OSS 20B (Together AI)", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/together-ai/kimi-k3", + "name": "Kimi K3 (Together AI)", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, + { + "id": "llmgateway-providers/together-ai/minimax-m3", + "name": "MiniMax M3 (Together AI)", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.06 + }, + "limit": { + "context": 524288, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/tundra/kimi-k2.6", + "name": "Kimi K2.6 (Tundra)", + "family": "kimi-k2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.2, + "cache_read": 0.08 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "llmgateway-providers/vertex-anthropic/claude-haiku-4.5", + "name": "Claude Haiku 4.5 (Vertex AI (Anthropic))", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/vertex-anthropic/claude-opus-4.5", + "name": "Claude Opus 4.5 (Vertex AI (Anthropic))", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-11-01", + "last_updated": "2025-11-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "llmgateway-providers/vertex-anthropic/claude-opus-4.6", + "name": "Claude Opus 4.6 (Vertex AI (Anthropic))", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05-31", + "release_date": "2026-02-05", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/vertex-anthropic/claude-opus-4.7", + "name": "Claude Opus 4.7 (Vertex AI (Anthropic))", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/vertex-anthropic/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5 (Vertex AI (Anthropic))", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/vertex-anthropic/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6 (Vertex AI (Anthropic))", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-17", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "llmgateway-providers/vertex-anthropic/claude-sonnet-5", + "name": "Claude Sonnet 5 (Vertex AI (Anthropic))", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-30", + "last_updated": "2026-06-30", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/vertex-openai/deepseek-v3.2", + "name": "DeepSeek V3.2 (Vertex AI (OpenAI-compatible))", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.56, + "output": 1.68, + "cache_read": 0.056 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/vertex-openai/glm-4.7", + "name": "GLM-4.7 (Vertex AI (OpenAI-compatible))", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 202752, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/vertex-openai/glm-5", + "name": "GLM-5 (Vertex AI (OpenAI-compatible))", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.1 + }, + "limit": { + "context": 202752, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/vertex-openai/grok-4-20-non-reasoning", + "name": "Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible))", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-09", + "last_updated": "2026-03-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "llmgateway-providers/vertex-openai/grok-4-20-reasoning", + "name": "Grok 4.20 Reasoning (Vertex AI (OpenAI-compatible))", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-09", + "last_updated": "2026-03-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "llmgateway-providers/vertex-openai/grok-4.6", + "name": "Grok 4.6 (Vertex AI (OpenAI-compatible))", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-01", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.5 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "llmgateway-providers/vertex-openai/kimi-k2-thinking", + "name": "Kimi K2 Thinking (Vertex AI (OpenAI-compatible))", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.06 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/vertex-openai/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI-compatible))", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-21", + "last_updated": "2025-07-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 0.88 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/vertex-openai/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct (Vertex AI (OpenAI-compatible))", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 1.8, + "cache_read": 0.022 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-instruct", + "name": "Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI-compatible))", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-thinking", + "name": "Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI-compatible))", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "llmgateway-providers/xai/grok-4", + "name": "Grok 4 (xAI)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "llmgateway-providers/xai/grok-4-20-beta-0309-non-reasoning", + "name": "Grok 4.20 Beta Non-Reasoning (0309) (xAI)", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-09", + "last_updated": "2026-03-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "llmgateway-providers/xai/grok-4-20-beta-0309-reasoning", + "name": "Grok 4.20 Beta Reasoning (0309) (xAI)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-09", + "last_updated": "2026-03-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "llmgateway-providers/xai/grok-4.3", + "name": "Grok 4.3 (xAI)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-30", + "last_updated": "2026-04-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, + { + "id": "llmgateway-providers/xai/grok-4.5", + "name": "Grok 4.5 (xAI)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-08", + "last_updated": "2026-07-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.3 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "llmgateway-providers/xai/grok-4.6", + "name": "Grok 4.6 (xAI)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-01", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.5 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "llmgateway-providers/xai/grok-build-0.1", + "name": "Grok Build 0.1 (xAI)", + "family": "grok-build", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-20", + "last_updated": "2026-05-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 2.0, + "cache_read": 0.2 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "llmgateway-providers/xiaomi/mimo-v2.5", + "name": "MiMo V2.5 (Xiaomi)", + "family": "mimo", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.0028 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/xiaomi/mimo-v2.5-pro", + "name": "MiMo V2.5 Pro (Xiaomi)", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.435, + "output": 0.87, + "cache_read": 0.0036 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/zai/glm-4-32b-0414-128k", + "name": "GLM-4 32B (0414-128k) (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.5", + "name": "GLM-4.5 (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 128000, + "output": 98304 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.5-air", + "name": "GLM-4.5 Air (Z AI)", + "family": "glm-air", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.1, + "cache_read": 0.03 + }, + "limit": { + "context": 128000, + "output": 98304 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.5-airx", + "name": "GLM-4.5 AirX (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.5, + "cache_read": 0.22 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.5-x", + "name": "GLM-4.5 X (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.2, + "output": 8.9, + "cache_read": 0.45 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.5v", + "name": "GLM-4.5V (Z AI)", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8, + "cache_read": 0.11 + }, + "limit": { + "context": 128000, + "output": 16000 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.6", + "name": "GLM-4.6 (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.6v", + "name": "GLM-4.6V (Z AI)", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9, + "cache_read": 0.05 + }, + "limit": { + "context": 128000, + "output": 16000 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.6v-flashx", + "name": "GLM-4.6V FlashX (Z AI)", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.04, + "output": 0.4, + "cache_read": 0.004 + }, + "limit": { + "context": 128000, + "output": 16000 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.7", + "name": "GLM-4.7 (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/zai/glm-4.7-flashx", + "name": "GLM-4.7 FlashX (Z AI)", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/zai/glm-5", + "name": "GLM-5 (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 202800, + "output": 131100 + } + }, + { + "id": "llmgateway-providers/zai/glm-5.1", + "name": "GLM-5.1 (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-07", + "last_updated": "2026-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/zai/glm-5.2", + "name": "GLM-5.2 (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "llmgateway-providers/zai/glm-5.3", + "name": "GLM-5.3 (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "llmgateway/auto", "name": "Auto Route", @@ -86071,37 +97898,6 @@ "output": 16384 } }, - { - "id": "llmgateway/claude-3-opus", - "name": "Claude 3 Opus", - "family": "claude", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2024-03-04", - "last_updated": "2024-03-04", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 15.0, - "output": 75.0, - "cache_read": 1.5, - "cache_write": 18.75 - }, - "limit": { - "context": 200000, - "output": 4096 - } - }, { "id": "llmgateway/claude-fable-5", "name": "Claude Fable 5", @@ -87645,6 +99441,64 @@ "output": 131072 } }, + { + "id": "llmgateway/glm-5.2-fast", + "name": "GLM-5.2", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.99, + "output": 6.16, + "cache_read": 0.4 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "llmgateway/glm-5.3", + "name": "GLM-5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "llmgateway/gpt-3.5-turbo", "name": "GPT-3.5-turbo", @@ -87893,35 +99747,6 @@ "output": 16384 } }, - { - "id": "llmgateway/gpt-4o-mini-search-preview", - "name": "GPT-4o Mini Search Preview", - "family": "gpt", - "attachment": true, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2024-10-01", - "last_updated": "2024-10-01", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.15, - "output": 0.6 - }, - "limit": { - "context": 128000, - "output": 16384 - } - }, { "id": "llmgateway/gpt-4o-mini-transcribe", "name": "GPT-4o Mini Transcribe", @@ -87951,35 +99776,6 @@ "output": 16000 } }, - { - "id": "llmgateway/gpt-4o-search-preview", - "name": "GPT-4o Search Preview", - "family": "gpt", - "attachment": true, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2024-10-01", - "last_updated": "2024-10-01", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 2.5, - "output": 10.0 - }, - "limit": { - "context": 128000, - "output": 16384 - } - }, { "id": "llmgateway/gpt-4o-transcribe", "name": "GPT-4o Transcribe", @@ -88685,8 +100481,8 @@ }, "open_weights": false, "cost": { - "input": 0.04, - "output": 0.15 + "input": 0.05, + "output": 0.2 }, "limit": { "context": 131072, @@ -89649,7 +101445,7 @@ "cache_read": 0.0028 }, "limit": { - "context": 1000000, + "context": 1048576, "output": 131072 } }, @@ -89679,7 +101475,7 @@ "cache_read": 0.0036 }, "limit": { - "context": 1000000, + "context": 1048576, "output": 131072 } }, @@ -90293,8 +102089,8 @@ "open_weights": true, "cost": { "input": 0.5, - "output": 2.5, - "cache_read": 0.15 + "output": 2.2, + "cache_read": 0.1 }, "limit": { "context": 1048576, @@ -90799,8 +102595,8 @@ }, "open_weights": true, "cost": { - "input": 0.3, - "output": 1.3 + "input": 0.38, + "output": 1.55 }, "limit": { "context": 262144, @@ -90888,10 +102684,10 @@ }, "open_weights": false, "cost": { - "input": 6.0, - "output": 60.0, - "cache_read": 1.2, - "cache_write": 7.5 + "input": 1.0, + "output": 5.0, + "cache_read": 0.2, + "cache_write": 1.25 }, "limit": { "context": 1000000, @@ -91290,7 +103086,7 @@ "cache_write": 0.625 }, "limit": { - "context": 262144, + "context": 1000000, "output": 65536 } }, @@ -91346,7 +103142,7 @@ "cost": { "input": 1.25, "output": 3.75, - "cache_read": 0.125, + "cache_read": 0.25, "cache_write": 3.125 }, "limit": { @@ -91569,34 +103365,6 @@ "output": 8192 } }, - { - "id": "llmgateway/seed-2.1-turbo", - "name": "Seed 2.1 Turbo", - "family": "seed", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-08-10", - "last_updated": "2026-08-10", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.5, - "output": 2.5 - }, - "limit": { - "context": 262144, - "output": 262144 - } - }, { "id": "llmgateway/sonar", "name": "Sonar", @@ -94295,9 +106063,9 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.0028 + "input": 0.22, + "output": 0.66, + "cache_read": 0.007 }, "limit": { "context": 1000000, @@ -94325,9 +106093,9 @@ }, "open_weights": true, "cost": { - "input": 0.435, - "output": 0.87, - "cache_read": 0.003625 + "input": 0.66, + "output": 1.98, + "cache_read": 0.022 }, "limit": { "context": 1000000, @@ -94927,9 +106695,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-19", - "last_updated": "2026-05-19", + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "modalities": { "input": [ "text", @@ -94961,9 +106729,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-07", - "last_updated": "2026-05-07", + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", "modalities": { "input": [ "text", @@ -96599,8 +108367,8 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, + "input": 4.0, + "output": 24.0, "cache_read": 0.5 }, "limit": { @@ -97741,6 +109509,35 @@ "output": 65536 } }, + { + "id": "merge-gateway/qwen/qwen3.8-2.4t-a95b", + "name": "Qwen3.8 2.4T A95B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.5, + "output": 6.25, + "cache_read": 0.5 + }, + "limit": { + "context": 262144, + "output": 1010000 + } + }, { "id": "merge-gateway/qwen/qwen3.8-max", "name": "Qwen3.8 Max", @@ -97801,6 +109598,36 @@ "output": 250000 } }, + { + "id": "merge-gateway/sakana/sakana-namazu", + "name": "Sakana Namazu", + "family": "sakana-namazu", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.95, + "output": 4.0, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "merge-gateway/thinkingmachines/inkling", "name": "Inkling", @@ -98402,6 +110229,35 @@ "output": 131072 } }, + { + "id": "merge-gateway/zai/glm-5.3", + "name": "GLM-5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.7, + "output": 2.2, + "cache_read": 0.13 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "meta-llama/cerebras-llama-4-maverick-17b-128e-instruct", "name": "Cerebras-Llama-4-Maverick-17B-128E-Instruct", @@ -102508,6 +114364,64 @@ "output": 16384 } }, + { + "id": "nano-gpt/Gemma-4-31B-MeroMero-v2", + "name": "Gemma 4 31B MeroMero v2", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-23", + "last_updated": "2026-08-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 + }, + "limit": { + "context": 65536, + "output": 32768 + } + }, + { + "id": "nano-gpt/Gemma-4-31B-MeroMero-v2:thinking", + "name": "Gemma 4 31B MeroMero v2 Thinking", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 + }, + "limit": { + "context": 65536, + "output": 32768 + } + }, { "id": "nano-gpt/Gemma-4-31B-Queen", "name": "Gemma 4 31B Queen", @@ -103356,64 +115270,6 @@ "output": 1048576 } }, - { - "id": "nano-gpt/TEE/deepseek-v4-pro", - "name": "DeepSeek V4 Pro 0813 TEE", - "family": "deepseek-thinking", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-08-12", - "last_updated": "2026-08-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.32, - "output": 3.96, - "cache_read": 0.132 - }, - "limit": { - "context": 1048576, - "output": 1048576 - } - }, - { - "id": "nano-gpt/TEE/deepseek-v4-pro-0813:thinking", - "name": "DeepSeek V4 Pro 0813 Thinking TEE", - "family": "deepseek-thinking", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-08-12", - "last_updated": "2026-08-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.32, - "output": 3.96, - "cache_read": 0.132 - }, - "limit": { - "context": 1048576, - "output": 1048576 - } - }, { "id": "nano-gpt/TEE/gemma-3-27b-it", "name": "Gemma 3 27B TEE", @@ -103837,8 +115693,7 @@ "modalities": { "input": [ "text", - "image", - "video" + "image" ], "output": [ "text" @@ -104120,6 +115975,37 @@ "output": 131072 } }, + { + "id": "nano-gpt/TEE/qwen3.8-27b", + "name": "Qwen3.8 27B TEE", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 3.0, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "nano-gpt/THUDM/GLM-4-32B", "name": "GLM 4 32B 0414", @@ -104819,34 +116705,6 @@ "output": 5120 } }, - { - "id": "nano-gpt/amazon/nova-micro-v1", - "name": "Amazon Nova Micro 1.0", - "family": "nova-micro", - "attachment": false, - "reasoning": false, - "tool_call": false, - "release_date": "2024-01-01", - "last_updated": "2024-12-03", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.0357, - "output": 0.1394, - "cache_read": 0.01785 - }, - "limit": { - "context": 128000, - "output": 5120 - } - }, { "id": "nano-gpt/amazon/nova-pro-v1", "name": "Amazon Nova Pro 1.0", @@ -107851,6 +119709,36 @@ "output": 131072 } }, + { + "id": "nano-gpt/deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 0.66, + "cache_read": 0.007 + }, + "limit": { + "context": 1048576, + "output": 384000 + } + }, { "id": "nano-gpt/deepseek/deepseek-v4-flash:thinking", "name": "DeepSeek V4 Flash (Thinking)", @@ -107920,7 +119808,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -107929,7 +119817,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.1, "output": 2.5, @@ -109948,16 +121836,18 @@ "family": "gemini-flash", "attachment": true, "reasoning": true, - "tool_call": false, + "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-19", - "last_updated": "2026-05-19", + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "modalities": { "input": [ "text", "image", - "audio" + "video", + "audio", + "pdf" ], "output": [ "text" @@ -109965,13 +121855,13 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075, - "cache_write": 0.041667 + "input": 0.375, + "output": 1.875, + "cache_read": 0.0375, + "cache_write": 0.020833 }, "limit": { - "context": 1048756, + "context": 1048576, "output": 65536 } }, @@ -109983,9 +121873,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-07", - "last_updated": "2026-05-07", + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", "modalities": { "input": [ "text", @@ -110062,9 +121952,9 @@ }, "open_weights": true, "cost": { - "input": 0.13, - "output": 0.4, - "cache_read": 0.065 + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 }, "limit": { "context": 262144, @@ -110101,6 +121991,64 @@ "output": 131072 } }, + { + "id": "nano-gpt/google/gemma-4-26b-a4b-uncensored", + "name": "Gemma 4 26B A4B Uncensored", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-22", + "last_updated": "2026-08-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "nano-gpt/google/gemma-4-26b-a4b-uncensored:thinking", + "name": "Gemma 4 26B A4B Uncensored Thinking", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, { "id": "nano-gpt/google/gemma-4-31b-it", "name": "Gemma 4 31B", @@ -110122,9 +122070,9 @@ }, "open_weights": true, "cost": { - "input": 0.1, - "output": 0.35, - "cache_read": 0.05 + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 }, "limit": { "context": 262144, @@ -110475,62 +122423,6 @@ "output": 131072 } }, - { - "id": "nano-gpt/inclusionai/ling-2.6-1t", - "name": "Ling 2.6 1T", - "family": "ling", - "attachment": false, - "reasoning": false, - "tool_call": true, - "release_date": "2026-04-23", - "last_updated": "2026-04-23", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.3, - "output": 2.5, - "cache_read": 0.06 - }, - "limit": { - "context": 262144, - "output": 32768 - } - }, - { - "id": "nano-gpt/inclusionai/ling-2.6-flash", - "name": "Ling 2.6 Flash", - "family": "ling", - "attachment": false, - "reasoning": false, - "tool_call": true, - "release_date": "2026-04-21", - "last_updated": "2026-04-21", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.1, - "output": 0.3, - "cache_read": 0.02 - }, - "limit": { - "context": 262144, - "output": 32768 - } - }, { "id": "nano-gpt/inclusionai/ling-3.0-flash", "name": "Ling 3.0 Flash", @@ -110587,34 +122479,6 @@ "output": 32768 } }, - { - "id": "nano-gpt/inclusionai/ring-2.6-1t", - "name": "Ring 2.6 1T", - "family": "ring", - "attachment": false, - "reasoning": true, - "tool_call": true, - "release_date": "2026-05-08", - "last_updated": "2026-05-08", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.3, - "output": 2.5, - "cache_read": 0.06 - }, - "limit": { - "context": 262144, - "output": 65536 - } - }, { "id": "nano-gpt/inflatebot/MN-12B-Mag-Mell-R1", "name": "Mag Mell R1", @@ -113315,10 +125179,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -114219,10 +126083,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -114252,10 +126116,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -114349,10 +126213,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -114794,6 +126658,180 @@ "output": 100000 } }, + { + "id": "nano-gpt/ornith-ai/ornith-1.5-35b-a3b", + "name": "Ornith 1.5 35B", + "family": "ornith", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-20", + "last_updated": "2026-08-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.05 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "nano-gpt/ornith-ai/ornith-1.5-35b-a3b:thinking", + "name": "Ornith 1.5 35B Thinking", + "family": "ornith", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-20", + "last_updated": "2026-08-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.05 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "nano-gpt/ornith-ai/ornith-1.5-397b", + "name": "Ornith 1.5 397B", + "family": "ornith", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.9, + "output": 3.6, + "cache_read": 0.045 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "nano-gpt/ornith-ai/ornith-1.5-397b:thinking", + "name": "Ornith 1.5 397B Thinking", + "family": "ornith", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.9, + "output": 3.6, + "cache_read": 0.045 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "nano-gpt/ornith-ai/ornith-1.5-9b", + "name": "Ornith 1.5 9B", + "family": "ornith", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-23", + "last_updated": "2026-08-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.1, + "cache_read": 0.025 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "nano-gpt/ornith-ai/ornith-1.5-9b:thinking", + "name": "Ornith 1.5 9B Thinking", + "family": "ornith", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.1, + "cache_read": 0.025 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, { "id": "nano-gpt/pamanseau/OpenReasoning-Nemotron-32B", "name": "OpenReasoning Nemotron 32B", @@ -115945,6 +127983,122 @@ "output": 65536 } }, + { + "id": "nano-gpt/qwen/qwen3.6-35b-a3b-uncensored", + "name": "Qwen 3.6 35B A3B Uncensored", + "family": "qwen3.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 65536, + "output": 32768 + } + }, + { + "id": "nano-gpt/qwen/qwen3.6-35b-a3b-uncensored:thinking", + "name": "Qwen 3.6 35B A3B Uncensored Thinking", + "family": "qwen3.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 65536, + "output": 32768 + } + }, + { + "id": "nano-gpt/qwen/qwen3.8-27b-obliterated", + "name": "Qwen 3.8 27B Obliterated", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.18, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "nano-gpt/qwen/qwen3.8-27b-obliterated:thinking", + "name": "Qwen 3.8 27B Obliterated Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.18, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "nano-gpt/qwen25-vl-72b-instruct", "name": "Qwen25 VL 72b", @@ -117230,6 +129384,35 @@ "output": 8192 } }, + { + "id": "nano-gpt/stealth/ox-alpha", + "name": "Ox Alpha", + "family": "alpha", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.05, + "cache_read": 0.025 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, { "id": "nano-gpt/step-r1-v-mini", "name": "Step R1 V Mini", @@ -117747,12 +129930,12 @@ "open_weights": true, "cost": { "input": 0.4, - "output": 0.4, - "cache_read": 0.2 + "output": 1.8, + "cache_read": 0.4 }, "limit": { "context": 128000, - "output": 16384 + "output": 8192 } }, { @@ -127831,6 +140014,36 @@ "output": 262144 } }, + { + "id": "nvidia/moonshotai/kimi-k3", + "name": "Kimi K3", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "nvidia/nvidia/active-speaker-detection", "name": "Active Speaker Detection", @@ -130287,10 +142500,10 @@ }, "open_weights": false, "cost": { - "input": 2.0, - "output": 12.0, + "input": 2.15, + "output": 12.86, "cache_read": 0.2, - "cache_write": 2.0 + "cache_write": 1.17 }, "limit": { "context": 262144, @@ -130393,6 +142606,38 @@ "output": 64000 } }, + { + "id": "ofox/bailian/qwen3.8-27b", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 3.2, + "cache_read": 0.05, + "cache_write": 0.5625 + }, + "limit": { + "context": 1131072, + "output": 131072 + } + }, { "id": "ofox/bailian/qwen3.8-max", "name": "Qwen3.8 Max", @@ -130486,6 +142731,36 @@ "output": 384000 } }, + { + "id": "ofox/deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.44, + "output": 1.32, + "cache_read": 0.014 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "ofox/deepseek/deepseek-v4-pro", "name": "DeepSeek V4 Pro", @@ -130821,10 +143096,45 @@ }, "open_weights": false, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15, - "cache_write": 0.083 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075, + "cache_write": 0.0415 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "ofox/google/gemini-3.7-flash", + "name": "Gemini 3.7 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075, + "cache_write": 0.0415 }, "limit": { "context": 1048576, @@ -131880,10 +144190,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 2.5, + "output": 15.0, + "cache_read": 0.25, + "cache_write": 3.125 }, "limit": { "context": 1050000, @@ -132190,10 +144500,10 @@ }, "open_weights": false, "cost": { - "input": 0.884, - "output": 4.42, - "cache_read": 0.177, - "cache_write": 0.0025 + "input": 0.7072, + "output": 3.536, + "cache_read": 0.1416, + "cache_write": 0.002 }, "limit": { "context": 256000, @@ -132222,10 +144532,10 @@ }, "open_weights": false, "cost": { - "input": 0.442, - "output": 2.212, - "cache_read": 0.085, - "cache_write": 0.0024 + "input": 0.3536, + "output": 1.7696, + "cache_read": 0.068, + "cache_write": 0.0019 }, "limit": { "context": 256000, @@ -132388,6 +144698,67 @@ "output": 30000 } }, + { + "id": "ofox/x-ai/grok-4.5", + "name": "Grok 4.5", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-08", + "last_updated": "2026-07-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.3 + }, + "limit": { + "context": 500000, + "output": 65536 + } + }, + { + "id": "ofox/x-ai/grok-4.6", + "name": "Grok 4.6", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-01", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.5 + }, + "limit": { + "context": 500000, + "output": 65536 + } + }, { "id": "ofox/z-ai/glm-4.6", "name": "GLM-4.6", @@ -132585,9 +144956,38 @@ }, "open_weights": true, "cost": { - "input": 1.4, - "output": 4.4, - "cache_read": 0.26 + "input": 0.98, + "output": 3.08, + "cache_read": 0.182 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "ofox/z-ai/glm-5.3", + "name": "GLM-5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.26, + "output": 3.96, + "cache_read": 0.234 }, "limit": { "context": 1000000, @@ -134508,6 +146908,36 @@ "output": 384000 } }, + { + "id": "opencode-go/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 0.66, + "cache_read": 0.007 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "opencode-go/deepseek-v4-pro", "name": "DeepSeek V4 Pro (New)", @@ -134658,7 +147088,7 @@ }, { "id": "opencode-go/gpt-5.6-luna", - "name": "GPT-5.6 Luna (2x usage)", + "name": "GPT-5.6 Luna", "family": "gpt-luna", "attachment": true, "reasoning": true, @@ -134679,10 +147109,10 @@ }, "open_weights": false, "cost": { - "input": 0.1, - "output": 0.6, - "cache_read": 0.01, - "cache_write": 0.125 + "input": 0.2, + "output": 1.2, + "cache_read": 0.02, + "cache_write": 0.25 }, "limit": { "context": 1050000, @@ -134721,7 +147151,7 @@ }, { "id": "opencode-go/hy3", - "name": "Hy3", + "name": "Hy3 (8x usage)", "family": "Hy", "attachment": false, "reasoning": true, @@ -134739,9 +147169,9 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 0.58, - "cache_read": 0.035 + "input": 0.0175, + "output": 0.0725, + "cache_read": 0.004375 }, "limit": { "context": 256000, @@ -134875,6 +147305,35 @@ "output": 131072 } }, + { + "id": "opencode-go/longcat-2.0", + "name": "LongCat-2.0", + "family": "longcat", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-30", + "last_updated": "2026-06-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.006 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "opencode-go/mimo-v2-omni", "name": "MiMo V2 Omni", @@ -135093,6 +147552,69 @@ "output": 131072 } }, + { + "id": "opencode-go/muse-spark-1.2-contributor", + "name": "Muse Spark 1.2 Contributor", + "family": "muse", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-05", + "last_updated": "2026-08-05", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.2, + "cache_read": 0.002 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "opencode-go/ox-alpha-free", + "name": "Ox Alpha Free (Unlimited)", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "opencode-go/qwen3.5-plus", "name": "Qwen3.5 Plus", @@ -136819,7 +149341,7 @@ }, { "id": "opencode/gpt-5.6-sol", - "name": "GPT-5.6 Sol", + "name": "GPT-5.6 Sol (50% Off)", "family": "gpt-sol", "attachment": true, "reasoning": true, @@ -136840,10 +149362,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -137799,6 +150321,39 @@ "output": 131072 } }, + { + "id": "opencode/muse-spark-1.2-contributor-free", + "name": "Muse Spark 1.2 Free", + "family": "muse-free", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-05", + "last_updated": "2026-08-05", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "opencode/nemotron-3-super-free", "name": "Nemotron 3 Super Free", @@ -138103,32 +150658,33 @@ } }, { - "id": "openrouter/ai21/jamba-large-1.7", - "name": "Jamba Large 1.7", - "family": "jamba", - "attachment": false, - "reasoning": false, + "id": "opencode/x-preview-f-free", + "name": "Ox Alpha Free (Unlimited)", + "attachment": true, + "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-08-31", - "release_date": "2025-08-08", - "last_updated": "2025-08-08", + "release_date": "2026-08-21", + "last_updated": "2026-08-21", "modalities": { "input": [ - "text" + "text", + "image", + "video" ], "output": [ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 2.0, - "output": 8.0 + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 }, "limit": { - "context": 256000, - "output": 4096 + "context": 1000000, + "output": 131072 } }, { @@ -139480,34 +152036,6 @@ "output": 64000 } }, - { - "id": "openrouter/deepcogito/cogito-v2.1-671b", - "name": "Cogito v2.1 671B", - "family": "cogito", - "attachment": false, - "reasoning": true, - "tool_call": false, - "temperature": true, - "release_date": "2025-11-13", - "last_updated": "2025-11-13", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 1.25 - }, - "limit": { - "context": 128000, - "output": 128000 - } - }, { "id": "openrouter/deepseek/deepseek-chat", "name": "DeepSeek Chat", @@ -139558,13 +152086,12 @@ }, "open_weights": true, "cost": { - "input": 0.27, - "output": 1.12, - "cache_read": 0.135 + "input": 0.25, + "output": 1.0 }, "limit": { "context": 163840, - "output": 65536 + "output": 163840 } }, { @@ -139588,13 +152115,13 @@ }, "open_weights": true, "cost": { - "input": 0.25, - "output": 0.95, - "cache_read": 0.13 + "input": 0.55, + "output": 1.65, + "cache_read": 0.55 }, "limit": { "context": 163840, - "output": 32768 + "output": 161000 } }, { @@ -139677,11 +152204,12 @@ "open_weights": true, "cost": { "input": 0.27, - "output": 1.0 + "output": 1.0, + "cache_read": 0.135 }, "limit": { "context": 163840, - "output": 163840 + "output": 32768 } }, { @@ -139705,13 +152233,13 @@ }, "open_weights": true, "cost": { - "input": 0.269, - "output": 0.4, - "cache_read": 0.1345 + "input": 0.26, + "output": 0.38, + "cache_read": 0.13 }, "limit": { "context": 163840, - "output": 65536 + "output": 163840 } }, { @@ -139764,9 +152292,39 @@ }, "open_weights": true, "cost": { - "input": 0.0686, - "output": 0.1372, - "cache_read": 0.01372 + "input": 0.056, + "output": 0.112, + "cache_read": 0.0112 + }, + "limit": { + "context": 1048576, + "output": 384000 + } + }, + { + "id": "openrouter/deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 0.66, + "cache_read": 0.007 }, "limit": { "context": 1048576, @@ -139794,9 +152352,9 @@ }, "open_weights": true, "cost": { - "input": 0.66, - "output": 1.98, - "cache_read": 0.022 + "input": 0.522, + "output": 1.044, + "cache_read": 0.0435 }, "limit": { "context": 1048576, @@ -140264,7 +152822,7 @@ }, "limit": { "context": 65536, - "output": 66000 + "output": 65536 } }, { @@ -140956,64 +153514,6 @@ "output": 50000 } }, - { - "id": "openrouter/inclusionai/ling-2.6-1t", - "name": "Ling-2.6-1T", - "family": "ling", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2026-04-23", - "last_updated": "2026-04-23", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.075, - "output": 0.625, - "cache_read": 0.015 - }, - "limit": { - "context": 262144, - "output": 32768 - } - }, - { - "id": "openrouter/inclusionai/ling-2.6-flash", - "name": "Ling-2.6-flash", - "family": "ling", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2026-04-21", - "last_updated": "2026-04-21", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.01, - "output": 0.03, - "cache_read": 0.002 - }, - "limit": { - "context": 262144, - "output": 32768 - } - }, { "id": "openrouter/inclusionai/ling-3.0-flash", "name": "Ling-3.0-flash", @@ -141043,35 +153543,6 @@ "output": 32768 } }, - { - "id": "openrouter/inclusionai/ring-2.6-1t", - "name": "Ring-2.6-1T", - "family": "ring", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-05-08", - "last_updated": "2026-05-08", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.075, - "output": 0.625, - "cache_read": 0.015 - }, - "limit": { - "context": 262144, - "output": 65536 - } - }, { "id": "openrouter/kwaipilot/kat-coder-air-v2.5", "name": "KAT-Coder-Air V2.5", @@ -141183,7 +153654,7 @@ "output": 0.0 }, "limit": { - "context": 128000, + "context": 65536, "output": 8192 } }, @@ -141578,6 +154049,39 @@ "output": 1048576 } }, + { + "id": "openrouter/meta/muse-spark-1.2-contributor", + "name": "Muse Spark 1.2 Contributor", + "family": "muse", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.2, + "cache_read": 0.002 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, { "id": "openrouter/microsoft/phi-4", "name": "Phi 4", @@ -141800,13 +154304,13 @@ }, "open_weights": true, "cost": { - "input": 0.22, - "output": 0.9, - "cache_read": 0.05 + "input": 0.27, + "output": 1.08, + "cache_read": 0.027 }, "limit": { "context": 204800, - "output": 196608 + "output": 128000 } }, { @@ -141900,6 +154404,37 @@ "output": 256000 } }, + { + "id": "openrouter/mistralai/devstral", + "name": "Devstral 2", + "family": "devstral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-09", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.44, + "output": 2.2, + "cache_read": 0.044 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "openrouter/mistralai/ministral-14b", "name": "Ministral 3 14B 2512", @@ -141962,32 +154497,31 @@ }, { "id": "openrouter/mistralai/ministral-8b", - "name": "Ministral 3 8B 2512", + "name": "Ministral 8B", "family": "ministral", - "attachment": true, + "attachment": false, "reasoning": false, - "tool_call": true, + "tool_call": false, "temperature": true, - "release_date": "2025-12-02", - "last_updated": "2025-12-02", + "knowledge": "2024-09-30", + "release_date": "2024-10-17", + "last_updated": "2024-10-17", "modalities": { "input": [ - "text", - "image" + "text" ], "output": [ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 0.15, - "output": 0.15, - "cache_read": 0.015 + "input": 0.11, + "output": 0.11 }, "limit": { - "context": 262144, - "output": 262144 + "context": 128000, + "output": 128000 } }, { @@ -142287,11 +154821,11 @@ }, "open_weights": true, "cost": { - "input": 0.09375, - "output": 0.25 + "input": 0.075, + "output": 0.2 }, "limit": { - "context": 256000, + "context": 131072, "output": 16384 } }, @@ -142438,9 +154972,9 @@ }, "open_weights": true, "cost": { - "input": 0.57, - "output": 2.85, - "cache_read": 0.095 + "input": 0.6, + "output": 3.0, + "cache_read": 0.1 }, "limit": { "context": 262144, @@ -142469,9 +155003,9 @@ }, "open_weights": true, "cost": { - "input": 0.5605, - "output": 2.36, - "cache_read": 0.0944 + "input": 0.95, + "output": 4.0, + "cache_read": 0.16 }, "limit": { "context": 262144, @@ -142500,9 +155034,9 @@ }, "open_weights": true, "cost": { - "input": 0.71, - "output": 3.5, - "cache_read": 0.15 + "input": 0.67, + "output": 3.4, + "cache_read": 0.19 }, "limit": { "context": 262144, @@ -142801,34 +155335,6 @@ "output": 262144 } }, - { - "id": "openrouter/nvidia/nemotron-3-nano-30b-a3b:free", - "name": "Nemotron 3 Nano 30B A3B (free)", - "family": "nemotron", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2025-12-15", - "last_updated": "2025-12-15", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0, - "output": 0.0 - }, - "limit": { - "context": 256000, - "output": 256000 - } - }, { "id": "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "name": "Nemotron 3 Nano Omni (free)", @@ -143027,7 +155533,7 @@ "cache_read": 0.04 }, "limit": { - "context": 1000000, + "context": 262144, "output": 131072 } }, @@ -143059,64 +155565,6 @@ "output": 65536 } }, - { - "id": "openrouter/nvidia/nemotron-nano-12b-v2-vl:free", - "name": "Nemotron Nano 12B 2 VL (free)", - "family": "nemotron", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2025-10-28", - "last_updated": "2025-10-28", - "modalities": { - "input": [ - "text", - "image", - "video" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0, - "output": 0.0 - }, - "limit": { - "context": 128000, - "output": 128000 - } - }, - { - "id": "openrouter/nvidia/nemotron-nano-9b-v2:free", - "name": "Nemotron Nano 9B V2 (free)", - "family": "nemotron", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2025-08-18", - "last_updated": "2025-08-18", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0, - "output": 0.0 - }, - "limit": { - "context": 128000, - "output": 128000 - } - }, { "id": "openrouter/openai/gpt-3.5-turbo", "name": "GPT-3.5-turbo", @@ -144238,10 +156686,10 @@ }, "open_weights": false, "cost": { - "input": 2.5, - "output": 15.0, - "cache_read": 0.25, - "cache_write": 3.125 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -144271,10 +156719,10 @@ }, "open_weights": false, "cost": { - "input": 2.5, - "output": 15.0, - "cache_read": 0.25, - "cache_write": 3.125 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -144458,9 +156906,8 @@ }, "open_weights": true, "cost": { - "input": 0.03, - "output": 0.17, - "cache_read": 0.03 + "input": 0.037, + "output": 0.17 }, "limit": { "context": 131072, @@ -144496,34 +156943,6 @@ "output": 131072 } }, - { - "id": "openrouter/openai/gpt-oss-20b:free", - "name": "gpt-oss-20b (free)", - "family": "gpt-oss", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2025-08-05", - "last_updated": "2025-08-05", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0, - "output": 0.0 - }, - "limit": { - "context": 131072, - "output": 32768 - } - }, { "id": "openrouter/openai/gpt-oss-safeguard-20b", "name": "gpt-oss-safeguard-20b", @@ -145483,7 +157902,7 @@ "output": 2.3 }, "limit": { - "context": 262144, + "context": 131072, "output": 32768 } }, @@ -145507,12 +157926,12 @@ }, "open_weights": true, "cost": { - "input": 0.13, - "output": 0.52 + "input": 0.12, + "output": 0.5 }, "limit": { "context": 131072, - "output": 8192 + "output": 16384 } }, { @@ -146130,12 +158549,12 @@ }, "open_weights": true, "cost": { - "input": 0.29, - "output": 2.4 + "input": 0.26, + "output": 2.08 }, "limit": { "context": 262144, - "output": 81920 + "output": 262144 } }, { @@ -146190,13 +158609,13 @@ }, "open_weights": true, "cost": { - "input": 0.225, - "output": 1.8, - "cache_read": 0.225 + "input": 0.25, + "output": 1.25, + "cache_read": 0.25 }, "limit": { "context": 262144, - "output": 65536 + "output": 262144 } }, { @@ -146221,12 +158640,13 @@ }, "open_weights": true, "cost": { - "input": 0.39, - "output": 2.34 + "input": 0.5, + "output": 3.6, + "cache_read": 0.3 }, "limit": { "context": 262144, - "output": 65536 + "output": 262144 } }, { @@ -146373,12 +158793,12 @@ }, "open_weights": true, "cost": { - "input": 0.289, - "output": 2.4 + "input": 0.32, + "output": 3.2 }, "limit": { "context": 262144, - "output": 131072 + "output": 81920 } }, { @@ -146625,7 +159045,7 @@ }, "limit": { "context": 1048576, - "output": 262144 + "output": 131072 } }, { @@ -146650,12 +159070,12 @@ }, "open_weights": true, "cost": { - "input": 0.45, - "output": 3.2, + "input": 0.4, + "output": 3.0, "cache_read": 0.05 }, "limit": { - "context": 262144, + "context": 1000000, "output": 131072 } }, @@ -146837,12 +159257,13 @@ { "id": "openrouter/sakana/sakana-namazu", "name": "Sakana Namazu", + "family": "sakana-namazu", "attachment": true, "reasoning": true, "tool_call": true, "temperature": false, - "release_date": "2026-08-11", - "last_updated": "2026-08-11", + "release_date": "2026-08-03", + "last_updated": "2026-08-03", "modalities": { "input": [ "text", @@ -146951,6 +159372,36 @@ "output": 16384 } }, + { + "id": "openrouter/stealth/ox-alpha", + "name": "Ox Alpha", + "family": "alpha", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-20", + "last_updated": "2026-08-20", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "openrouter/stepfun/step-3.5-flash", "name": "Step 3.5 Flash", @@ -147039,6 +159490,90 @@ "output": 131072 } }, + { + "id": "openrouter/tencent/hy-mt2-1.8b", + "name": "Hy-MT2-1.8B", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-08-20", + "last_updated": "2026-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.044, + "output": 0.177 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "openrouter/tencent/hy-mt2-30b-a3b", + "name": "Hy-MT2-30B-A3B", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-08-20", + "last_updated": "2026-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.074, + "output": 0.295 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "openrouter/tencent/hy-mt2-7b", + "name": "Hy-MT2-7B", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-08-19", + "last_updated": "2026-08-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.074, + "output": 0.295 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, { "id": "openrouter/tencent/hy3", "name": "Hy3", @@ -147208,7 +159743,7 @@ }, "limit": { "context": 1024000, - "output": 1024000 + "output": 32768 } }, { @@ -147233,9 +159768,9 @@ }, "open_weights": true, "cost": { - "input": 0.95, + "input": 1.0, "output": 4.05, - "cache_read": 0.16 + "cache_read": 0.17 }, "limit": { "context": 1048576, @@ -147269,7 +159804,67 @@ "cache_read": 0.1 }, "limit": { - "context": 524288, + "context": 1048576, + "output": 262144 + } + }, + { + "id": "openrouter/thinkingmachines/inkling-small:free", + "name": "Inkling Small (free)", + "family": "ling", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-30", + "last_updated": "2026-07-30", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 262144 + } + }, + { + "id": "openrouter/thinkingmachines/inkling:free", + "name": "Inkling (free)", + "family": "ling", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-15", + "last_updated": "2026-07-15", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, "output": 262144 } }, @@ -147298,7 +159893,7 @@ }, "limit": { "context": 6144, - "output": 6144 + "output": 4096 } }, { @@ -147959,9 +160554,9 @@ }, "open_weights": true, "cost": { - "input": 0.462, - "output": 1.452, - "cache_read": 0.0858 + "input": 0.966, + "output": 3.036, + "cache_read": 0.1932 }, "limit": { "context": 1048576, @@ -147974,7 +160569,7 @@ "family": "glm", "attachment": false, "reasoning": true, - "tool_call": false, + "tool_call": true, "temperature": true, "release_date": "2026-06-13", "last_updated": "2026-06-13", @@ -147992,8 +160587,37 @@ "output": 0.0 }, "limit": { - "context": 128000, - "output": 128000 + "context": 256000, + "output": 256000 + } + }, + { + "id": "openrouter/z-ai/glm-5.3", + "name": "GLM-5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1048576, + "output": 131072 } }, { @@ -148176,13 +160800,13 @@ }, "open_weights": false, "cost": { - "input": 0.0783, - "output": 0.1566, - "cache_read": 0.01566 + "input": 0.035, + "output": 0.12, + "cache_read": 0.01 }, "limit": { "context": 1310720, - "output": 262144 + "output": 1048576 } }, { @@ -148309,10 +160933,10 @@ }, "open_weights": false, "cost": { - "input": 2.5, - "output": 15.0, - "cache_read": 0.25, - "cache_write": 3.125 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -148382,6 +161006,1314 @@ "output": 1000000 } }, + { + "id": "openrouter/~z-ai/glm", + "name": "GLM Latest", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-19", + "last_updated": "2026-08-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "opper/anthropic/claude-fable-5", + "name": "Claude Fable 5", + "family": "claude-fable", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 50.0, + "cache_read": 1.0, + "cache_write": 12.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "opper/anthropic/claude-haiku-4.5", + "name": "Claude Haiku 4.5 (latest)", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "opper/anthropic/claude-opus-4.5", + "name": "Claude Opus 4.5 (latest)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "opper/anthropic/claude-opus-4.6", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05-31", + "release_date": "2026-02-05", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "opper/anthropic/claude-opus-4.7", + "name": "Claude Opus 4.7", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "opper/anthropic/claude-opus-4.8", + "name": "Claude Opus 4.8", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01", + "release_date": "2026-05-28", + "last_updated": "2026-05-28", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "opper/anthropic/claude-opus-5", + "name": "Claude Opus 5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-05", + "release_date": "2026-07-24", + "last_updated": "2026-07-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "opper/anthropic/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5 (latest)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "opper/anthropic/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-17", + "last_updated": "2026-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "opper/anthropic/claude-sonnet-5", + "name": "Claude Sonnet 5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-30", + "last_updated": "2026-06-30", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "opper/gemini/gemini-3-flash-preview", + "name": "Gemini 3 Flash Preview", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opper/gemini/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opper/gemini/gemini-3.5-flash", + "name": "Gemini 3.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-19", + "last_updated": "2026-05-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 9.0, + "cache_read": 0.15 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opper/gemini/gemini-3.5-flash-lite", + "name": "Gemini 3.5 Flash Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opper/meta/muse-spark-1.2", + "name": "Muse Spark 1.2", + "family": "muse", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-05", + "last_updated": "2026-08-05", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 4.25, + "cache_read": 0.15 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "opper/minimax/m3", + "name": "MiniMax-M3", + "family": "minimax", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.4, + "cache_read": 0.12 + }, + "limit": { + "context": 1048576, + "output": 128000 + } + }, + { + "id": "opper/mistral/devstral", + "name": "Devstral 2", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-09", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "opper/mistral/mistral-large", + "name": "Mistral Large 3", + "family": "mistral-large", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2024-11-01", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "opper/mistral/mistral-small", + "name": "Mistral Small 4", + "family": "mistral-small", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-03-16", + "last_updated": "2026-03-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "opper/moonshot/kimi-k3", + "name": "Kimi K3", + "family": "kimi-k3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "opper/openai/gpt-5.3-chat", + "name": "GPT-5.3 Chat (latest)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-03-03", + "last_updated": "2026-03-03", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "opper/openai/gpt-5.3-codex", + "name": "GPT-5.3 Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.4", + "name": "GPT-5.4", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 15.0, + "cache_read": 0.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.4-mini", + "name": "GPT-5.4 mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 4.5, + "cache_read": 0.075 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.4-nano", + "name": "GPT-5.4 nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.25, + "cache_read": 0.02 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.4-pro", + "name": "GPT-5.4 Pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 180.0 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.5", + "name": "GPT-5.5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.5-pro", + "name": "GPT-5.5 Pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 180.0 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.6-luna", + "name": "GPT-5.6 Luna", + "family": "gpt-luna", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.2, + "cache_read": 0.02, + "cache_write": 0.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.6-sol", + "name": "GPT-5.6 Sol", + "family": "gpt-sol", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "opper/openai/gpt-5.6-terra", + "name": "GPT-5.6 Terra", + "family": "gpt-terra", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "opper/perplexity/sonar", + "name": "Sonar", + "family": "sonar", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "opper/perplexity/sonar-pro", + "name": "Sonar Pro", + "family": "sonar-pro", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "opper/perplexity/sonar-reasoning-pro", + "name": "Sonar Reasoning Pro", + "family": "sonar-reasoning", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "opper/vertexai/gemini-3.7-flash", + "name": "Gemini 3.7 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opper/vertexai/gemini-3.7-flash-eu", + "name": "Gemini 3.7 Flash (EU)", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opper/xai/grok-4.3", + "name": "Grok 4.3", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-17", + "last_updated": "2026-04-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 30000 + } + }, + { + "id": "opper/xai/grok-4.5", + "name": "Grok 4.5", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-08", + "last_updated": "2026-07-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.3 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "opper/xai/grok-4.6", + "name": "Grok 4.6", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-01", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.5 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "opper/xai/grok-build-0.1", + "name": "Grok Build 0.1", + "family": "grok-build", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 2.0, + "cache_read": 0.2 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, { "id": "orcarouter/anthropic/claude-haiku-4.5", "name": "Claude Haiku 4.5 (latest)", @@ -149079,9 +163011,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-19", - "last_updated": "2026-05-19", + "knowledge": "2026-03", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "modalities": { "input": [ "text", @@ -149113,9 +163045,9 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-05-07", - "last_updated": "2026-05-07", + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", "modalities": { "input": [ "text", @@ -152111,7 +166043,7 @@ }, "limit": { "context": 204800, - "output": 131072 + "output": 131000 } }, { @@ -152263,7 +166195,7 @@ }, "limit": { "context": 131072, - "output": 16384 + "output": 8192 } }, { @@ -152320,8 +166252,8 @@ "cache_write": 0.2 }, "limit": { - "context": 262144, - "output": 131072 + "context": 32768, + "output": 32768 } }, { @@ -152351,8 +166283,8 @@ "cache_write": 0.2 }, "limit": { - "context": 131072, - "output": 131072 + "context": 40960, + "output": 40960 } }, { @@ -152515,7 +166447,7 @@ }, "limit": { "context": 1050000, - "output": 131072 + "output": 131000 } }, { @@ -153272,8 +167204,8 @@ "cache_write": 0.083333 }, "limit": { - "context": 1048576, - "output": 65535 + "context": 1000000, + "output": 65000 } }, { @@ -153342,8 +167274,8 @@ "cache_write": 0.375 }, "limit": { - "context": 1048576, - "output": 65536 + "context": 1000000, + "output": 64000 } }, { @@ -153377,8 +167309,8 @@ "cache_write": 0.083333 }, "limit": { - "context": 1048576, - "output": 65536 + "context": 1000000, + "output": 64000 } }, { @@ -153890,7 +167822,7 @@ }, "limit": { "context": 400000, - "output": 128000 + "output": 131072 } }, { @@ -154213,8 +168145,8 @@ "cache_write": 0.2 }, "limit": { - "context": 131072, - "output": 16384 + "context": 128000, + "output": 8192 } }, { @@ -154368,8 +168300,8 @@ "cache_write": 0.9 }, "limit": { - "context": 131072, - "output": 131072 + "context": 16384, + "output": 16384 } }, { @@ -154464,7 +168396,7 @@ "cache_write": 1.5 }, "limit": { - "context": 262144, + "context": 256000, "output": 131072 } }, @@ -154614,7 +168546,7 @@ "cache_write": 0.02 }, "limit": { - "context": 131072, + "context": 128000, "output": 128000 } }, @@ -154646,8 +168578,8 @@ "cache_write": 0.15 }, "limit": { - "context": 262144, - "output": 65536 + "context": 32000, + "output": 32000 } }, { @@ -154711,7 +168643,7 @@ "cache_write": 0.95 }, "limit": { - "context": 262144, + "context": 262000, "output": 131072 } }, @@ -154744,7 +168676,7 @@ "cache_write": 0.95 }, "limit": { - "context": 262144, + "context": 256000, "output": 32768 } }, @@ -154836,7 +168768,7 @@ "cache_write": 0.09 }, "limit": { - "context": 1000000, + "context": 256000, "output": 32000 } }, @@ -154870,6 +168802,36 @@ "output": 65000 } }, + { + "id": "pioneer/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", + "name": "Nemotron 3.5 Lightning 30B A3B", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-11", + "last_updated": "2026-08-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 0.5, + "cache_read": 0.5, + "cache_write": 0.5 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, { "id": "pioneer/openai/gpt-oss-120b", "name": "GPT OSS 120B", @@ -155046,8 +169008,8 @@ "cache_write": 1.3 }, "limit": { - "context": 262144, - "output": 65536 + "context": 240000, + "output": 64000 } }, { @@ -155080,7 +169042,7 @@ }, "limit": { "context": 1000000, - "output": 65536 + "output": 64000 } }, { @@ -155109,8 +169071,8 @@ "cache_write": 1.5625 }, "limit": { - "context": 1000000, - "output": 65536 + "context": 991000, + "output": 64000 } }, { @@ -155143,7 +169105,7 @@ }, "limit": { "context": 1000000, - "output": 65536 + "output": 64000 } }, { @@ -155203,7 +169165,7 @@ "cache_write": 0.98 }, "limit": { - "context": 202752, + "context": 202000, "output": 131072 } }, @@ -155233,7 +169195,7 @@ "cache_write": 1.4 }, "limit": { - "context": 1048576, + "context": 1040000, "output": 128000 } }, @@ -162684,10 +176646,43 @@ }, "open_weights": false, "cost": { - "input": 10.0, - "output": 50.0, - "cache_read": 1.0, - "cache_write": 12.5 + "input": 9.0, + "output": 45.0, + "cache_read": 0.9, + "cache_write": 11.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "requesty/claude-fable-5@eu", + "name": "Claude Fable 5 (EU)", + "family": "claude-fable", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 9.9, + "output": 49.5, + "cache_read": 0.99, + "cache_write": 12.375 }, "limit": { "context": 1000000, @@ -162717,10 +176712,10 @@ }, "open_weights": false, "cost": { - "input": 1.0, - "output": 5.0, - "cache_read": 0.1, - "cache_write": 1.25 + "input": 0.9, + "output": 4.5, + "cache_read": 0.09, + "cache_write": 1.125 }, "limit": { "context": 200000, @@ -162750,10 +176745,10 @@ }, "open_weights": false, "cost": { - "input": 1.1, - "output": 5.5, - "cache_read": 0.11, - "cache_write": 1.375 + "input": 0.99, + "output": 4.95, + "cache_read": 0.099, + "cache_write": 1.2375 }, "limit": { "context": 200000, @@ -162783,10 +176778,10 @@ }, "open_weights": false, "cost": { - "input": 15.0, - "output": 75.0, - "cache_read": 1.5, - "cache_write": 18.75 + "input": 13.5, + "output": 67.5, + "cache_read": 1.35, + "cache_write": 16.875 }, "limit": { "context": 200000, @@ -162816,10 +176811,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 25.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.5, + "output": 22.5, + "cache_read": 0.45, + "cache_write": 5.625 }, "limit": { "context": 200000, @@ -162849,10 +176844,10 @@ }, "open_weights": false, "cost": { - "input": 5.5, - "output": 27.5, - "cache_read": 0.55, - "cache_write": 6.875 + "input": 4.95, + "output": 24.75, + "cache_read": 0.495, + "cache_write": 6.1875 }, "limit": { "context": 200000, @@ -162882,10 +176877,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 25.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.5, + "output": 22.5, + "cache_read": 0.45, + "cache_write": 5.625 }, "limit": { "context": 1000000, @@ -162915,10 +176910,10 @@ }, "open_weights": false, "cost": { - "input": 5.5, - "output": 27.5, - "cache_read": 0.55, - "cache_write": 6.875 + "input": 4.95, + "output": 24.75, + "cache_read": 0.495, + "cache_write": 6.1875 }, "limit": { "context": 1000000, @@ -162948,10 +176943,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 25.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.5, + "output": 22.5, + "cache_read": 0.45, + "cache_write": 5.625 }, "limit": { "context": 1000000, @@ -162981,10 +176976,10 @@ }, "open_weights": false, "cost": { - "input": 5.5, - "output": 27.5, - "cache_read": 0.55, - "cache_write": 6.875 + "input": 4.95, + "output": 24.75, + "cache_read": 0.495, + "cache_write": 6.1875 }, "limit": { "context": 1000000, @@ -163014,10 +177009,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 25.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.5, + "output": 22.5, + "cache_read": 0.45, + "cache_write": 5.625 }, "limit": { "context": 1000000, @@ -163047,10 +177042,10 @@ }, "open_weights": false, "cost": { - "input": 5.5, - "output": 27.5, - "cache_read": 0.55, - "cache_write": 6.875 + "input": 4.95, + "output": 24.75, + "cache_read": 0.495, + "cache_write": 6.1875 }, "limit": { "context": 1000000, @@ -163080,10 +177075,10 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 25.0, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 4.5, + "output": 22.5, + "cache_read": 0.45, + "cache_write": 5.625 }, "limit": { "context": 1000000, @@ -163113,10 +177108,10 @@ }, "open_weights": false, "cost": { - "input": 5.5, - "output": 27.5, - "cache_read": 0.55, - "cache_write": 6.875 + "input": 4.95, + "output": 24.75, + "cache_read": 0.495, + "cache_write": 6.1875 }, "limit": { "context": 1000000, @@ -163146,10 +177141,10 @@ }, "open_weights": false, "cost": { - "input": 3.0, - "output": 15.0, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2.7, + "output": 13.5, + "cache_read": 0.27, + "cache_write": 3.375 }, "limit": { "context": 1000000, @@ -163179,10 +177174,10 @@ }, "open_weights": false, "cost": { - "input": 3.3, - "output": 16.5, - "cache_read": 0.3, - "cache_write": 4.125 + "input": 2.97, + "output": 14.85, + "cache_read": 0.27, + "cache_write": 3.7125 }, "limit": { "context": 1000000, @@ -163212,10 +177207,10 @@ }, "open_weights": false, "cost": { - "input": 3.0, - "output": 15.0, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2.7, + "output": 13.5, + "cache_read": 0.27, + "cache_write": 3.375 }, "limit": { "context": 1000000, @@ -163245,10 +177240,10 @@ }, "open_weights": false, "cost": { - "input": 3.3, - "output": 16.5, - "cache_read": 0.3, - "cache_write": 4.125 + "input": 2.97, + "output": 14.85, + "cache_read": 0.27, + "cache_write": 3.7125 }, "limit": { "context": 1000000, @@ -163278,10 +177273,10 @@ }, "open_weights": false, "cost": { - "input": 3.0, - "output": 15.0, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2.7, + "output": 13.5, + "cache_read": 0.27, + "cache_write": 3.375 }, "limit": { "context": 1000000, @@ -163311,10 +177306,10 @@ }, "open_weights": false, "cost": { - "input": 2.0, - "output": 10.0, - "cache_read": 0.2, - "cache_write": 2.5 + "input": 1.8, + "output": 9.0, + "cache_read": 0.18, + "cache_write": 2.25 }, "limit": { "context": 1000000, @@ -163344,10 +177339,10 @@ }, "open_weights": false, "cost": { - "input": 2.2, - "output": 11.0, - "cache_read": 0.22, - "cache_write": 2.75 + "input": 1.98, + "output": 9.9, + "cache_read": 0.198, + "cache_write": 2.475 }, "limit": { "context": 1000000, @@ -163356,15 +177351,15 @@ }, { "id": "requesty/deepseek-v4-flash", - "name": "DeepSeek V4 Flash 0731", + "name": "DeepSeek V4 Flash", "family": "deepseek-flash", "attachment": false, - "reasoning": true, + "reasoning": false, "tool_call": true, "temperature": true, "knowledge": "2025-05", - "release_date": "2026-07-31", - "last_updated": "2026-07-31", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", "modalities": { "input": [ "text" @@ -163375,13 +177370,13 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.07 + "input": 0.396, + "output": 1.188, + "cache_read": 0.0126 }, "limit": { - "context": 1048576, - "output": 131072 + "context": 1000000, + "output": 384000 } }, { @@ -163405,9 +177400,155 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.07 + "input": 0.126, + "output": 0.252, + "cache_read": 0.063 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "requesty/deepseek-v4-pro", + "name": "DeepSeek V4 Pro", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.188, + "output": 3.564, + "cache_read": 0.0396 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, + { + "id": "requesty/deepseek-v4-pro@eu", + "name": "DeepSeek V4 Pro (EU)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.575, + "output": 3.15, + "cache_read": 0.396 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, + { + "id": "requesty/devstral", + "name": "devstral-latest", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2026-05-27", + "last_updated": "2026-05-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.396, + "output": 1.98, + "cache_read": 0.396 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/devstral-latest@eu", + "name": "devstral-latest@eu", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2026-05-27", + "last_updated": "2026-05-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.396, + "output": 1.98, + "cache_read": 0.396 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/fugu-ultra", + "name": "Fugu Ultra", + "family": "fugu", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2026-06-15", + "last_updated": "2026-06-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.5, + "output": 27.0, + "cache_read": 0.45 }, "limit": { "context": 1048576, @@ -163439,10 +177580,111 @@ }, "open_weights": false, "cost": { - "input": 0.3, - "output": 2.5, - "cache_read": 0.075, - "cache_write": 0.55 + "input": 0.27, + "output": 2.25, + "cache_read": 0.0675, + "cache_write": 0.495 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "requesty/gemini-3-pro-image", + "name": "Nano Banana Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-28", + "last_updated": "2026-05-28", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 10.8, + "cache_read": 0.18, + "cache_write": 4.05 + }, + "limit": { + "context": 1048576, + "output": 32768 + } + }, + { + "id": "requesty/gemini-3.1-flash-image", + "name": "Nano Banana 2", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-28", + "last_updated": "2026-05-28", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 1.8 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "requesty/gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-07", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.225, + "output": 1.35, + "cache_read": 0.0225, + "cache_write": 0.074997 }, "limit": { "context": 1048576, @@ -163474,10 +177716,80 @@ }, "open_weights": false, "cost": { - "input": 0.275, - "output": 1.65, - "cache_read": 0.0275, - "cache_write": 0.091663 + "input": 0.2475, + "output": 1.485, + "cache_read": 0.02475, + "cache_write": 0.082497 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "requesty/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 10.8, + "cache_read": 0.18, + "cache_write": 4.05 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "requesty/gemini-3.5-flash", + "name": "Gemini 3.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-19", + "last_updated": "2026-05-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.35, + "output": 8.1, + "cache_read": 0.135, + "cache_write": 1.4247 }, "limit": { "context": 1048576, @@ -163509,9 +177821,43 @@ }, "open_weights": false, "cost": { - "input": 0.3, - "output": 2.5, - "cache_read": 0.03 + "input": 0.27, + "output": 2.25, + "cache_read": 0.027 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "requesty/gemini-3.5-flash-lite@eu", + "name": "Gemini 3.5 Flash Lite (EU)", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03", + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.297, + "output": 2.475, + "cache_read": 0.0297 }, "limit": { "context": 1048576, @@ -163543,10 +177889,10 @@ }, "open_weights": false, "cost": { - "input": 1.65, - "output": 9.9, - "cache_read": 0.165, - "cache_write": 1.7413 + "input": 1.485, + "output": 8.91, + "cache_read": 0.1485, + "cache_write": 1.56717 }, "limit": { "context": 1048576, @@ -163578,9 +177924,9 @@ }, "open_weights": false, "cost": { - "input": 1.5, - "output": 7.0, - "cache_read": 0.15 + "input": 1.35, + "output": 6.3, + "cache_read": 0.135 }, "limit": { "context": 1048576, @@ -163612,9 +177958,9 @@ }, "open_weights": false, "cost": { - "input": 0.75, - "output": 3.75, - "cache_read": 0.075 + "input": 0.6, + "output": 3.0, + "cache_read": 0.06 }, "limit": { "context": 1048576, @@ -163646,15 +177992,132 @@ }, "open_weights": false, "cost": { - "input": 0.825, - "output": 4.125, - "cache_read": 0.0825 + "input": 0.66, + "output": 3.3, + "cache_read": 0.066 }, "limit": { "context": 1048576, "output": 65535 } }, + { + "id": "requesty/gemma-4-26b-a4b-it", + "name": "Gemma 4 26B A4B IT", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.063, + "output": 0.306, + "cache_read": 0.063 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/gemma-4-31b-it", + "name": "Gemma 4 31B IT", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 8192 + } + }, + { + "id": "requesty/glm-5.1", + "name": "GLM-5.1", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-07", + "last_updated": "2026-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.26, + "output": 3.96, + "cache_read": 0.234 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "requesty/glm-5.1@eu", + "name": "GLM-5.1 (EU)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-07", + "last_updated": "2026-04-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.26, + "output": 3.96, + "cache_read": 1.26 + }, + "limit": { + "context": 200000, + "output": 200000 + } + }, { "id": "requesty/glm-5.2", "name": "GLM-5.2", @@ -163675,15 +178138,43 @@ }, "open_weights": true, "cost": { - "input": 1.2, - "output": 4.2, - "cache_read": 0.26 + "input": 1.08, + "output": 3.78, + "cache_read": 0.234 }, "limit": { "context": 1048576, "output": 131072 } }, + { + "id": "requesty/glm-5.2-fast", + "name": "glm-5.2-fast", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-07-13", + "last_updated": "2026-07-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.89, + "output": 5.94, + "cache_read": 0.189 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "requesty/glm-5.2@eu", "name": "GLM-5.2 (EU)", @@ -163704,15 +178195,44 @@ }, "open_weights": true, "cost": { - "input": 1.2, - "output": 4.2, - "cache_read": 0.26 + "input": 1.08, + "output": 3.78, + "cache_read": 0.234 }, "limit": { "context": 1048576, "output": 131072 } }, + { + "id": "requesty/glm-5.3", + "name": "GLM-5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.26, + "output": 3.96, + "cache_read": 0.234 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "requesty/gpt-4.1-mini@eu", "name": "GPT-4.1 mini (EU)", @@ -163736,9 +178256,9 @@ }, "open_weights": false, "cost": { - "input": 0.44, - "output": 1.76, - "cache_read": 0.11 + "input": 0.396, + "output": 1.584, + "cache_read": 0.099 }, "limit": { "context": 1047576, @@ -163767,9 +178287,9 @@ }, "open_weights": false, "cost": { - "input": 0.11, - "output": 0.44, - "cache_read": 0.0275 + "input": 0.099, + "output": 0.396, + "cache_read": 0.02475 }, "limit": { "context": 1047576, @@ -163799,9 +178319,9 @@ }, "open_weights": false, "cost": { - "input": 2.2, - "output": 8.8, - "cache_read": 0.55 + "input": 1.98, + "output": 7.92, + "cache_read": 0.495 }, "limit": { "context": 1047576, @@ -163831,9 +178351,9 @@ }, "open_weights": false, "cost": { - "input": 0.165, - "output": 0.66, - "cache_read": 0.0825 + "input": 0.1485, + "output": 0.594, + "cache_read": 0.07425 }, "limit": { "context": 128000, @@ -163862,9 +178382,9 @@ }, "open_weights": false, "cost": { - "input": 0.275, - "output": 2.2, - "cache_read": 0.0275 + "input": 0.2475, + "output": 1.98, + "cache_read": 0.02475 }, "limit": { "context": 200000, @@ -163893,9 +178413,9 @@ }, "open_weights": false, "cost": { - "input": 0.055, - "output": 0.44, - "cache_read": 0.0055 + "input": 0.0495, + "output": 0.396, + "cache_read": 0.00495 }, "limit": { "context": 200000, @@ -163924,15 +178444,201 @@ }, "open_weights": false, "cost": { - "input": 1.375, - "output": 11.0, - "cache_read": 0.1375 + "input": 1.2375, + "output": 9.9, + "cache_read": 0.12375 }, "limit": { "context": 400000, "output": 128000 } }, + { + "id": "requesty/gpt-5.3-chat", + "name": "gpt-5.3-chat", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.575, + "output": 12.6, + "cache_read": 0.1575 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "requesty/gpt-5.3-codex", + "name": "GPT-5.3 Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.575, + "output": 12.6, + "cache_read": 0.1575 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.4", + "name": "GPT-5.4", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.475, + "output": 14.85, + "cache_read": 0.2475 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.4-mini", + "name": "GPT-5.4 mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.675, + "output": 4.05, + "cache_read": 0.0675 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.4-nano", + "name": "GPT-5.4 nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 1.125, + "cache_read": 0.018 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.4-pro", + "name": "GPT-5.4 Pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 27.0, + "output": 162.0, + "cache_read": 27.0 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, { "id": "requesty/gpt-5.4@eu", "name": "GPT-5.4 (EU)", @@ -163956,9 +178662,72 @@ }, "open_weights": false, "cost": { - "input": 2.5, - "output": 15.0, - "cache_read": 0.25 + "input": 2.25, + "output": 13.5, + "cache_read": 0.225 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.5", + "name": "GPT-5.5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.95, + "output": 29.7, + "cache_read": 0.495 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.5-pro", + "name": "GPT-5.5 Pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 27.0, + "output": 162.0 }, "limit": { "context": 1050000, @@ -163988,9 +178757,41 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 30.0, - "cache_read": 0.5 + "input": 4.5, + "output": 27.0, + "cache_read": 0.45 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.6-luna", + "name": "GPT-5.6 Luna", + "family": "gpt-luna", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 1.08, + "cache_read": 0.018 }, "limit": { "context": 1050000, @@ -164020,9 +178821,42 @@ }, "open_weights": false, "cost": { - "input": 0.22, - "output": 1.32, - "cache_read": 0.022 + "input": 0.198, + "output": 1.188, + "cache_read": 0.0198 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.6-sol", + "name": "GPT-5.6 Sol", + "family": "gpt-sol", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.6, + "output": 18.0, + "cache_read": 0.36, + "cache_write": 4.5 }, "limit": { "context": 1050000, @@ -164052,9 +178886,41 @@ }, "open_weights": false, "cost": { - "input": 5.5, - "output": 33.0, - "cache_read": 0.55 + "input": 4.95, + "output": 29.7, + "cache_read": 0.495 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "requesty/gpt-5.6-terra", + "name": "GPT-5.6 Terra", + "family": "gpt-terra", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 10.8, + "cache_read": 0.18 }, "limit": { "context": 1050000, @@ -164084,9 +178950,9 @@ }, "open_weights": false, "cost": { - "input": 2.2, - "output": 13.2, - "cache_read": 0.22 + "input": 1.98, + "output": 11.88, + "cache_read": 0.198 }, "limit": { "context": 1050000, @@ -164115,15 +178981,77 @@ }, "open_weights": false, "cost": { - "input": 1.375, - "output": 11.0, - "cache_read": 0.1375 + "input": 1.2375, + "output": 9.9, + "cache_read": 0.12375 }, "limit": { "context": 400000, "output": 128000 } }, + { + "id": "requesty/grok-4.2-beta", + "name": "grok-4.2-beta", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-03-19", + "last_updated": "2026-03-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 5.4, + "cache_read": 0.18, + "cache_write": 1.8 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "requesty/grok-4.3", + "name": "Grok 4.3", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-17", + "last_updated": "2026-04-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.125, + "output": 2.25, + "cache_read": 0.18, + "cache_write": 1.125 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, { "id": "requesty/grok-4.5", "name": "Grok 4.5", @@ -164145,16 +179073,322 @@ }, "open_weights": false, "cost": { - "input": 2.0, - "output": 6.0, - "cache_read": 0.5, - "cache_write": 2.0 + "input": 1.8, + "output": 5.4, + "cache_read": 0.45, + "cache_write": 1.8 }, "limit": { "context": 500000, "output": 500000 } }, + { + "id": "requesty/grok-4.6", + "name": "Grok 4.6", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-01", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 5.4, + "cache_read": 0.45, + "cache_write": 1.8 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "requesty/grok-build-0.1", + "name": "Grok Build 0.1", + "family": "grok-build", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.9, + "output": 1.8, + "cache_read": 0.09 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/hy3", + "name": "Hy3", + "family": "Hy", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-06", + "last_updated": "2026-07-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.126, + "output": 0.522, + "cache_read": 0.0315 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/inkling", + "name": "Inkling", + "family": "ling", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-15", + "last_updated": "2026-07-15", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.683, + "output": 4.212, + "cache_read": 0.3366 + }, + "limit": { + "context": 65536, + "output": 32768 + } + }, + { + "id": "requesty/inkling-256k", + "name": "inkling-256k", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.496, + "output": 3.744, + "cache_read": 0.2992 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "requesty/kat-coder-pro", + "name": "kat-coder-pro", + "family": "kat-coder", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2026-03-27", + "last_updated": "2026-03-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 1.08 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/kimi-k2.6", + "name": "Kimi K2.6", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.855, + "output": 3.6, + "cache_read": 0.144 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/kimi-k2.6@eu", + "name": "Kimi K2.6 (EU)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.855, + "output": 3.6, + "cache_read": 0.855 + }, + "limit": { + "context": 256000, + "output": 128000 + } + }, + { + "id": "requesty/kimi-k2.7-code", + "name": "Kimi K2.7 Code", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.855, + "output": 3.6, + "cache_read": 0.171 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/kimi-k2.7-code@eu", + "name": "Kimi K2.7 Code (EU)", + "family": "kimi-k2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.125, + "output": 4.05, + "cache_read": 0.279 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "requesty/kimi-k3", "name": "Kimi K3", @@ -164177,9 +179411,9 @@ }, "open_weights": true, "cost": { - "input": 2.25, - "output": 11.25, - "cache_read": 0.225 + "input": 2.025, + "output": 10.125, + "cache_read": 0.2025 }, "limit": { "context": 1048576, @@ -164208,15 +179442,908 @@ }, "open_weights": true, "cost": { - "input": 2.25, - "output": 11.25, - "cache_read": 0.225 + "input": 2.025, + "output": 10.125, + "cache_read": 0.2025 }, "limit": { "context": 1048576, "output": 262144 } }, + { + "id": "requesty/laguna-m.1", + "name": "Laguna M.1", + "family": "laguna", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-04-28", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "requesty/laguna-xs.2", + "name": "Laguna XS.2", + "family": "laguna", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-04-28", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "requesty/leanstral-1.5", + "name": "leanstral-1-5", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2026-05-27", + "last_updated": "2026-05-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "requesty/leanstral-1.5@eu", + "name": "leanstral-1-5@eu", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2026-05-27", + "last_updated": "2026-05-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "requesty/ling-2.6-1t", + "name": "ling-2.6-1t", + "family": "ling", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 2.25 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/ling-2.6-flash", + "name": "ling-2.6-flash", + "family": "ling", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.27 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/ling-3.0-tiny", + "name": "ling-3.0-tiny", + "family": "ling", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-05", + "last_updated": "2026-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "requesty/mimo-v2.5", + "name": "MiMo-V2.5", + "family": "mimo", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.126, + "output": 0.252, + "cache_read": 0.00252 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "requesty/mimo-v2.5-pro", + "name": "MiMo-V2.5-Pro", + "family": "mimo", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3915, + "output": 0.783, + "cache_read": 0.00324 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "requesty/minimax-m2.7", + "name": "MiniMax-M2.7", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.08, + "cache_read": 0.054, + "cache_write": 1.08 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "requesty/minimax-m2.7-highspeed", + "name": "MiniMax-M2.7-highspeed", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.54, + "output": 2.16, + "cache_read": 0.054, + "cache_write": 1.08 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "requesty/minimax-m3", + "name": "MiniMax-M3", + "family": "minimax", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.24, + "output": 0.96, + "cache_read": 0.048 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "requesty/minimax-m3@eu", + "name": "MiniMax-M3 (EU)", + "family": "minimax", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-01", + "last_updated": "2026-06-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.36, + "output": 1.8, + "cache_read": 0.09 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, + { + "id": "requesty/mistral-medium", + "name": "Mistral Medium (latest)", + "family": "mistral-medium", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-29", + "last_updated": "2026-04-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.396, + "output": 1.98, + "cache_read": 0.396 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "requesty/mistral-medium-3.5", + "name": "mistral-medium-3-5", + "family": "mistral-medium", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-04-30", + "last_updated": "2026-04-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.485, + "output": 7.425, + "cache_read": 1.485 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/mistral-medium-3.5@eu", + "name": "mistral-medium-3-5@eu", + "family": "mistral-medium", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-04-30", + "last_updated": "2026-04-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.485, + "output": 7.425, + "cache_read": 1.485 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/mistral-medium-latest@eu", + "name": "Mistral Medium (latest) (EU)", + "family": "mistral-medium", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-29", + "last_updated": "2026-04-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.396, + "output": 1.98, + "cache_read": 0.396 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "requesty/mistral-small", + "name": "Mistral Small 4", + "family": "mistral-small", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-03-16", + "last_updated": "2026-03-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1485, + "output": 0.594, + "cache_read": 0.1485 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/mistral-small-2603@eu", + "name": "Mistral Small 4 (EU)", + "family": "mistral-small", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-03-16", + "last_updated": "2026-03-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1485, + "output": 0.594, + "cache_read": 0.1485 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/muse-glimmer-30b", + "name": "Muse Glimmer 30B", + "family": "muse", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-01-04", + "release_date": "2026-08-10", + "last_updated": "2026-08-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 20480 + } + }, + { + "id": "requesty/nemotron-3-nano-omni", + "name": "nemotron-3-nano-omni", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-05-20", + "last_updated": "2026-05-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.054, + "output": 0.216, + "cache_read": 0.054 + }, + "limit": { + "context": 300000, + "output": 300000 + } + }, + { + "id": "requesty/nemotron-3-nano-omni-30b-a3b-reasoning", + "name": "Nemotron 3 Nano Omni 30B A3B Reasoning", + "family": "nemotron", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-28", + "last_updated": "2026-04-28", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 20480 + } + }, + { + "id": "requesty/nemotron-3-nano-omni@eu", + "name": "nemotron-3-nano-omni@eu", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-05-20", + "last_updated": "2026-05-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.054, + "output": 0.216, + "cache_read": 0.054 + }, + "limit": { + "context": 300000, + "output": 300000 + } + }, + { + "id": "requesty/nemotron-3-super-120b-a12b", + "name": "Nemotron 3 Super 120B A12B", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-11", + "last_updated": "2026-03-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "requesty/nemotron-3-ultra-550b-a55b", + "name": "Nemotron 3 Ultra 550B A55B", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-04", + "last_updated": "2026-06-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "requesty/nemotron-3-ultra-nvfp4", + "name": "nemotron-3-ultra-nvfp4", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.54, + "output": 2.16, + "cache_read": 0.108 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/nemotron-3.5-content-safety", + "name": "Nemotron 3.5 Content Safety", + "family": "nemotron", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-06-04", + "last_updated": "2026-06-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "requesty/nemotron-3.5-lightning-30b-a3b", + "name": "nemotron-3.5-lightning-30b-a3b", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-11", + "last_updated": "2026-08-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "requesty/nemotron-lightning-3.5-30b-a3b", + "name": "nemotron-lightning-3.5-30b-a3b", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-15", + "last_updated": "2026-08-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.045, + "output": 0.18, + "cache_read": 0.009 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/nvidia-nemotron-3-super-120b-a12b", + "name": "nvidia-nemotron-3-super-120b-a12b", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-03-11", + "last_updated": "2026-03-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.45 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/nvidia-nemotron-3-ultra", + "name": "nvidia-nemotron-3-ultra", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": false, + "release_date": "2026-06-23", + "last_updated": "2026-06-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 2.25 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, { "id": "requesty/o4-mini@eu", "name": "o4-mini (EU)", @@ -164239,15 +180366,500 @@ }, "open_weights": false, "cost": { - "input": 1.21, - "output": 4.84, - "cache_read": 0.3025 + "input": 1.089, + "output": 4.356, + "cache_read": 0.27225 }, "limit": { "context": 200000, "output": 100000 } }, + { + "id": "requesty/qwen3.5-27b", + "name": "Qwen3.5 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-23", + "last_updated": "2026-02-23", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.234, + "output": 2.34 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/qwen3.5-2b", + "name": "qwen3.5-2b", + "family": "qwen3.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-03-10", + "last_updated": "2026-03-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.018, + "output": 0.09 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/qwen3.5-35b-a3b", + "name": "Qwen3.5 35B-A3B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-23", + "last_updated": "2026-02-23", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.126, + "output": 0.9, + "cache_read": 0.045 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/qwen3.6-plus", + "name": "Qwen3.6 Plus", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 2.7, + "cache_read": 0.045, + "cache_write": 0.5625 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "requesty/qwen3.7-max", + "name": "Qwen3.7 Max", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-21", + "last_updated": "2026-05-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.25, + "output": 6.75, + "cache_read": 0.225, + "cache_write": 2.8125 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "requesty/qwen3.7-plus", + "name": "Qwen3.7 Plus", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-06-02", + "last_updated": "2026-06-02", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 1.12, + "cache_read": 0.028, + "cache_write": 0.35 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "requesty/qwen3.8-2.4T-A95B", + "name": "Qwen3.8 2.4T A95B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.8, + "output": 5.4, + "cache_read": 0.18 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/qwen3.8-max", + "name": "Qwen3.8 Max", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 5.4, + "cache_read": 0.225, + "cache_write": 2.25 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "requesty/ring-2.6-1t", + "name": "ring-2.6-1t", + "family": "ring", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-05-08", + "last_updated": "2026-05-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 2.25 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "requesty/seed-1.8", + "name": "seed-1.8", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-05-27", + "last_updated": "2026-05-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.225, + "output": 1.8, + "cache_read": 0.045 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/seed-2.0-code", + "name": "Seed 2.0 Code", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-14", + "last_updated": "2026-02-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 2.7, + "cache_read": 0.09 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/seed-2.0-mini", + "name": "Seed 2.0 Mini", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-14", + "last_updated": "2026-02-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.36, + "cache_read": 0.018 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/seed-2.0-pro", + "name": "Seed 2.0 Pro", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-14", + "last_updated": "2026-02-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 2.7, + "cache_read": 0.09 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "requesty/step-3.7-flash", + "name": "Step 3.7 Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-03-01", + "release_date": "2026-05-29", + "last_updated": "2026-05-29", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.18, + "output": 1.035, + "cache_read": 0.036 + }, + "limit": { + "context": 262144, + "output": 256000 + } + }, + { + "id": "requesty/thinkingcap-qwen3.6-27b", + "name": "thinkingcap-qwen3.6-27b", + "family": "qwen3.6", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-07-13", + "last_updated": "2026-07-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.36, + "output": 2.7, + "cache_read": 0.234 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "requesty/thinkingcap-qwen3.6-27b@eu", + "name": "thinkingcap-qwen3.6-27b@eu", + "family": "qwen3.6", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-07-13", + "last_updated": "2026-07-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.36, + "output": 2.7, + "cache_read": 0.234 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "routing-run/claude-opus-4.8", "name": "Claude Opus 4.8", @@ -164732,7 +181344,7 @@ "id": "runinfra/Qwen/Qwen3.8-27B", "name": "Qwen3.8 27B", "family": "qwen", - "attachment": false, + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, @@ -164740,7 +181352,8 @@ "last_updated": "2026-08-14", "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -164787,6 +181400,35 @@ "output": 32768 } }, + { + "id": "runinfra/deepseek-ai/DeepSeek-V4-Pro", + "name": "DeepSeek V4 Pro 0813", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-12", + "last_updated": "2026-08-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.9, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, + "output": 32768 + } + }, { "id": "runinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "name": "Nemotron 3.5 Lightning 30B A3B", @@ -164871,6 +181513,37 @@ "output": 1000000 } }, + { + "id": "sakana/sakana-namazu", + "name": "Sakana Namazu", + "family": "sakana-namazu", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.95, + "output": 4.0, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "salad-cloud/qwen3.6-35b-a3b", "name": "Qwen3.6 35B-A3B", @@ -165702,6 +182375,36 @@ "output": 1 } }, + { + "id": "sap-ai-core/gemini-embedding-2", + "name": "Gemini Embedding 2", + "family": "gemini", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-11", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 8192, + "output": 3072 + } + }, { "id": "sap-ai-core/gpt-4.1", "name": "gpt-4.1", @@ -166080,6 +182783,32 @@ "output": 128000 } }, + { + "id": "sap-ai-core/mistralai--mistral-medium", + "name": "Mistral Medium 3.5", + "family": "mistral-medium", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-29", + "last_updated": "2026-04-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "sap-ai-core/mistralai--mistral-medium-instruct", "name": "mistralai--mistral-medium-instruct", @@ -166414,6 +183143,36 @@ "output": 3072 } }, + { + "id": "scaleway/deepseek-v4-flash", + "name": "DeepSeek V4 Flash 0731", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-07-31", + "last_updated": "2026-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.468, + "output": 0.936, + "cache_read": 0.0936 + }, + "limit": { + "context": 256000, + "output": 16384 + } + }, { "id": "scaleway/gemma-4-26b-a4b-it", "name": "Gemma 4 26B A4B IT", @@ -166854,6 +183613,36 @@ "output": 384000 } }, + { + "id": "scnet-token-plan/DeepSeek-V4-Pro", + "name": "DeepSeek V4 Pro", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "scnet-token-plan/GLM-5", "name": "GLM-5", @@ -167180,7 +183969,68 @@ } }, { - "id": "scx/MiniMax-M2.7", + "id": "scnet-token-plan/Qwen3.8-Max", + "name": "Qwen3.8 Max", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "scx-ai/GLM-5.2", + "name": "GLM-5.2", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-13", + "last_updated": "2026-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 1.784, + "cache_read": 0.111 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "scx-ai/MiniMax-M2.7", "name": "MiniMax-M2.7", "family": "minimax", "attachment": false, @@ -167204,12 +184054,44 @@ "cache_read": 0.05 }, "limit": { - "context": 192000, - "output": 64000 + "context": 196608, + "output": 196608 } }, { - "id": "scx/gpt-oss-120b", + "id": "scx-ai/Qwen3.8-Max", + "name": "Qwen3.8 Max", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.815, + "output": 5.4461, + "cache_read": 0.17, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "scx-ai/gpt-oss-120b", "name": "GPT OSS 120B", "family": "gpt-oss", "attachment": false, @@ -173351,9 +190233,9 @@ }, "open_weights": true, "cost": { - "input": 0.7, - "output": 1.9, - "cache_read": 0.125 + "input": 0.3, + "output": 0.7, + "cache_read": 0.06 }, "limit": { "context": 1048576, @@ -173499,7 +190381,8 @@ "open_weights": true, "cost": { "input": 4.0, - "output": 20.0 + "output": 20.0, + "cache_read": 0.8 }, "limit": { "context": 262144, @@ -174835,7 +191718,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -174844,7 +191727,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.0, "output": 0.0, @@ -174887,37 +191770,6 @@ "output": 262144 } }, - { - "id": "umans-ai-coding-plan/umans-glm-5.1", - "name": "GLM 5.1", - "family": "glm", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-04-07", - "last_updated": "2026-04-07", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0, - "output": 0.0, - "cache_read": 0.0, - "cache_write": 0.0 - }, - "limit": { - "context": 204800, - "output": 131072 - } - }, { "id": "umans-ai-coding-plan/umans-glm-5.2", "name": "GLM 5.2", @@ -175114,7 +191966,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-08-12", - "last_updated": "2026-08-12", + "last_updated": "2026-08-22", "modalities": { "input": [ "text" @@ -175123,7 +191975,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.32, "output": 3.96, @@ -175164,36 +192016,6 @@ "output": 32768 } }, - { - "id": "umans-ai/umans-glm-5.1", - "name": "GLM 5.1", - "family": "glm", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-04-07", - "last_updated": "2026-04-07", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 1.4, - "output": 4.4, - "cache_read": 0.29 - }, - "limit": { - "context": 204800, - "output": 131072 - } - }, { "id": "umans-ai/umans-glm-5.2", "name": "GLM 5.2", @@ -177697,33 +194519,6 @@ "output": 32768 } }, - { - "id": "venice/nvidia-nemotron-3.5-lightning-30b-a3b", - "name": "NVIDIA Nemotron 3.5 Lightning 30B", - "family": "nemotron", - "attachment": false, - "reasoning": true, - "tool_call": true, - "release_date": "2026-08-12", - "last_updated": "2026-08-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.1, - "output": 0.25 - }, - "limit": { - "context": 1000000, - "output": 32768 - } - }, { "id": "venice/olafangensan-glm-4.7-flash-heretic", "name": "GLM 4.7 Flash Heretic", @@ -178405,6 +195200,36 @@ "output": 65536 } }, + { + "id": "venice/qwen-3.8-27b", + "name": "Qwen 3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-17", + "last_updated": "2026-08-18", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 3.2 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "venice/qwen-3.8-max", "name": "Qwen 3.8 Max", @@ -178755,6 +195580,36 @@ "output": 65536 } }, + { + "id": "venice/stealth-ox-alpha", + "name": "Ox Alpha", + "family": "alpha", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "venice/venice-uncensored-1.2", "name": "Venice Uncensored 1.2", @@ -178873,6 +195728,35 @@ "output": 32768 } }, + { + "id": "venice/z-ai-glm-5.3", + "name": "GLM 5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-18", + "last_updated": "2026-08-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 5.5, + "cache_read": 0.325 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "venice/z-ai-glm-5v-turbo", "name": "GLM 5V Turbo", @@ -179325,7 +196209,7 @@ "tool_call": true, "temperature": true, "knowledge": "2025-09", - "release_date": "2025-07-22", + "release_date": "2026-02-03", "last_updated": "2026-02-03", "modalities": { "input": [ @@ -179335,7 +196219,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.5, "output": 1.2 @@ -179364,7 +196248,7 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 1.0, "output": 5.0, @@ -179549,7 +196433,7 @@ "tool_call": true, "temperature": true, "knowledge": "2025-04", - "release_date": "2025-09-11", + "release_date": "2025-09", "last_updated": "2025-09", "modalities": { "input": [ @@ -179577,8 +196461,8 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-09", - "release_date": "2025-09-11", + "knowledge": "2025-04", + "release_date": "2025-09", "last_updated": "2025-09", "modalities": { "input": [ @@ -179606,8 +196490,9 @@ "reasoning": false, "tool_call": false, "temperature": true, + "knowledge": "2025-03-31", "release_date": "2025-09-23", - "last_updated": "2026-05-01", + "last_updated": "2025-09-23", "modalities": { "input": [ "text", @@ -179617,7 +196502,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.4, "output": 1.6 @@ -179696,7 +196581,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-02-24", + "release_date": "2026-02-23", "last_updated": "2026-02-23", "modalities": { "input": [ @@ -179756,7 +196641,7 @@ { "id": "vercel/alibaba/qwen3.6-27b", "name": "Qwen 3.6 27B", - "family": "qwen3.6", + "family": "qwen", "attachment": true, "reasoning": true, "tool_call": true, @@ -179773,7 +196658,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.6, "output": 3.6 @@ -179824,7 +196709,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-07-28", + "release_date": "2026-07-15", "last_updated": "2026-07-15", "modalities": { "input": [ @@ -179881,7 +196766,7 @@ { "id": "vercel/alibaba/qwen3.7-plus", "name": "Qwen 3.7 Plus", - "family": "qwen3.7-plus", + "family": "qwen", "attachment": true, "reasoning": true, "tool_call": true, @@ -179919,11 +196804,12 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-08-03", + "release_date": "2026-08-12", "last_updated": "2026-08-12", "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -179953,17 +196839,22 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" ] }, - "open_weights": false, - "cost": {}, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 3.3, + "cache_read": 0.11 + }, "limit": { - "context": 262144, - "output": 262133 + "context": 1000000, + "output": 131072 } }, { @@ -179974,7 +196865,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-08-02", + "release_date": "2026-07-19", "last_updated": "2026-07-19", "modalities": { "input": [ @@ -180389,7 +197280,7 @@ "tool_call": true, "temperature": false, "knowledge": "2026-01-31", - "release_date": "2026-07-01", + "release_date": "2026-06-09", "last_updated": "2026-06-09", "modalities": { "input": [ @@ -180818,7 +197709,7 @@ "tool_call": true, "temperature": false, "knowledge": "2026-01-31", - "release_date": "2026-06-29", + "release_date": "2026-06-30", "last_updated": "2026-06-30", "modalities": { "input": [ @@ -180870,35 +197761,6 @@ "output": 80000 } }, - { - "id": "vercel/arcee-ai/trinity-mini", - "name": "Trinity Mini", - "family": "trinity", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-12-01", - "last_updated": "2025-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.045, - "output": 0.15 - }, - "limit": { - "context": 131072, - "output": 131072 - } - }, { "id": "vercel/bfl/flux-2-flex", "name": "FLUX.2 [flex]", @@ -181287,6 +198149,31 @@ "output": 0 } }, + { + "id": "vercel/bytedance/seedance-2.0-mini", + "name": "Seedance 2.0 Mini", + "family": "seed", + "attachment": true, + "reasoning": false, + "tool_call": false, + "release_date": "2026-06-22", + "last_updated": "2026-06-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/bytedance/seedance-2.5", "name": "Seedance 2.5", @@ -181652,7 +198539,6 @@ "reasoning": false, "tool_call": true, "temperature": true, - "knowledge": "2024-07", "release_date": "2024-12-26", "last_updated": "2024-12-26", "modalities": { @@ -181663,7 +198549,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.27, "output": 1.12, @@ -181682,7 +198568,6 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-07", "release_date": "2025-08-21", "last_updated": "2025-08-21", "modalities": { @@ -181693,7 +198578,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.25, "output": 0.95, @@ -181753,7 +198638,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.28, "output": 0.42, @@ -181796,13 +198681,13 @@ { "id": "vercel/deepseek/deepseek-v4-flash", "name": "DeepSeek V4 Flash", - "family": "deepseek", + "family": "deepseek-flash", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2025-05", - "release_date": "2026-04-23", + "release_date": "2026-04-24", "last_updated": "2026-04-24", "modalities": { "input": [ @@ -181823,16 +198708,46 @@ "output": 384000 } }, + { + "id": "vercel/deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp", + "family": "deepseek-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 0.66, + "cache_read": 0.007 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "vercel/deepseek/deepseek-v4-pro", "name": "DeepSeek V4 Pro", - "family": "deepseek", + "family": "deepseek-thinking", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2025-05", - "release_date": "2026-04-23", + "release_date": "2026-04-24", "last_updated": "2026-04-24", "modalities": { "input": [ @@ -181877,6 +198792,30 @@ "output": 0 } }, + { + "id": "vercel/fish-audio/s1-free", + "name": "S1 (Free)", + "family": "o", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2025-10-20", + "last_updated": "2025-10-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/fish-audio/s2-pro", "name": "S2 Pro", @@ -181901,6 +198840,30 @@ "output": 0 } }, + { + "id": "vercel/fish-audio/s2-pro-free", + "name": "S2 Pro (Free)", + "family": "o", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-03-09", + "last_updated": "2026-03-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/fish-audio/s2.1-pro", "name": "S2.1 Pro", @@ -181925,6 +198888,30 @@ "output": 0 } }, + { + "id": "vercel/fish-audio/s2.1-pro-free", + "name": "S2.1 Pro (Free)", + "family": "o", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-07-28", + "last_updated": "2026-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/fish-audio/transcribe-1", "name": "Transcribe-1", @@ -181949,6 +198936,30 @@ "output": 0 } }, + { + "id": "vercel/fish-audio/transcribe-1-free", + "name": "Transcribe-1 (Free)", + "family": "o", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-03-01", + "last_updated": "2026-03-01", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/google/gemini-2.5-flash", "name": "Gemini 2.5 Flash", @@ -182122,7 +199133,7 @@ "tool_call": false, "temperature": true, "knowledge": "2025-01", - "release_date": "2025-09-01", + "release_date": "2026-05-28", "last_updated": "2026-05-28", "modalities": { "input": [ @@ -182180,7 +199191,7 @@ { "id": "vercel/google/gemini-3.1-flash-image-preview", "name": "Gemini 3.1 Flash Image Preview (Nano Banana 2)", - "family": "gemini", + "family": "gemini-flash", "attachment": true, "reasoning": true, "tool_call": false, @@ -182212,7 +199223,7 @@ { "id": "vercel/google/gemini-3.1-flash-lite", "name": "Gemini 3.1 Flash Lite", - "family": "gemini", + "family": "gemini-flash-lite", "attachment": true, "reasoning": true, "tool_call": true, @@ -182244,7 +199255,7 @@ { "id": "vercel/google/gemini-3.1-flash-lite-image", "name": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)", - "family": "gemini", + "family": "gemini-flash-lite", "attachment": true, "reasoning": true, "tool_call": false, @@ -182276,7 +199287,7 @@ { "id": "vercel/google/gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro Preview", - "family": "gemini", + "family": "gemini-pro", "attachment": true, "reasoning": true, "tool_call": true, @@ -182308,7 +199319,7 @@ { "id": "vercel/google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", - "family": "gemini", + "family": "gemini-flash", "attachment": true, "reasoning": true, "tool_call": true, @@ -182340,7 +199351,7 @@ { "id": "vercel/google/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash Lite", - "family": "gemini", + "family": "gemini-flash-lite", "attachment": true, "reasoning": true, "tool_call": true, @@ -182372,7 +199383,7 @@ { "id": "vercel/google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", - "family": "gemini", + "family": "gemini-flash", "attachment": true, "reasoning": true, "tool_call": true, @@ -182392,9 +199403,9 @@ }, "open_weights": false, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "limit": { "context": 1000000, @@ -182404,7 +199415,7 @@ { "id": "vercel/google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", - "family": "gemini", + "family": "gemini-flash", "attachment": true, "reasoning": true, "tool_call": true, @@ -182436,7 +199447,7 @@ { "id": "vercel/google/gemini-embedding-001", "name": "Gemini Embedding 001", - "family": "gemini-embedding", + "family": "gemini", "attachment": false, "reasoning": false, "tool_call": false, @@ -182462,13 +199473,13 @@ { "id": "vercel/google/gemini-embedding-2", "name": "Gemini Embedding 2", - "family": "gemini-embedding", + "family": "gemini", "attachment": false, "reasoning": false, "tool_call": false, "temperature": true, "knowledge": "2025-11", - "release_date": "2026-03-10", + "release_date": "2026-04-22", "last_updated": "2026-04-22", "modalities": { "input": [ @@ -182535,7 +199546,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.15, "output": 0.6, @@ -182566,7 +199577,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.14, "output": 0.4 @@ -182576,81 +199587,6 @@ "output": 131072 } }, - { - "id": "vercel/google/imagen-4.0-fast-generate-001", - "name": "Imagen 4 Fast", - "family": "imagen", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2025-06-01", - "last_updated": "2025-06", - "modalities": { - "input": [ - "text" - ], - "output": [ - "image" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 480, - "output": 0 - } - }, - { - "id": "vercel/google/imagen-4.0-generate-001", - "name": "Imagen 4", - "family": "imagen", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2025-05-20", - "last_updated": "2025-05-22", - "modalities": { - "input": [ - "text" - ], - "output": [ - "image" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 480, - "output": 0 - } - }, - { - "id": "vercel/google/imagen-4.0-ultra-generate-001", - "name": "Imagen 4 Ultra", - "family": "imagen", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": false, - "release_date": "2025-05-24", - "last_updated": "2025-05-24", - "modalities": { - "input": [ - "text" - ], - "output": [ - "image" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 480, - "output": 0 - } - }, { "id": "vercel/google/text-embedding-005", "name": "Text Embedding 005", @@ -183444,7 +200380,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-07-09", + "release_date": "2026-04-08", "last_updated": "2026-07-09", "modalities": { "input": [ @@ -183592,7 +200528,6 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", "release_date": "2025-12-23", "last_updated": "2025-12-23", "modalities": { @@ -183603,7 +200538,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.3, "output": 1.2, @@ -183664,7 +200599,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.3, "output": 1.2, @@ -183684,7 +200619,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-02-12", + "release_date": "2026-02-13", "last_updated": "2026-02-13", "modalities": { "input": [ @@ -183694,7 +200629,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.6, "output": 2.4, @@ -183769,12 +200704,12 @@ { "id": "vercel/minimax/minimax-m3", "name": "MiniMax M3", - "family": "minimax-m3", + "family": "minimax", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-05-31", + "release_date": "2026-06-01", "last_updated": "2026-06-01", "modalities": { "input": [ @@ -183910,64 +200845,6 @@ "output": 256000 } }, - { - "id": "vercel/mistral/magistral-medium", - "name": "Magistral Medium (latest)", - "family": "magistral-medium", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-06", - "release_date": "2025-03-17", - "last_updated": "2025-03-20", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 2.0, - "output": 5.0 - }, - "limit": { - "context": 128000, - "output": 16384 - } - }, - { - "id": "vercel/mistral/magistral-small", - "name": "Magistral Small", - "family": "magistral-small", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-06", - "release_date": "2025-03-17", - "last_updated": "2025-03-17", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.5, - "output": 1.5 - }, - "limit": { - "context": 128000, - "output": 128000 - } - }, { "id": "vercel/mistral/ministral-14b", "name": "Ministral 14B", @@ -184308,7 +201185,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.47, "output": 2.0, @@ -184328,7 +201205,7 @@ "tool_call": true, "temperature": true, "knowledge": "2025-01", - "release_date": "2026-01-26", + "release_date": "2026-01", "last_updated": "2026-01", "modalities": { "input": [ @@ -184359,7 +201236,7 @@ "tool_call": true, "temperature": true, "knowledge": "2025-01", - "release_date": "2026-04-20", + "release_date": "2026-04-21", "last_updated": "2026-04-21", "modalities": { "input": [ @@ -184402,7 +201279,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.95, "output": 4.0, @@ -184422,7 +201299,7 @@ "tool_call": true, "temperature": true, "knowledge": "2025-01", - "release_date": "2026-06-15", + "release_date": "2026-06-12", "last_updated": "2026-06-12", "modalities": { "input": [ @@ -184434,7 +201311,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.9, "output": 8.0, @@ -184465,7 +201342,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 3.0, "output": 15.0, @@ -184484,7 +201361,7 @@ "reasoning": true, "tool_call": true, "temperature": false, - "release_date": "2026-07-27", + "release_date": "2026-07-16", "last_updated": "2026-07-16", "modalities": { "input": [ @@ -184496,7 +201373,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 4.5, "output": 22.5, @@ -184571,7 +201448,6 @@ "reasoning": true, "tool_call": false, "temperature": true, - "knowledge": "2024-10", "release_date": "2025-12-15", "last_updated": "2025-12-15", "modalities": { @@ -184582,7 +201458,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.05, "output": 0.24 @@ -184610,7 +201486,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.15, "output": 0.65 @@ -184638,7 +201514,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.6, "output": 2.4, @@ -184667,11 +201543,42 @@ "text" ] }, - "open_weights": false, - "cost": {}, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, "limit": { - "context": 262144, - "output": 131072 + "context": 1000000, + "output": 32768 + } + }, + { + "id": "vercel/nvidia/nemotron-3.5-lightning-free", + "name": "Nemotron 3.5 Lightning 30B (Free)", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-11", + "last_updated": "2026-08-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1000000, + "output": 32768 } }, { @@ -184682,7 +201589,6 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", "release_date": "2025-10-28", "last_updated": "2025-10-28", "modalities": { @@ -184694,7 +201600,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.2, "output": 0.6 @@ -184712,7 +201618,6 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", "release_date": "2025-08-18", "last_updated": "2025-08-18", "modalities": { @@ -184723,7 +201628,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.06, "output": 0.23 @@ -184824,6 +201729,38 @@ "output": 32768 } }, + { + "id": "vercel/openai/gpt-4.1-fast", + "name": "GPT-4.1 (Fast)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.5, + "output": 14.0, + "cache_read": 0.875 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, { "id": "vercel/openai/gpt-4.1-mini", "name": "GPT-4.1 mini", @@ -184856,6 +201793,38 @@ "output": 32768 } }, + { + "id": "vercel/openai/gpt-4.1-mini-fast", + "name": "GPT-4.1 mini (Fast)", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.7, + "output": 2.8, + "cache_read": 0.175 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, { "id": "vercel/openai/gpt-4.1-nano", "name": "GPT-4.1 nano", @@ -184887,6 +201856,38 @@ "output": 32768 } }, + { + "id": "vercel/openai/gpt-4.1-nano-fast", + "name": "GPT-4.1 nano (Fast)", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.8, + "cache_read": 0.05 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, { "id": "vercel/openai/gpt-4o", "name": "GPT-4o", @@ -184919,6 +201920,38 @@ "output": 16384 } }, + { + "id": "vercel/openai/gpt-4o-fast", + "name": "GPT-4o (Fast)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-08-06", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.25, + "output": 17.0, + "cache_read": 2.125 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, { "id": "vercel/openai/gpt-4o-mini", "name": "GPT-4o mini", @@ -184952,19 +201985,21 @@ } }, { - "id": "vercel/openai/gpt-4o-mini-search-preview", - "name": "GPT 4o Mini Search Preview", + "id": "vercel/openai/gpt-4o-mini-fast", + "name": "GPT-4o mini (Fast)", "family": "gpt-mini", - "attachment": false, + "attachment": true, "reasoning": false, - "tool_call": false, + "tool_call": true, "temperature": true, "knowledge": "2023-09", - "release_date": "2025-03-12", - "last_updated": "2025-01", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", "modalities": { "input": [ - "text" + "text", + "image", + "pdf" ], "output": [ "text" @@ -184972,8 +202007,9 @@ }, "open_weights": false, "cost": { - "input": 0.15, - "output": 0.6 + "input": 0.25, + "output": 1.0, + "cache_read": 0.125 }, "limit": { "context": 128000, @@ -185070,7 +202106,7 @@ { "id": "vercel/openai/gpt-5-codex", "name": "GPT-5-Codex", - "family": "gpt", + "family": "gpt-codex", "attachment": true, "reasoning": true, "tool_call": true, @@ -185099,6 +202135,38 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5-fast", + "name": "GPT-5 (Fast)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 20.0, + "cache_read": 0.25 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-5-mini", "name": "GPT-5 Mini", @@ -185130,6 +202198,38 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5-mini-fast", + "name": "GPT-5 mini (Fast)", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 3.6, + "cache_read": 0.045 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-5-nano", "name": "GPT-5 Nano", @@ -185164,12 +202264,12 @@ { "id": "vercel/openai/gpt-5-pro", "name": "GPT-5 pro", - "family": "gpt", + "family": "gpt-pro", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", + "knowledge": "2024-09-30", "release_date": "2025-10-06", "last_updated": "2025-10-06", "modalities": { @@ -185195,13 +202295,13 @@ { "id": "vercel/openai/gpt-5.1-codex", "name": "GPT-5.1-Codex", - "family": "gpt", + "family": "gpt-codex", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-11-12", + "knowledge": "2024-09-30", + "release_date": "2025-11-13", "last_updated": "2025-11-13", "modalities": { "input": [ @@ -185227,13 +202327,13 @@ { "id": "vercel/openai/gpt-5.1-codex-max", "name": "GPT 5.1 Codex Max", - "family": "gpt", + "family": "gpt-codex", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-11-19", + "knowledge": "2024-09-30", + "release_date": "2025-11-13", "last_updated": "2025-11-13", "modalities": { "input": [ @@ -185259,13 +202359,13 @@ { "id": "vercel/openai/gpt-5.1-codex-mini", "name": "GPT-5.1 Codex mini", - "family": "gpt", + "family": "gpt-codex", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-11-12", + "knowledge": "2024-09-30", + "release_date": "2025-11-13", "last_updated": "2025-11-13", "modalities": { "input": [ @@ -185321,6 +202421,36 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5.1-thinking-fast", + "name": "GPT 5.1 Thinking (Fast)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2025-11-12", + "last_updated": "2025-11-12", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 20.0, + "cache_read": 0.25 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-5.2", "name": "GPT-5.2", @@ -185361,8 +202491,8 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-12-18", + "knowledge": "2025-08-31", + "release_date": "2025-12-11", "last_updated": "2025-12-11", "modalities": { "input": [ @@ -185386,14 +202516,46 @@ } }, { - "id": "vercel/openai/gpt-5.2-pro", - "name": "GPT 5.2 ", + "id": "vercel/openai/gpt-5.2-fast", + "name": "GPT 5.2 (Fast)", "family": "gpt", "attachment": true, "reasoning": true, "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.5, + "output": 28.0, + "cache_read": 0.35 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5.2-pro", + "name": "GPT 5.2 ", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, "temperature": true, - "knowledge": "2024-10", + "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", "modalities": { @@ -185419,7 +202581,7 @@ { "id": "vercel/openai/gpt-5.3-codex", "name": "GPT 5.3 Codex", - "family": "gpt", + "family": "gpt-codex", "attachment": true, "reasoning": true, "tool_call": true, @@ -185448,6 +202610,38 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5.3-codex-fast", + "name": "GPT 5.3 Codex (Fast)", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.5, + "output": 28.0, + "cache_read": 0.35 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-5.4", "name": "GPT 5.4", @@ -185480,10 +202674,42 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5.4-fast", + "name": "GPT 5.4 (Fast)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-5.4-mini", "name": "GPT 5.4 Mini", - "family": "gpt", + "family": "gpt-mini", "attachment": true, "reasoning": true, "tool_call": true, @@ -185512,10 +202738,42 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5.4-mini-fast", + "name": "GPT 5.4 Mini (Fast)", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 9.0, + "cache_read": 0.15 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-5.4-nano", "name": "GPT 5.4 Nano", - "family": "gpt", + "family": "gpt-nano", "attachment": true, "reasoning": true, "tool_call": true, @@ -185547,7 +202805,7 @@ { "id": "vercel/openai/gpt-5.4-pro", "name": "GPT 5.4 Pro", - "family": "gpt", + "family": "gpt-pro", "attachment": true, "reasoning": true, "tool_call": true, @@ -185584,7 +202842,7 @@ "tool_call": true, "temperature": true, "knowledge": "2025-12-01", - "release_date": "2026-04-24", + "release_date": "2026-04-23", "last_updated": "2026-04-23", "modalities": { "input": [ @@ -185607,16 +202865,48 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5.5-fast", + "name": "GPT 5.5 (Fast)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 12.5, + "output": 75.0, + "cache_read": 1.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-5.5-pro", "name": "GPT 5.5 Pro", - "family": "gpt", + "family": "gpt-pro", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2025-12-01", - "release_date": "2026-04-24", + "release_date": "2026-04-23", "last_updated": "2026-04-23", "modalities": { "input": [ @@ -185671,6 +202961,39 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5.6-luna-fast", + "name": "GPT 5.6 Luna (Fast)", + "family": "gpt-luna", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4, + "cache_read": 0.04, + "cache_write": 0.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-5.6-sol", "name": "GPT 5.6 Sol", @@ -185694,10 +203017,43 @@ }, "open_weights": false, "cost": { - "input": 2.5, - "output": 15.0, - "cache_read": 0.25, - "cache_write": 3.125 + "input": 2.0, + "output": 10.0, + "cache_read": 0.2, + "cache_write": 2.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5.6-sol-fast", + "name": "GPT 5.6 Sol (Fast)", + "family": "gpt-sol", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.0, + "output": 20.0, + "cache_read": 0.4, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -185737,6 +203093,39 @@ "output": 128000 } }, + { + "id": "vercel/openai/gpt-5.6-terra-fast", + "name": "GPT 5.6 Terra (Fast)", + "family": "gpt-terra", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-02-16", + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.0, + "output": 24.0, + "cache_read": 0.4, + "cache_write": 2.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, { "id": "vercel/openai/gpt-image-1", "name": "GPT Image 1", @@ -185745,7 +203134,7 @@ "reasoning": false, "tool_call": false, "temperature": true, - "release_date": "2025-03-25", + "release_date": "2025-04-24", "last_updated": "2025-04-24", "modalities": { "input": [ @@ -185803,7 +203192,7 @@ "reasoning": false, "tool_call": false, "temperature": true, - "release_date": "2025-12-16", + "release_date": "2025-11-25", "last_updated": "2025-11-25", "modalities": { "input": [ @@ -186012,7 +203401,7 @@ "tool_call": false, "temperature": true, "knowledge": "2024-09-30", - "release_date": "2026-07-09", + "release_date": "2026-07-06", "last_updated": "2026-07-06", "modalities": { "input": [ @@ -186156,16 +203545,16 @@ } }, { - "id": "vercel/openai/o3-deep-research", - "name": "o3-deep-research", + "id": "vercel/openai/o3-fast", + "name": "o3 (Fast)", "family": "o", "attachment": true, "reasoning": true, "tool_call": true, - "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-06-26", - "last_updated": "2024-06-26", + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", "modalities": { "input": [ "text", @@ -186178,9 +203567,9 @@ }, "open_weights": false, "cost": { - "input": 10.0, - "output": 40.0, - "cache_read": 2.5 + "input": 3.5, + "output": 14.0, + "cache_read": 0.875 }, "limit": { "context": 200000, @@ -186279,6 +203668,38 @@ "output": 100000 } }, + { + "id": "vercel/openai/o4-mini-fast", + "name": "o4-mini (Fast)", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, { "id": "vercel/openai/text-embedding-3-large", "name": "text-embedding-3-large", @@ -186560,12 +203981,12 @@ { "id": "vercel/poolside/laguna-s-2.1", "name": "Laguna S 2.1", - "family": "laguna-s", + "family": "laguna", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-07-20", + "release_date": "2026-07-21", "last_updated": "2026-07-21", "modalities": { "input": [ @@ -186589,7 +204010,7 @@ { "id": "vercel/poolside/laguna-s-2.1-free", "name": "Laguna S 2.1 Free", - "family": "laguna-s", + "family": "laguna", "attachment": false, "reasoning": true, "tool_call": true, @@ -186867,12 +204288,12 @@ { "id": "vercel/sakana/fugu-ultra", "name": "Fugu Ultra", - "family": "aura", + "family": "fugu", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-06-21", + "release_date": "2026-06-15", "last_updated": "2026-06-15", "modalities": { "input": [ @@ -186923,10 +204344,587 @@ "output": 256000 } }, + { + "id": "vercel/spacexai/grok-4.1-fast-non-reasoning", + "name": "Grok 4.1 Fast Non-Reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, + { + "id": "vercel/spacexai/grok-4.1-fast-reasoning", + "name": "Grok 4.1 Fast Reasoning", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, + { + "id": "vercel/spacexai/grok-4.20-multi-agent", + "name": "Grok 4.20 Multi-Agent", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-03-10", + "last_updated": "2026-03-10", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "vercel/spacexai/grok-4.20-multi-agent-beta", + "name": "Grok 4.20 Multi Agent Beta", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-03-11", + "last_updated": "2026-03-11", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "vercel/spacexai/grok-4.20-non-reasoning", + "name": "Grok 4.20 Non-Reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2026-03-10", + "last_updated": "2026-03-10", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "vercel/spacexai/grok-4.20-non-reasoning-beta", + "name": "Grok 4.20 Beta Non-Reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2026-03-11", + "last_updated": "2026-03-11", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.4 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "vercel/spacexai/grok-4.20-reasoning", + "name": "Grok 4.20 Reasoning", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-03-10", + "last_updated": "2026-03-10", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "vercel/spacexai/grok-4.20-reasoning-beta", + "name": "Grok 4.20 Beta Reasoning", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-03-11", + "last_updated": "2026-03-11", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "vercel/spacexai/grok-4.3", + "name": "Grok 4.3", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-04-30", + "last_updated": "2026-04-30", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, + { + "id": "vercel/spacexai/grok-4.5", + "name": "Grok 4.5", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-07-08", + "last_updated": "2026-07-08", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.3 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "vercel/spacexai/grok-4.6", + "name": "Grok 4.6", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.5 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "vercel/spacexai/grok-build-0.1", + "name": "Grok Build 0.1", + "family": "grok-build", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-05-20", + "last_updated": "2026-05-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 2.0, + "cache_read": 0.2 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "vercel/spacexai/grok-imagine-image", + "name": "Grok Imagine Image", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-01-28", + "last_updated": "2026-01-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/spacexai/grok-imagine-image-2.0", + "name": "Grok Imagine Image 2.0", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-08-07", + "last_updated": "2026-08-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/spacexai/grok-imagine-video", + "name": "Grok Imagine", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-01-28", + "last_updated": "2026-01-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/spacexai/grok-imagine-video-1.5", + "name": "Grok Imagine Video 1.5", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-06-22", + "last_updated": "2026-06-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/spacexai/grok-imagine-video-1.5-preview", + "name": "Grok Imagine Video 1.5 Preview", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-05-30", + "last_updated": "2026-05-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/spacexai/grok-stt", + "name": "Grok STT", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-03-16", + "last_updated": "2026-03-16", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/spacexai/grok-tts", + "name": "Grok TTS", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-03-16", + "last_updated": "2026-03-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/spacexai/grok-voice-think-fast-1.0", + "name": "Grok Voice Think Fast 1.0", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/spacexai/grok-voice-think-fast-2.0", + "name": "Grok Voice Think Fast 2.0", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-07-29", + "last_updated": "2026-07-29", + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/stepfun/step-3.5-flash", "name": "StepFun 3.5 Flash", - "family": "step", "attachment": false, "reasoning": true, "tool_call": true, @@ -186943,7 +204941,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.09, "output": 0.3, @@ -186957,13 +204955,12 @@ { "id": "vercel/stepfun/step-3.7-flash", "name": "Step 3.7 Flash", - "family": "step", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2026-03-01", - "release_date": "2026-05-28", + "release_date": "2026-05-29", "last_updated": "2026-05-29", "modalities": { "input": [ @@ -186974,7 +204971,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.2, "output": 1.15, @@ -186985,10 +204982,91 @@ "output": 256000 } }, + { + "id": "vercel/tencent/hy-mt2-lite", + "name": "Tencent Hy-MT2-Lite", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.044, + "output": 0.177 + }, + "limit": { + "context": 8000, + "output": 4000 + } + }, + { + "id": "vercel/tencent/hy-mt2-plus", + "name": "Tencent Hy-MT2-Plus", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.074, + "output": 0.295 + }, + "limit": { + "context": 8000, + "output": 4000 + } + }, + { + "id": "vercel/tencent/hy-mt2-pro", + "name": "Tencent Hy-MT2-Pro", + "family": "Hy", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-05-21", + "last_updated": "2026-05-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.074, + "output": 0.295 + }, + "limit": { + "context": 8000, + "output": 4000 + } + }, { "id": "vercel/tencent/hy3", "name": "Hy3", - "family": "hy3", + "family": "Hy", "attachment": false, "reasoning": true, "tool_call": true, @@ -187005,13 +205083,13 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 0.58, - "cache_read": 0.035 + "input": 0.132, + "output": 0.528, + "cache_read": 0.033 }, "limit": { - "context": 262144, - "output": 262144 + "context": 256000, + "output": 128000 } }, { @@ -187065,7 +205143,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.5, "output": 1.2, @@ -187376,612 +205454,10 @@ "output": 1536 } }, - { - "id": "vercel/xai/grok-4.1-fast-non-reasoning", - "name": "Grok 4.1 Fast Non-Reasoning", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-11-19", - "last_updated": "2025-07-09", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.2, - "output": 0.5, - "cache_read": 0.05 - }, - "limit": { - "context": 1000000, - "output": 1000000 - } - }, - { - "id": "vercel/xai/grok-4.1-fast-reasoning", - "name": "Grok 4.1 Fast Reasoning", - "family": "grok", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-11-19", - "last_updated": "2025-07-09", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.2, - "output": 0.5, - "cache_read": 0.05 - }, - "limit": { - "context": 1000000, - "output": 1000000 - } - }, - { - "id": "vercel/xai/grok-4.20-multi-agent", - "name": "Grok 4.20 Multi-Agent", - "family": "grok", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-03-10", - "last_updated": "2026-03-23", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 2.5, - "cache_read": 0.2 - }, - "limit": { - "context": 2000000, - "output": 2000000 - } - }, - { - "id": "vercel/xai/grok-4.20-multi-agent-beta", - "name": "Grok 4.20 Multi Agent Beta", - "family": "grok", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-03-11", - "last_updated": "2026-03-13", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 2.5, - "cache_read": 0.2 - }, - "limit": { - "context": 2000000, - "output": 2000000 - } - }, - { - "id": "vercel/xai/grok-4.20-non-reasoning", - "name": "Grok 4.20 Non-Reasoning", - "family": "grok", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2026-03-10", - "last_updated": "2026-03-23", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 2.5, - "cache_read": 0.2 - }, - "limit": { - "context": 2000000, - "output": 2000000 - } - }, - { - "id": "vercel/xai/grok-4.20-non-reasoning-beta", - "name": "Grok 4.20 Beta Non-Reasoning", - "family": "grok", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2026-03-11", - "last_updated": "2026-03-13", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 2.5, - "cache_read": 0.4 - }, - "limit": { - "context": 2000000, - "output": 2000000 - } - }, - { - "id": "vercel/xai/grok-4.20-reasoning", - "name": "Grok 4.20 Reasoning", - "family": "grok", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-03-10", - "last_updated": "2026-03-23", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 2.5, - "cache_read": 0.2 - }, - "limit": { - "context": 2000000, - "output": 2000000 - } - }, - { - "id": "vercel/xai/grok-4.20-reasoning-beta", - "name": "Grok 4.20 Beta Reasoning", - "family": "grok", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-03-11", - "last_updated": "2026-03-13", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 2.5, - "cache_read": 0.2 - }, - "limit": { - "context": 2000000, - "output": 2000000 - } - }, - { - "id": "vercel/xai/grok-4.3", - "name": "Grok 4.3", - "family": "grok", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-04-30", - "last_updated": "2026-04-17", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.25, - "output": 2.5, - "cache_read": 0.2 - }, - "limit": { - "context": 1000000, - "output": 1000000 - } - }, - { - "id": "vercel/xai/grok-4.5", - "name": "Grok 4.5", - "family": "grok", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-07-08", - "last_updated": "2026-07-08", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 2.0, - "output": 6.0, - "cache_read": 0.3 - }, - "limit": { - "context": 500000, - "output": 500000 - } - }, - { - "id": "vercel/xai/grok-4.6", - "name": "Grok 4.6", - "family": "grok", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2026-02-01", - "release_date": "2026-08-12", - "last_updated": "2026-08-12", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 2.0, - "output": 6.0, - "cache_read": 0.5 - }, - "limit": { - "context": 500000, - "output": 500000 - } - }, - { - "id": "vercel/xai/grok-build-0.1", - "name": "Grok Build 0.1", - "family": "grok-build", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-05-20", - "last_updated": "2026-04-16", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.0, - "output": 2.0, - "cache_read": 0.2 - }, - "limit": { - "context": 256000, - "output": 256000 - } - }, - { - "id": "vercel/xai/grok-imagine-image", - "name": "Grok Imagine Image", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2026-01-28", - "last_updated": "2026-02-19", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text", - "image" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, - { - "id": "vercel/xai/grok-imagine-image-2.0", - "name": "Grok Imagine Image 2.0", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": false, - "release_date": "2026-08-07", - "last_updated": "2026-08-07", - "modalities": { - "input": [ - "text" - ], - "output": [ - "image" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, - { - "id": "vercel/xai/grok-imagine-video", - "name": "Grok Imagine", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2026-01-28", - "last_updated": "2026-01-28", - "modalities": { - "input": [ - "text" - ], - "output": [ - "video" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, - { - "id": "vercel/xai/grok-imagine-video-1.5", - "name": "Grok Imagine Video 1.5", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2026-06-22", - "last_updated": "2026-05-30", - "modalities": { - "input": [ - "text" - ], - "output": [ - "video" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, - { - "id": "vercel/xai/grok-imagine-video-1.5-preview", - "name": "Grok Imagine Video 1.5 Preview", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2026-05-30", - "last_updated": "2026-05-30", - "modalities": { - "input": [ - "text" - ], - "output": [ - "video" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, - { - "id": "vercel/xai/grok-stt", - "name": "Grok STT", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2026-03-16", - "last_updated": "2026-03-16", - "modalities": { - "input": [ - "audio" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, - { - "id": "vercel/xai/grok-tts", - "name": "Grok TTS", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2026-03-16", - "last_updated": "2026-03-16", - "modalities": { - "input": [ - "text" - ], - "output": [ - "audio" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, - { - "id": "vercel/xai/grok-voice-think-fast-1.0", - "name": "Grok Voice Think Fast 1.0", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2026-04-23", - "last_updated": "2026-04-23", - "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, - { - "id": "vercel/xai/grok-voice-think-fast-2.0", - "name": "Grok Voice Think Fast 2.0", - "family": "grok", - "attachment": false, - "reasoning": false, - "tool_call": false, - "release_date": "2026-07-29", - "last_updated": "2026-07-29", - "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 0, - "output": 0 - } - }, { "id": "vercel/xiaomi/mimo-v2.5", "name": "MiMo M2.5", - "family": "mimo-v2.5", + "family": "mimo", "attachment": true, "reasoning": true, "tool_call": true, @@ -187998,7 +205474,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.14, "output": 0.28, @@ -188012,7 +205488,7 @@ { "id": "vercel/xiaomi/mimo-v2.5-pro", "name": "MiMo V2.5 Pro", - "family": "mimo-v2.5-pro", + "family": "mimo", "attachment": true, "reasoning": true, "tool_call": true, @@ -188028,7 +205504,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.435, "output": 0.87, @@ -188160,66 +205636,6 @@ "output": 96000 } }, - { - "id": "vercel/zai/glm-4.6v", - "name": "GLM-4.6V", - "family": "glm", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-09-30", - "last_updated": "2025-12-08", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.3, - "output": 0.9, - "cache_read": 0.05 - }, - "limit": { - "context": 128000, - "output": 24000 - } - }, - { - "id": "vercel/zai/glm-4.6v-flash", - "name": "GLM-4.6V-Flash", - "family": "glm", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2024-10", - "release_date": "2025-09-30", - "last_updated": "2025-09-30", - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": {}, - "limit": { - "context": 128000, - "output": 24000 - } - }, { "id": "vercel/zai/glm-4.7", "name": "GLM 4.7", @@ -188228,7 +205644,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-10", + "knowledge": "2025-04", "release_date": "2025-12-22", "last_updated": "2025-12-22", "modalities": { @@ -188239,7 +205655,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.6, "output": 2.2, @@ -188253,7 +205669,7 @@ { "id": "vercel/zai/glm-4.7-flash", "name": "GLM 4.7 Flash", - "family": "glm", + "family": "glm-flash", "attachment": false, "reasoning": true, "tool_call": true, @@ -188269,7 +205685,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.07, "output": 0.4 @@ -188345,7 +205761,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-03-15", + "release_date": "2026-03-16", "last_updated": "2026-03-16", "modalities": { "input": [ @@ -188384,7 +205800,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.4, "output": 4.4, @@ -188403,7 +205819,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-06-16", + "release_date": "2026-06-13", "last_updated": "2026-06-13", "modalities": { "input": [ @@ -188415,9 +205831,9 @@ }, "open_weights": true, "cost": { - "input": 1.1, - "output": 3.851, - "cache_read": 0.275 + "input": 0.8, + "output": 2.55, + "cache_read": 0.16 }, "limit": { "context": 1000000, @@ -188432,7 +205848,7 @@ "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-06-23", + "release_date": "2026-06-13", "last_updated": "2026-06-13", "modalities": { "input": [ @@ -188442,15 +205858,44 @@ "text" ] }, + "open_weights": true, + "cost": { + "input": 2.1, + "output": 6.6, + "cache_read": 0.21 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "vercel/zai/glm-5.3", + "name": "GLM 5.3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, "open_weights": false, "cost": { - "input": 2.1, - "output": 6.6, - "cache_read": 0.21 + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 }, "limit": { "context": 1000000, - "output": 128000 + "output": 12800 } }, { @@ -189825,6 +207270,36 @@ "output": 262144 } }, + { + "id": "wandb/Qwen/Qwen3.8-27B", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-14", + "last_updated": "2026-08-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 3.0, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "wandb/deepseek-ai/DeepSeek-V3.1", "name": "DeepSeek V3.1", diff --git a/crates/goose-provider-types/src/canonical/data/provider_metadata.json b/crates/goose-provider-types/src/canonical/data/provider_metadata.json index 61703379e..f3d8425cd 100644 --- a/crates/goose-provider-types/src/canonical/data/provider_metadata.json +++ b/crates/goose-provider-types/src/canonical/data/provider_metadata.json @@ -32,6 +32,17 @@ ], "model_count": 2 }, + { + "id": "agentrouter", + "display_name": "AgentRouter", + "npm": "@ai-sdk/openai-compatible", + "api": "https://agentrouter.org/v1", + "doc": "https://agentrouter.org/docs/opencode.html", + "env": [ + "AGENTROUTER_API_KEY" + ], + "model_count": 3 + }, { "id": "ai-router", "display_name": "AI-ROUTER", @@ -63,7 +74,7 @@ "env": [ "AKI_IO_API_KEY" ], - "model_count": 6 + "model_count": 7 }, { "id": "alibaba", @@ -306,7 +317,7 @@ "CLOUDFLARE_ACCOUNT_ID", "CLOUDFLARE_API_KEY" ], - "model_count": 24 + "model_count": 25 }, { "id": "coralbricks", @@ -339,7 +350,7 @@ "env": [ "CROF_API_KEY" ], - "model_count": 26 + "model_count": 21 }, { "id": "crossmodel", @@ -350,7 +361,7 @@ "env": [ "CROSSMODEL_API_KEY" ], - "model_count": 51 + "model_count": 53 }, { "id": "crusoe", @@ -395,7 +406,7 @@ "env": [ "DEEPSEEK_API_KEY" ], - "model_count": 4 + "model_count": 5 }, { "id": "digitalocean", @@ -441,6 +452,17 @@ ], "model_count": 4 }, + { + "id": "echo", + "display_name": "Echo", + "npm": "@ai-sdk/openai-compatible", + "api": "https://echo.tracerml.ai/v1", + "doc": "https://echo.tracerml.ai/docs/api", + "env": [ + "ECHO_API_KEY" + ], + "model_count": 1 + }, { "id": "edenai", "display_name": "Eden AI", @@ -461,7 +483,7 @@ "env": [ "EMPIRIOLABS_API_KEY" ], - "model_count": 53 + "model_count": 55 }, { "id": "evroc", @@ -582,7 +604,7 @@ "env": [ "HETZNER_API_KEY" ], - "model_count": 4 + "model_count": 2 }, { "id": "hpc-ai", @@ -604,7 +626,7 @@ "env": [ "HF_TOKEN" ], - "model_count": 68 + "model_count": 69 }, { "id": "hyper", @@ -659,7 +681,7 @@ "env": [ "INCEPTRON_API_KEY" ], - "model_count": 5 + "model_count": 4 }, { "id": "inference", @@ -748,7 +770,7 @@ "env": [ "KILO_API_KEY" ], - "model_count": 360 + "model_count": 365 }, { "id": "kimi-for-coding", @@ -761,6 +783,17 @@ ], "model_count": 4 }, + { + "id": "kosmik", + "display_name": "Kosmik Compute", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.koscompute.com/v1", + "doc": "https://api.koscompute.com/docs/", + "env": [ + "KOSMIK_API_KEY" + ], + "model_count": 1 + }, { "id": "kuae-cloud-coding-plan", "display_name": "KUAE Cloud Coding Plan", @@ -785,6 +818,17 @@ }, { "id": "llmgateway", + "display_name": "DevPass (LLM Gateway)", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.llmgateway.io/v1", + "doc": "https://llmgateway.io/docs", + "env": [ + "LLMGATEWAY_API_KEY" + ], + "model_count": 187 + }, + { + "id": "llmgateway-providers", "display_name": "LLM Gateway", "npm": "@ai-sdk/openai-compatible", "api": "https://api.llmgateway.io/v1", @@ -792,7 +836,7 @@ "env": [ "LLMGATEWAY_API_KEY" ], - "model_count": 189 + "model_count": 377 }, { "id": "llmtr", @@ -1034,7 +1078,7 @@ "env": [ "NANO_GPT_API_KEY" ], - "model_count": 595 + "model_count": 606 }, { "id": "nearai", @@ -1112,7 +1156,7 @@ "env": [ "NVIDIA_API_KEY" ], - "model_count": 100 + "model_count": 102 }, { "id": "ofox", @@ -1123,7 +1167,7 @@ "env": [ "OFOX_API_KEY" ], - "model_count": 103 + "model_count": 111 }, { "id": "ollama-cloud", @@ -1145,7 +1189,7 @@ "env": [ "OPENCODE_API_KEY" ], - "model_count": 91 + "model_count": 93 }, { "id": "opencode-go", @@ -1156,7 +1200,18 @@ "env": [ "OPENCODE_API_KEY" ], - "model_count": 25 + "model_count": 29 + }, + { + "id": "opper", + "display_name": "Opper", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.opper.ai/v3/compat", + "doc": "https://opper.ai/models", + "env": [ + "OPPER_API_KEY" + ], + "model_count": 40 }, { "id": "orcarouter", @@ -1200,7 +1255,7 @@ "env": [ "PIONEER_API_KEY" ], - "model_count": 102 + "model_count": 103 }, { "id": "poe", @@ -1278,7 +1333,7 @@ "env": [ "REQUESTY_API_KEY" ], - "model_count": 49 + "model_count": 139 }, { "id": "routing-run", @@ -1300,7 +1355,7 @@ "env": [ "RUNINFRA_GATEWAY_KEY" ], - "model_count": 4 + "model_count": 5 }, { "id": "sakana", @@ -1311,7 +1366,7 @@ "env": [ "SAKANA_API_KEY" ], - "model_count": 3 + "model_count": 4 }, { "id": "sarvam", @@ -1333,7 +1388,7 @@ "env": [ "SCALEWAY_API_KEY" ], - "model_count": 14 + "model_count": 15 }, { "id": "scnet-token-plan", @@ -1344,10 +1399,10 @@ "env": [ "SCNET_API_KEY" ], - "model_count": 13 + "model_count": 16 }, { - "id": "scx", + "id": "scx-ai", "display_name": "SCX.ai", "npm": "@ai-sdk/openai-compatible", "api": "https://api.scx.ai/v1", @@ -1355,7 +1410,7 @@ "env": [ "SCX_API_KEY" ], - "model_count": 2 + "model_count": 4 }, { "id": "siliconflow", @@ -1576,7 +1631,7 @@ "env": [ "UMANS_AI_API_KEY" ], - "model_count": 8 + "model_count": 7 }, { "id": "umans-ai-coding-plan", @@ -1587,7 +1642,7 @@ "env": [ "UMANS_AI_CODING_PLAN_API_KEY" ], - "model_count": 9 + "model_count": 8 }, { "id": "unorouter", @@ -1653,7 +1708,7 @@ "env": [ "WANDB_API_KEY" ], - "model_count": 28 + "model_count": 29 }, { "id": "xiaomi", diff --git a/ui/desktop/package.json b/ui/desktop/package.json index 7f6fd88f7..59d97c4ae 100644 --- a/ui/desktop/package.json +++ b/ui/desktop/package.json @@ -1,7 +1,7 @@ { "name": "goose-app", "productName": "Goose", - "version": "1.47.0", + "version": "1.48.0", "description": "Goose App", "engines": { "node": "^24.10.0",