From f87c4d73d186b504b734120433124ba5b84cb475 Mon Sep 17 00:00:00 2001 From: Kalvin C Date: Fri, 28 Aug 2026 04:53:42 +0000 Subject: [PATCH] chore: update canonical models json (#11641) Co-authored-by: Lifei Zhou --- .../src/canonical/data/canonical_models.json | 6133 +++++++++++------ .../src/canonical/data/provider_metadata.json | 134 +- .../src/canonical/name_builder.rs | 12 +- crates/goose/src/providers/formats/bedrock.rs | 20 +- 4 files changed, 4101 insertions(+), 2198 deletions(-) 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 5ed5c4025..f73d54164 100644 --- a/crates/goose-provider-types/src/canonical/data/canonical_models.json +++ b/crates/goose-provider-types/src/canonical/data/canonical_models.json @@ -4285,7 +4285,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -4407,7 +4407,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -4528,7 +4528,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -4590,7 +4590,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -4621,7 +4621,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -4652,7 +4652,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -6032,6 +6032,91 @@ "output": 128000 } }, + { + "id": "agnes/agnes-2.0-flash", + "name": "Agnes 2.0 Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-25", + "last_updated": "2026-05-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 512000, + "output": 65536 + } + }, + { + "id": "agnes/agnes-2.5-flash", + "name": "Agnes 2.5 Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07", + "last_updated": "2026-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 512000, + "output": 65536 + } + }, + { + "id": "agnes/agnes-2.5-pro-alpha", + "name": "Agnes 2.5 Pro Alpha", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-07-24", + "last_updated": "2026-07-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 0.9, + "cache_read": 0.0038 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, { "id": "ai-router/gpt-5.4", "name": "GPT-5.4", @@ -6039,7 +6124,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -8658,6 +8743,38 @@ "output": 128000 } }, + { + "id": "aixy/openai/gpt-4.1-mini", + "name": "GPT-4.1 mini", + "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": 1047576, + "output": 32768 + } + }, { "id": "aki-io/deepseek-v4-flash-0731-284b", "name": "DeepSeek V4 Flash 0731", @@ -9283,8 +9400,8 @@ }, "open_weights": false, "cost": { - "input": 0.86, - "output": 3.15 + "input": 0.573, + "output": 2.58 }, "limit": { "context": 202752, @@ -9311,8 +9428,8 @@ }, "open_weights": true, "cost": { - "input": 0.87, - "output": 3.48, + "input": 0.825, + "output": 3.301, "cache_read": 0.17 }, "limit": { @@ -10886,8 +11003,8 @@ }, "open_weights": true, "cost": { - "input": 0.43, - "output": 2.58 + "input": 0.172, + "output": 1.032 }, "limit": { "context": 262144, @@ -16637,10 +16754,10 @@ }, "open_weights": false, "cost": { - "input": 0.22, - "output": 1.32, - "cache_read": 0.022, - "cache_write": 0.275 + "input": 0.2, + "output": 1.2, + "cache_read": 0.02, + "cache_write": 0.25 }, "limit": { "context": 1050000, @@ -16670,10 +16787,10 @@ }, "open_weights": false, "cost": { - "input": 5.5, - "output": 33.0, - "cache_read": 0.55, - "cache_write": 6.875 + "input": 4.0, + "output": 20.0, + "cache_read": 0.4, + "cache_write": 5.0 }, "limit": { "context": 1050000, @@ -16703,10 +16820,10 @@ }, "open_weights": false, "cost": { - "input": 2.2, - "output": 13.2, - "cache_read": 0.22, - "cache_write": 2.75 + "input": 2.0, + "output": 12.0, + "cache_read": 0.2, + "cache_write": 2.5 }, "limit": { "context": 1050000, @@ -17699,7 +17816,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-06-01", @@ -17812,10 +17929,10 @@ }, "open_weights": false, "cost": { - "input": 5.5, - "output": 33.0, - "cache_read": 0.55, - "cache_write": 6.875 + "input": 4.4, + "output": 22.0, + "cache_read": 0.44, + "cache_write": 5.5 }, "limit": { "context": 1050000, @@ -17873,7 +17990,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.15, "output": 0.6 @@ -17901,7 +18018,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.15, "output": 0.6 @@ -17929,7 +18046,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.07, "output": 0.3 @@ -17957,7 +18074,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.07, "output": 0.3 @@ -17985,7 +18102,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.15, "output": 0.6 @@ -18013,7 +18130,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.07, "output": 0.2 @@ -20117,7 +20234,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -20144,7 +20261,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -20171,7 +20288,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -22428,7 +22545,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -22460,7 +22577,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -22492,7 +22609,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -24725,7 +24842,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -24757,7 +24874,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -24789,7 +24906,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -26485,6 +26602,35 @@ "output": 262144 } }, + { + "id": "baseten/zai-org/GLM-5.3-Flash", + "name": "GLM 5.3 Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.5 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "berget/google/gemma-4-31B-it", "name": "Gemma 4 31B Instruct", @@ -27776,6 +27922,35 @@ "output": 131072 } }, + { + "id": "cline-pass/cline-pass/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": "cline-pass/cline-pass/kimi-k2.6", "name": "Kimi K2.6", @@ -27961,8 +28136,8 @@ "cache_read": 0.06 }, "limit": { - "context": 512000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -28028,6 +28203,39 @@ "output": 64000 } }, + { + "id": "cline-pass/cline-pass/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": 2.0, + "output": 6.0, + "cache_read": 0.25, + "cache_write": 2.5 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "cloudferro-sherlock/MiniMaxAI/MiniMax-M2.5", "name": "MiniMax-M2.5", @@ -28170,6 +28378,159 @@ "output": 32000 } }, + { + "id": "cloudflare-ai-gateway/alibaba/qwen3-max", + "name": "Qwen3 Max", + "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": 1.2, + "output": 6.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "cloudflare-ai-gateway/alibaba/qwen3.5-397b-a17b", + "name": "Qwen3.5 397B-A17B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-15", + "last_updated": "2026-02-15", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "cloudflare-ai-gateway/alibaba/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": 1.25, + "output": 3.75, + "cache_read": 0.25 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "cloudflare-ai-gateway/alibaba/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": 0.32, + "output": 1.28, + "cache_read": 0.064 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "cloudflare-ai-gateway/alibaba/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": 2.0, + "output": 6.0, + "cache_read": 0.25 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "cloudflare-ai-gateway/anthropic/claude-fable-5", "name": "Claude Fable 5", @@ -28179,7 +28540,7 @@ "tool_call": true, "temperature": false, "knowledge": "2026-01-31", - "release_date": "2026-06-07", + "release_date": "2026-06-09", "last_updated": "2026-06-09", "modalities": { "input": [ @@ -28278,7 +28639,7 @@ "tool_call": true, "temperature": true, "knowledge": "2025-05-31", - "release_date": "2026-02-04", + "release_date": "2026-02-05", "last_updated": "2026-03-13", "modalities": { "input": [ @@ -28311,7 +28672,7 @@ "tool_call": true, "temperature": false, "knowledge": "2026-01-31", - "release_date": "2026-04-14", + "release_date": "2026-04-16", "last_updated": "2026-04-16", "modalities": { "input": [ @@ -28476,7 +28837,7 @@ "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": [ @@ -28501,16 +28862,16 @@ } }, { - "id": "cloudflare-ai-gateway/openai/gpt-3.5-turbo", - "name": "GPT-3.5-turbo", - "family": "gpt", + "id": "cloudflare-ai-gateway/deepseek/deepseek-v4-pro", + "name": "DeepSeek V4 Pro", + "family": "deepseek-thinking", "attachment": false, - "reasoning": false, - "tool_call": false, + "reasoning": true, + "tool_call": true, "temperature": true, - "knowledge": "2021-09-01", - "release_date": "2023-03-01", - "last_updated": "2023-11-06", + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", "modalities": { "input": [ "text" @@ -28519,74 +28880,46 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { - "input": 0.5, - "output": 1.5, - "cache_read": 0.0 + "input": 1.74, + "output": 3.48, + "cache_read": 0.145 }, "limit": { - "context": 16385, - "output": 4096 + "context": 131072, + "output": 384000 } }, { - "id": "cloudflare-ai-gateway/openai/gpt-4", - "name": "GPT-4", - "family": "gpt", + "id": "cloudflare-ai-gateway/moonshotai/kimi-k3", + "name": "Kimi K3", + "family": "kimi-k3", "attachment": true, - "reasoning": false, + "reasoning": true, "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": "cloudflare-ai-gateway/openai/gpt-4-turbo", - "name": "GPT-4 Turbo", - "family": "gpt", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2023-12", - "release_date": "2023-11-06", - "last_updated": "2024-04-09", + "temperature": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", "modalities": { "input": [ "text", - "image" + "image", + "video" ], "output": [ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { - "input": 10.0, - "output": 30.0 + "input": 3.0, + "output": 15.0, + "cache_read": 0.3 }, "limit": { - "context": 128000, - "output": 4096 + "context": 1048576, + "output": 131072 } }, { @@ -28680,7 +29013,7 @@ "cache_read": 0.025 }, "limit": { - "context": 1047576, + "context": 1000000, "output": 32768 } }, @@ -28775,7 +29108,7 @@ "cache_read": 0.125 }, "limit": { - "context": 400000, + "context": 128000, "output": 128000 } }, @@ -28806,7 +29139,7 @@ "cache_read": 0.025 }, "limit": { - "context": 400000, + "context": 128000, "output": 128000 } }, @@ -28837,40 +29170,10 @@ "cache_read": 0.005 }, "limit": { - "context": 400000, + "context": 128000, "output": 128000 } }, - { - "id": "cloudflare-ai-gateway/openai/gpt-5-pro", - "name": "GPT-5 Pro", - "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": "cloudflare-ai-gateway/openai/gpt-5.1", "name": "GPT-5.1", @@ -28878,7 +29181,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -28897,198 +29200,11 @@ "output": 10.0, "cache_read": 0.125 }, - "limit": { - "context": 400000, - "output": 128000 - } - }, - { - "id": "cloudflare-ai-gateway/openai/gpt-5.2", - "name": "GPT-5.2", - "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": "cloudflare-ai-gateway/openai/gpt-5.2-chat", - "name": "GPT-5.2 Chat", - "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" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 1.75, - "output": 14.0, - "cache_read": 0.175 - }, "limit": { "context": 128000, - "output": 16384 - } - }, - { - "id": "cloudflare-ai-gateway/openai/gpt-5.2-pro", - "name": "GPT-5.2 Pro", - "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": 128000 } }, - { - "id": "cloudflare-ai-gateway/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": "cloudflare-ai-gateway/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": "cloudflare-ai-gateway/openai/gpt-5.3-codex-spark", - "name": "GPT-5.3 Codex Spark", - "family": "gpt-codex-spark", - "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": 128000, - "output": 32000 - } - }, { "id": "cloudflare-ai-gateway/openai/gpt-5.4", "name": "GPT-5.4", @@ -29096,7 +29212,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -29117,7 +29233,7 @@ "cache_read": 0.25 }, "limit": { - "context": 1050000, + "context": 1000000, "output": 128000 } }, @@ -29128,7 +29244,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -29148,7 +29264,7 @@ "cache_read": 0.075 }, "limit": { - "context": 400000, + "context": 128000, "output": 128000 } }, @@ -29159,7 +29275,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -29179,7 +29295,7 @@ "cache_read": 0.02 }, "limit": { - "context": 400000, + "context": 128000, "output": 128000 } }, @@ -29209,7 +29325,7 @@ "output": 180.0 }, "limit": { - "context": 1050000, + "context": 1000000, "output": 128000 } }, @@ -29237,11 +29353,10 @@ "open_weights": false, "cost": { "input": 5.0, - "output": 30.0, - "cache_read": 0.5 + "output": 30.0 }, "limit": { - "context": 1050000, + "context": 1000000, "output": 128000 } }, @@ -29272,40 +29387,7 @@ "output": 180.0 }, "limit": { - "context": 1050000, - "output": 128000 - } - }, - { - "id": "cloudflare-ai-gateway/openai/gpt-5.6", - "name": "GPT-5.6", - "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, + "context": 1000000, "output": 128000 } }, @@ -29365,10 +29447,10 @@ }, "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": 0.25, + "cache_write": 3.125 }, "limit": { "context": 1050000, @@ -29408,68 +29490,6 @@ "output": 128000 } }, - { - "id": "cloudflare-ai-gateway/openai/o1", - "name": "o1", - "family": "o", - "attachment": true, - "reasoning": true, - "tool_call": true, - "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": "cloudflare-ai-gateway/openai/o1-pro", - "name": "o1-pro", - "family": "o-pro", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": false, - "knowledge": "2023-09", - "release_date": "2025-03-19", - "last_updated": "2025-03-19", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 150.0, - "output": 600.0 - }, - "limit": { - "context": 200000, - "output": 100000 - } - }, { "id": "cloudflare-ai-gateway/openai/o3", "name": "o3", @@ -29532,36 +29552,6 @@ "output": 100000 } }, - { - "id": "cloudflare-ai-gateway/openai/o3-pro", - "name": "o3-pro", - "family": "o-pro", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": false, - "knowledge": "2024-05", - "release_date": "2025-06-10", - "last_updated": "2025-06-10", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 20.0, - "output": 80.0 - }, - "limit": { - "context": 200000, - "output": 100000 - } - }, { "id": "cloudflare-ai-gateway/openai/o4-mini", "name": "o4-mini", @@ -29594,71 +29584,108 @@ } }, { - "id": "cloudflare-ai-gateway/workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it", - "name": "Gemma Sea Lion V4 27B It", - "family": "gemma", - "attachment": false, + "id": "cloudflare-ai-gateway/xai/grok-4.20-0309-non-reasoning", + "name": "Grok 4.20 (Non-Reasoning)", + "family": "grok", + "attachment": true, "reasoning": false, - "tool_call": false, + "tool_call": true, "temperature": true, - "release_date": "2025-09-23", - "last_updated": "2025-09-23", + "release_date": "2026-03-09", + "last_updated": "2026-03-09", "modalities": { "input": [ - "text" + "text", + "image", + "pdf" ], "output": [ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 0.351, - "output": 0.555 + "input": 2.0, + "output": 6.0, + "cache_read": 0.2 }, "limit": { - "context": 128000, - "output": 128000 + "context": 2000000, + "output": 30000 } }, { - "id": "cloudflare-ai-gateway/workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", - "name": "Deepseek R1 Distill Qwen 32B", - "family": "deepseek-thinking", - "attachment": false, - "reasoning": true, - "tool_call": false, - "temperature": true, - "release_date": "2025-01-20", - "last_updated": "2025-01-20", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.497, - "output": 4.881 - }, - "limit": { - "context": 80000, - "output": 80000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/google/gemma-4-26b-a4b-it", - "name": "Gemma 4 26B A4B IT", - "family": "gemma", + "id": "cloudflare-ai-gateway/xai/grok-4.20-0309-reasoning", + "name": "Grok 4.20 (Reasoning)", + "family": "grok", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2026-04-02", - "last_updated": "2026-04-02", + "release_date": "2026-03-09", + "last_updated": "2026-03-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.2 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "cloudflare-ai-gateway/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": "cloudflare-ai-gateway/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", @@ -29668,84 +29695,28 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 0.1, - "output": 0.3 + "input": 2.0, + "output": 6.0, + "cache_read": 0.3 }, "limit": { - "context": 256000, - "output": 16384 + "context": 500000, + "output": 500000 } }, { - "id": "cloudflare-ai-gateway/workers-ai/@cf/ibm-granite/granite-4.0-h-micro", - "name": "Granite 4.0 H Micro", - "family": "granite", - "attachment": false, - "reasoning": false, + "id": "cloudflare-ai-gateway/xai/grok-4.6", + "name": "Grok 4.6", + "family": "grok", + "attachment": true, + "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2025-10-02", - "last_updated": "2025-10-02", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.017, - "output": 0.112 - }, - "limit": { - "context": 131000, - "output": 131000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8", - "name": "Llama 3.1 8B Instruct fp8", - "family": "llama", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "knowledge": "2023-12", - "release_date": "2024-07-23", - "last_updated": "2024-07-23", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.152, - "output": 0.287 - }, - "limit": { - "context": 32000, - "output": 32000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", - "name": "Llama 3.2 11B Vision Instruct", - "family": "llama", - "attachment": true, - "reasoning": false, - "tool_call": false, - "temperature": true, - "knowledge": "2023-12", - "release_date": "2024-09-25", - "last_updated": "2024-09-25", + "knowledge": "2026-02-01", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", "modalities": { "input": [ "text", @@ -29755,478 +29726,15 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 0.0485, - "output": 0.676 + "input": 2.0, + "output": 6.0, + "cache_read": 0.5 }, "limit": { - "context": 128000, - "output": 128000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-1b-instruct", - "name": "Llama 3.2 1B Instruct", - "family": "llama", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "knowledge": "2023-12", - "release_date": "2024-09-25", - "last_updated": "2024-09-25", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.027, - "output": 0.201 - }, - "limit": { - "context": 60000, - "output": 60000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-3b-instruct", - "name": "Llama 3.2 3B Instruct", - "family": "llama", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "knowledge": "2023-12", - "release_date": "2024-09-25", - "last_updated": "2024-09-25", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0509, - "output": 0.335 - }, - "limit": { - "context": 80000, - "output": 80000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast", - "name": "Llama 3.3 70B Instruct fp8 Fast", - "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": 0.293, - "output": 2.253 - }, - "limit": { - "context": 24000, - "output": 24000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", - "name": "Llama 4 Scout 17B 16E Instruct", - "family": "llama", - "attachment": true, - "reasoning": false, - "tool_call": true, - "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": 131000, - "output": 16384 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-guard-3-8b", - "name": "Llama Guard 3 8B", - "family": "llama", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "knowledge": "2023-12", - "release_date": "2024-07-23", - "last_updated": "2024-07-23", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.484, - "output": 0.03 - }, - "limit": { - "context": 131072, - "output": 131072 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", - "name": "Mistral Small 3.1 24B Instruct", - "family": "mistral-small", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2024-06", - "release_date": "2025-03-17", - "last_updated": "2025-03-17", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.351, - "output": 0.555 - }, - "limit": { - "context": 128000, - "output": 128000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/moonshotai/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" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.95, - "output": 4.0, - "cache_read": 0.16 - }, - "limit": { - "context": 262144, - "output": 256000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.7-code", - "name": "Kimi K2.7 Code", - "family": "kimi-k2", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-01", - "release_date": "2026-06-12", - "last_updated": "2026-06-12", - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.95, - "output": 4.0, - "cache_read": 0.19 - }, - "limit": { - "context": 262144, - "output": 262144 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/nvidia/nemotron-3-120b-a12b", - "name": "Nemotron 3 Super 120B", - "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": 0.5, - "output": 1.5 - }, - "limit": { - "context": 256000, - "output": 256000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-120b", - "name": "GPT OSS 120B", - "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": 128000, - "output": 16384 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-20b", - "name": "GPT OSS 20B", - "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": 0.2, - "output": 0.3 - }, - "limit": { - "context": 128000, - "output": 16384 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", - "name": "Qwen2.5 Coder 32B Instruct", - "family": "qwen", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2024-11-12", - "last_updated": "2024-11-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.66, - "output": 1.0 - }, - "limit": { - "context": 32768, - "output": 32768 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", - "name": "Qwen3 30B A3b fp8", - "family": "qwen", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2025-04-28", - "last_updated": "2025-04-28", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.0509, - "output": 0.335 - }, - "limit": { - "context": 32768, - "output": 32768 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwq-32b", - "name": "Qwq 32B", - "family": "qwen", - "attachment": false, - "reasoning": true, - "tool_call": false, - "temperature": true, - "knowledge": "2024-04", - "release_date": "2025-03-05", - "last_updated": "2025-03-05", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.66, - "output": 1.0 - }, - "limit": { - "context": 24000, - "output": 24000 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/zai-org/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": 0.0605, - "output": 0.4 - }, - "limit": { - "context": 131072, - "output": 131072 - } - }, - { - "id": "cloudflare-ai-gateway/workers-ai/@cf/zai-org/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": 1.4, - "output": 4.4, - "cache_read": 0.26 - }, - "limit": { - "context": 262144, - "output": 256000 + "context": 500000, + "output": 500000 } }, { @@ -30954,6 +30462,36 @@ "output": 256000 } }, + { + "id": "cloudflare-workers-ai/@cf/zai-org/glm-5.3-flash", + "name": "Glm 5.3 Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1310720, + "output": 1310720 + } + }, { "id": "cohere/c4ai-aya-expanse-32b", "name": "Aya Expanse 32B", @@ -32784,7 +32322,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -32816,7 +32354,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -33710,8 +33248,9 @@ }, "open_weights": false, "cost": { - "input": 1.671, - "output": 5.57 + "input": 1.393, + "output": 7.13, + "cache_read": 0.139 }, "limit": { "context": 256000, @@ -36065,7 +35604,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -36097,7 +35636,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -36129,7 +35668,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -37283,7 +36822,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -38030,7 +37569,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -38061,7 +37600,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -38092,7 +37631,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -38124,7 +37663,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -38155,7 +37694,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -38572,7 +38111,7 @@ }, "limit": { "context": 524288, - "output": 128000 + "output": 512000 } }, { @@ -40100,63 +39639,35 @@ } }, { - "id": "deepseek/deepseek-chat", - "name": "DeepSeek Chat", - "family": "deepseek", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2025-09", - "release_date": "2025-12-01", - "last_updated": "2026-02-28", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.0028 - }, - "limit": { - "context": 1000000, - "output": 384000 - } - }, - { - "id": "deepseek/deepseek-reasoner", - "name": "DeepSeek Reasoner", - "family": "deepseek-thinking", + "id": "deepinfra/zai-org/GLM-5.3-Flash", + "name": "GLM-5.3-Flash", + "family": "glm", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-09", - "release_date": "2025-12-01", - "last_updated": "2026-02-28", + "release_date": "2026-08-26", + "last_updated": "2026-08-26", "modalities": { "input": [ - "text" + "text", + "image", + "video", + "pdf" ], "output": [ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.0028 + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 }, "limit": { - "context": 1000000, - "output": 384000 + "context": 1048576, + "output": 131072 } }, { @@ -42412,9 +41923,9 @@ }, "open_weights": false, "cost": { - "input": 0.1, - "output": 0.6, - "cache_read": 0.01 + "input": 0.2, + "output": 1.2, + "cache_read": 0.02 }, "limit": { "context": 1050000, @@ -42443,9 +41954,9 @@ }, "open_weights": false, "cost": { - "input": 2.0, - "output": 10.0, - "cache_read": 0.2 + "input": 4.0, + "output": 20.0, + "cache_read": 0.4 }, "limit": { "context": 1050000, @@ -42474,9 +41985,9 @@ }, "open_weights": false, "cost": { - "input": 1.0, - "output": 6.0, - "cache_read": 0.1 + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 }, "limit": { "context": 1050000, @@ -44351,7 +43862,39 @@ "open_weights": true, "cost": { "input": 0.15001, - "output": 0.59997 + "output": 0.59997, + "cache_read": 0.15001, + "cache_write": 0.15001 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "edenai/databricks/databricks-gpt-oss-120b@eu", + "name": "GPT OSS 120B (EU)", + "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": 0.15001, + "output": 0.59997, + "cache_read": 0.15001, + "cache_write": 0.15001 }, "limit": { "context": 131072, @@ -44379,7 +43922,39 @@ "open_weights": true, "cost": { "input": 0.07, - "output": 0.30002 + "output": 0.30002, + "cache_read": 0.07, + "cache_write": 0.07 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "edenai/databricks/databricks-gpt-oss-20b@eu", + "name": "GPT OSS 20B (EU)", + "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": 0.07, + "output": 0.30002, + "cache_read": 0.07, + "cache_write": 0.07 }, "limit": { "context": 131072, @@ -45036,36 +44611,6 @@ "output": 384000 } }, - { - "id": "edenai/deepseek/deepseek-reasoner", - "name": "DeepSeek Reasoner", - "family": "deepseek-thinking", - "attachment": false, - "reasoning": true, - "tool_call": false, - "temperature": true, - "knowledge": "2025-09", - "release_date": "2025-12-01", - "last_updated": "2026-02-28", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.28, - "output": 0.42, - "cache_read": 0.028 - }, - "limit": { - "context": 131072, - "output": 384000 - } - }, { "id": "edenai/deepseek/deepseek-v4-flash", "name": "DeepSeek V4 Flash", @@ -45362,35 +44907,6 @@ "output": 32768 } }, - { - "id": "edenai/flexai/DeepSeek-V4-Flash", - "name": "DeepSeek V4 Flash 0731", - "family": "deepseek-flash", - "attachment": false, - "reasoning": true, - "tool_call": false, - "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": 0.08, - "output": 0.18 - }, - "limit": { - "context": 1000000, - "output": 384000 - } - }, { "id": "edenai/flexai/Muse-Glimmer-30B", "name": "Muse Glimmer 30B", @@ -45474,7 +44990,7 @@ "output": 0.18 }, "limit": { - "context": 1000000, + "context": 786432, "output": 384000 } }, @@ -46222,8 +45738,8 @@ }, "open_weights": true, "cost": { - "input": 0.75816, - "output": 0.75816 + "input": 0.758485, + "output": 0.758485 }, "limit": { "context": 128000, @@ -46250,8 +45766,8 @@ }, "open_weights": true, "cost": { - "input": 0.17496, - "output": 0.75816 + "input": 0.175035, + "output": 0.758485 }, "limit": { "context": 131072, @@ -46283,7 +45799,7 @@ }, "limit": { "context": 204800, - "output": 128000 + "output": 131072 } }, { @@ -46401,7 +45917,7 @@ }, "limit": { "context": 524288, - "output": 128000 + "output": 512000 } }, { @@ -46455,8 +45971,9 @@ }, "open_weights": true, "cost": { - "input": 0.4, - "output": 2.0 + "input": 0.44, + "output": 2.2, + "cache_read": 0.044 }, "limit": { "context": 262144, @@ -47270,7 +46787,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -47302,7 +46819,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -47365,7 +46882,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -47397,7 +46914,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -47429,7 +46946,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -47461,7 +46978,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -47688,7 +47205,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -48158,8 +47675,8 @@ }, "open_weights": true, "cost": { - "input": 0.627, - "output": 1.881 + "input": 0.5808, + "output": 1.7424 }, "limit": { "context": 1000000, @@ -48406,6 +47923,35 @@ "output": 65536 } }, + { + "id": "edenai/qwen/qwen3-coder-next@eu", + "name": "Qwen3 Coder Next (EU)", + "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": 0.3, + "output": 1.5 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "edenai/qwen/qwen3-coder-plus", "name": "Qwen3 Coder Plus", @@ -48468,6 +48014,37 @@ "output": 65536 } }, + { + "id": "edenai/qwen/qwen3-max@eu", + "name": "Qwen3 Max (EU)", + "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": 1.2, + "output": 6.0, + "cache_read": 0.24, + "cache_write": 1.5 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "edenai/qwen/qwen3-next-80b-a3b-instruct", "name": "Qwen3-Next 80B-A3B Instruct", @@ -48717,7 +48294,7 @@ "family": "deepseek-flash", "attachment": false, "reasoning": true, - "tool_call": true, + "tool_call": false, "temperature": true, "knowledge": "2025-05", "release_date": "2026-07-31", @@ -48732,8 +48309,8 @@ }, "open_weights": true, "cost": { - "input": 0.46656, - "output": 0.93312 + "input": 0.46676, + "output": 0.933521 }, "limit": { "context": 256000, @@ -48746,7 +48323,7 @@ "family": "gpt-oss", "attachment": false, "reasoning": true, - "tool_call": true, + "tool_call": false, "temperature": true, "release_date": "2025-08-05", "last_updated": "2025-08-05", @@ -48760,8 +48337,8 @@ }, "open_weights": true, "cost": { - "input": 0.17496, - "output": 0.69984 + "input": 0.175035, + "output": 0.70014 }, "limit": { "context": 128000, @@ -48774,7 +48351,7 @@ "family": "llama", "attachment": false, "reasoning": false, - "tool_call": true, + "tool_call": false, "temperature": true, "knowledge": "2023-12", "release_date": "2024-12-06", @@ -48789,8 +48366,8 @@ }, "open_weights": true, "cost": { - "input": 1.04976, - "output": 1.04976 + "input": 1.050211, + "output": 1.050211 }, "limit": { "context": 128000, @@ -50237,6 +49814,37 @@ "output": 131072 } }, + { + "id": "edenai/zai/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "edenai/zai/glm-5v-turbo", "name": "GLM-5V-Turbo", @@ -50625,6 +50233,38 @@ "output": 131072 } }, + { + "id": "empiriolabs/glm-5.3-flash", + "name": "GLM 5.3 Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.25, + "cache_read": 0.075 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "empiriolabs/kimi-k2-6", "name": "Kimi K2.6", @@ -51584,6 +51224,37 @@ "output": 32768 } }, + { + "id": "empiriolabs/qwen3-8-flash", + "name": "Qwen3.8 Flash", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.16, + "output": 0.47, + "cache_read": 0.16 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "empiriolabs/qwen3-8-max", "name": "Qwen3.8 Max", @@ -51942,7 +51613,7 @@ } }, { - "id": "evroc/Qwen/Qwen3.6-35B-A3B-FP8", + "id": "evroc/Qwen/Qwen3.6-35B-A3B", "name": "Qwen3.6 35B-A3B", "family": "qwen", "attachment": true, @@ -51972,6 +51643,35 @@ "output": 65536 } }, + { + "id": "evroc/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": 0.87, + "output": 3.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "evroc/evroc/roc", "name": "roc", @@ -53145,7 +52845,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -53176,7 +52876,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -53206,7 +52906,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -54491,7 +54191,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -54524,7 +54224,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -54557,7 +54257,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -56136,7 +55836,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -56199,7 +55899,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -56231,7 +55931,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -56263,7 +55963,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -56294,7 +55994,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -57362,6 +57062,66 @@ "output": 64000 } }, + { + "id": "gmicloud/MiniMaxAI/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": 0.3, + "output": 1.2, + "cache_read": 0.06 + }, + "limit": { + "context": 196608, + "output": 131072 + } + }, + { + "id": "gmicloud/MiniMaxAI/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": 512000 + } + }, { "id": "gmicloud/Qwen/Qwen3.7-Max", "name": "Qwen3.7 Max", @@ -65284,7 +65044,7 @@ }, "limit": { "context": 204800, - "output": 128000 + "output": 131072 } }, { @@ -65400,7 +65160,7 @@ }, "limit": { "context": 524288, - "output": 128000 + "output": 512000 } }, { @@ -66069,6 +65829,35 @@ "output": 131072 } }, + { + "id": "huggingface/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 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "huggingface/XiaomiMiMo/MiMo-V2-Flash", "name": "MiMo-V2-Flash", @@ -67118,6 +66907,34 @@ "output": 131072 } }, + { + "id": "huggingface/zai-org/GLM-5.3-Flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.5 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "hyper/deepseek-v4-flash", "name": "DeepSeek V4 Flash", @@ -67198,9 +67015,9 @@ }, "open_weights": true, "cost": { - "input": 0.11, - "output": 0.408, - "cache_write": 0.055 + "input": 0.12, + "output": 0.42, + "cache_write": 0.06 }, "limit": { "context": 256000, @@ -67227,9 +67044,9 @@ }, "open_weights": true, "cost": { - "input": 0.86, - "output": 2.784, - "cache_write": 0.43 + "input": 0.9, + "output": 2.804, + "cache_write": 0.45 }, "limit": { "context": 202752, @@ -67256,9 +67073,9 @@ }, "open_weights": true, "cost": { - "input": 1.332, - "output": 4.312, - "cache_write": 0.666 + "input": 1.29, + "output": 4.22, + "cache_write": 0.645 }, "limit": { "context": 202750, @@ -67467,9 +67284,9 @@ }, "open_weights": true, "cost": { - "input": 0.598, - "output": 0.738, - "cache_write": 0.299 + "input": 0.6066, + "output": 1.0386, + "cache_write": 0.3033 }, "limit": { "context": 128000, @@ -67526,9 +67343,9 @@ }, "open_weights": true, "cost": { - "input": 0.41, - "output": 1.52, - "cache_write": 0.205 + "input": 0.408, + "output": 1.512, + "cache_write": 0.204 }, "limit": { "context": 262100, @@ -67809,6 +67626,94 @@ "output": 64000 } }, + { + "id": "hyper/qwen3.8-2.4t-a95b", + "name": "Qwen3.8 2.4T A95B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "hyper/qwen3.8-27b", + "name": "Qwen3.8 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "hyper/qwen3.8-flash", + "name": "Qwen3.8 Flash", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.47, + "cache_read": 0.016 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "hyper/qwen3.8-max", "name": "Qwen3.8 Max Preview", @@ -69429,7 +69334,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -69522,7 +69427,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -69585,7 +69490,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -69617,7 +69522,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -69649,7 +69554,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -69680,7 +69585,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -70709,9 +70614,9 @@ }, "open_weights": true, "cost": { - "input": 0.57, - "output": 3.41, - "cache_read": 0.2, + "input": 0.56, + "output": 3.39, + "cache_read": 0.17, "cache_write": 0.0 }, "limit": { @@ -70741,9 +70646,9 @@ }, "open_weights": true, "cost": { - "input": 0.67, + "input": 0.66, "output": 3.4, - "cache_read": 0.19, + "cache_read": 0.18, "cache_write": 0.0 }, "limit": { @@ -70772,7 +70677,7 @@ "open_weights": true, "cost": { "input": 0.75, - "output": 2.9, + "output": 2.4, "cache_read": 0.17, "cache_write": 0.0 }, @@ -72218,6 +72123,37 @@ "output": 4096 } }, + { + "id": "iteracompute/iteracompute/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": 0.35, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "jalapeno/DeepSeek-V4-Flash", "name": "DeepSeek V4 Flash", @@ -72479,7 +72415,7 @@ }, "limit": { "context": 524288, - "output": 128000 + "output": 512000 } }, { @@ -74923,7 +74859,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -75486,8 +75422,8 @@ "output": 0.0 }, "limit": { - "context": 512000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -75742,7 +75678,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 29491 } }, { @@ -75770,7 +75706,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -76531,7 +76467,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -76767,7 +76703,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -77025,7 +76961,7 @@ }, "limit": { "context": 163840, - "output": 163840 + "output": 147456 } }, { @@ -77054,7 +76990,7 @@ }, "limit": { "context": 161000, - "output": 161000 + "output": 144900 } }, { @@ -77111,7 +77047,7 @@ }, "limit": { "context": 8192, - "output": 8192 + "output": 7372 } }, { @@ -77170,7 +77106,7 @@ }, "limit": { "context": 163840, - "output": 163840 + "output": 147456 } }, { @@ -77316,7 +77252,7 @@ }, "limit": { "context": 512000, - "output": 512000 + "output": 460800 } }, { @@ -77590,7 +77526,7 @@ "cache_write": 0.375 }, "limit": { - "context": 65536, + "context": 131072, "output": 32768 } }, @@ -77689,7 +77625,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -77756,7 +77692,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -78087,7 +78023,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -78119,34 +78055,6 @@ "output": 16384 } }, - { - "id": "kilo/google/gemma-3n-e4b-it", - "name": "Google: Gemma 3n 4B", - "family": "gemma", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "release_date": "2025-05-20", - "last_updated": "2025-05-20", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.06, - "output": 0.12 - }, - "limit": { - "context": 32768, - "output": 6554 - } - }, { "id": "kilo/google/gemma-4-26b-a4b-it", "name": "Gemma 4 26B A4B IT", @@ -78199,13 +78107,13 @@ }, "open_weights": true, "cost": { - "input": 0.08, - "output": 0.35, - "cache_read": 0.01 + "input": 0.09, + "output": 0.34, + "cache_read": 0.05 }, "limit": { "context": 262144, - "output": 262144 + "output": 16384 } }, { @@ -78292,7 +78200,7 @@ }, "limit": { "context": 4096, - "output": 4096 + "output": 3686 } }, { @@ -78320,7 +78228,7 @@ }, "limit": { "context": 131000, - "output": 131000 + "output": 117900 } }, { @@ -78349,7 +78257,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -78819,7 +78727,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -78847,7 +78755,7 @@ }, "limit": { "context": 60000, - "output": 60000 + "output": 54000 } }, { @@ -78875,7 +78783,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -78903,8 +78811,8 @@ "output": 0.32 }, "limit": { - "context": 131072, - "output": 16384 + "context": 128000, + "output": 115200 } }, { @@ -78961,8 +78869,8 @@ "output": 0.3 }, "limit": { - "context": 327680, - "output": 16384 + "context": 131072, + "output": 8192 } }, { @@ -79023,7 +78931,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -79056,7 +78964,7 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 943718 } }, { @@ -79089,7 +78997,7 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 943718 } }, { @@ -79122,7 +79030,7 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 943718 } }, { @@ -79150,7 +79058,7 @@ }, "limit": { "context": 16384, - "output": 16384 + "output": 14745 } }, { @@ -79206,7 +79114,7 @@ }, "limit": { "context": 1000192, - "output": 1000192 + "output": 900172 } }, { @@ -79377,10 +79285,39 @@ "cache_read": 0.06 }, "limit": { - "context": 196608, + "context": 204800, "output": 131072 } }, + { + "id": "kilo/minimax/minimax-m2.7:free", + "name": "MiniMax: MiniMax M2.7 (free)", + "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": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 196608, + "output": 196608 + } + }, { "id": "kilo/minimax/minimax-m3", "name": "MiniMax-M3", @@ -79412,6 +79349,36 @@ "output": 512000 } }, + { + "id": "kilo/minimax/minimax-m3:free", + "name": "MiniMax: MiniMax M3 (free)", + "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" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, { "id": "kilo/mistralai/codestral", "name": "Mistral: Codestral 2508", @@ -79439,7 +79406,7 @@ }, "limit": { "context": 256000, - "output": 51200 + "output": 204800 } }, { @@ -79470,7 +79437,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 209715 } }, { @@ -79500,7 +79467,7 @@ }, "limit": { "context": 262144, - "output": 52429 + "output": 209715 } }, { @@ -79530,7 +79497,7 @@ }, "limit": { "context": 131072, - "output": 32768 + "output": 104857 } }, { @@ -79558,7 +79525,7 @@ }, "limit": { "context": 128000, - "output": 128000 + "output": 102400 } }, { @@ -79588,7 +79555,7 @@ }, "limit": { "context": 128000, - "output": 25600 + "output": 102400 } }, { @@ -79619,7 +79586,7 @@ }, "limit": { "context": 131072, - "output": 26215 + "output": 104857 } }, { @@ -79650,7 +79617,7 @@ }, "limit": { "context": 131072, - "output": 26215 + "output": 104857 } }, { @@ -79680,7 +79647,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 209715 } }, { @@ -79740,7 +79707,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 26214 } }, { @@ -79771,7 +79738,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 209715 } }, { @@ -79828,7 +79795,7 @@ }, "limit": { "context": 128000, - "output": 128000 + "output": 102400 } }, { @@ -79888,7 +79855,7 @@ }, "limit": { "context": 65536, - "output": 13108 + "output": 52428 } }, { @@ -79919,7 +79886,7 @@ }, "limit": { "context": 32000, - "output": 6400 + "output": 25600 } }, { @@ -80008,7 +79975,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -80039,7 +80006,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -80070,7 +80037,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -80101,7 +80068,7 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 943718 } }, { @@ -80187,7 +80154,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -80217,7 +80184,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -80301,7 +80268,7 @@ }, "limit": { "context": 131072, - "output": 26215 + "output": 117964 } }, { @@ -80329,7 +80296,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -80358,7 +80325,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 228000 } }, { @@ -80445,7 +80412,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -80474,7 +80441,7 @@ }, "limit": { "context": 512288, - "output": 512288 + "output": 461059 } }, { @@ -80676,7 +80643,7 @@ }, "limit": { "context": 4095, - "output": 4096 + "output": 3685 } }, { @@ -81977,7 +81944,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -82000,13 +81967,12 @@ }, "open_weights": true, "cost": { - "input": 0.03, - "output": 0.13, - "cache_read": 0.03 + "input": 0.02, + "output": 0.1 }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -82456,7 +82422,7 @@ }, "limit": { "context": 127072, - "output": 25415 + "output": 114364 } }, { @@ -82484,7 +82450,7 @@ }, "limit": { "context": 128000, - "output": 25600 + "output": 115200 } }, { @@ -82571,7 +82537,7 @@ }, "limit": { "context": 128000, - "output": 25600 + "output": 115200 } }, { @@ -82741,7 +82707,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 29491 } }, { @@ -82769,7 +82735,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 29491 } }, { @@ -82803,34 +82769,6 @@ "output": 32768 } }, - { - "id": "kilo/qwen/qwen-plus-2025-07-28:thinking", - "name": "Qwen: Qwen Plus 0728 (thinking)", - "family": "qwen", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2025-09-08", - "last_updated": "2025-09-08", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.26, - "output": 0.78 - }, - "limit": { - "context": 1000000, - "output": 32768 - } - }, { "id": "kilo/qwen/qwen2.5-vl-72b-instruct", "name": "Qwen: Qwen2.5 VL 72B Instruct", @@ -82852,13 +82790,12 @@ }, "open_weights": false, "cost": { - "input": 0.8, - "output": 1.0, - "cache_read": 0.4 + "input": 0.25, + "output": 0.75 }, "limit": { - "context": 128000, - "output": 128000 + "context": 32000, + "output": 28800 } }, { @@ -82943,7 +82880,7 @@ }, "limit": { "context": 131072, - "output": 262144 + "output": 117964 } }, { @@ -83141,7 +83078,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -83201,7 +83138,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -83320,7 +83257,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -83584,7 +83521,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -83644,7 +83581,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -83674,7 +83611,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 65536 } }, { @@ -83704,7 +83641,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -83825,7 +83762,7 @@ }, "limit": { "context": 262144, - "output": 81920 + "output": 235929 } }, { @@ -83850,13 +83787,13 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 1.0, + "input": 0.1, + "output": 0.9, "cache_read": 0.05 }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -84104,7 +84041,39 @@ "cache_write": 0.53125 }, "limit": { - "context": 262144, + "context": 1000000, + "output": 131072 + } + }, + { + "id": "kilo/qwen/qwen3.8-flash", + "name": "Qwen3.8 Flash", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.47, + "cache_read": 0.016, + "cache_write": 0.2 + }, + "limit": { + "context": 1000000, "output": 131072 } }, @@ -84167,7 +84136,7 @@ }, "limit": { "context": 16384, - "output": 16384 + "output": 14745 } }, { @@ -84195,7 +84164,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -84338,7 +84307,7 @@ }, "limit": { "context": 8192, - "output": 16384 + "output": 7372 } }, { @@ -84525,36 +84494,6 @@ "output": 64000 } }, - { - "id": "kilo/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": "kilo/stealth/qwen3.6-plus", "name": "Stealth: Qwen3.6 Plus (50% off)", @@ -84642,7 +84581,7 @@ }, "limit": { "context": 256000, - "output": 256000 + "output": 230400 } }, { @@ -84700,7 +84639,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -84842,7 +84781,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -84899,7 +84838,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -84926,7 +84865,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -84954,7 +84893,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 29491 } }, { @@ -84981,7 +84920,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 26214 } }, { @@ -85159,7 +85098,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -85247,7 +85186,7 @@ }, "limit": { "context": 2000000, - "output": 2000000 + "output": 1800000 } }, { @@ -85278,7 +85217,7 @@ }, "limit": { "context": 2000000, - "output": 2000000 + "output": 1800000 } }, { @@ -85309,7 +85248,7 @@ }, "limit": { "context": 1000000, - "output": 4096 + "output": 900000 } }, { @@ -85340,7 +85279,7 @@ }, "limit": { "context": 500000, - "output": 500000 + "output": 450000 } }, { @@ -85372,7 +85311,7 @@ }, "limit": { "context": 500000, - "output": 500000 + "output": 450000 } }, { @@ -85403,7 +85342,7 @@ }, "limit": { "context": 256000, - "output": 256000 + "output": 230400 } }, { @@ -85581,13 +85520,13 @@ }, "open_weights": true, "cost": { - "input": 0.5, - "output": 2.0, - "cache_read": 0.1 + "input": 0.43, + "output": 1.75, + "cache_read": 0.08 }, "limit": { - "context": 202752, - "output": 131072 + "context": 198000, + "output": 16384 } }, { @@ -85766,7 +85705,7 @@ }, "limit": { "context": 202752, - "output": 202752 + "output": 182476 } }, { @@ -85827,6 +85766,37 @@ "output": 131072 } }, + { + "id": "kilo/z-ai/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.25, + "cache_read": 0.015 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "kilo/z-ai/glm-5v-turbo", "name": "GLM-5V-Turbo", @@ -86007,13 +85977,13 @@ }, "open_weights": false, "cost": { - "input": 0.035, - "output": 0.12, - "cache_read": 0.01 + "input": 0.03, + "output": 0.1, + "cache_read": 0.007 }, "limit": { "context": 1048576, - "output": 1048576 + "output": 131072 } }, { @@ -86106,13 +86076,13 @@ }, "open_weights": false, "cost": { - "input": 2.6, - "output": 13.0, - "cache_read": 0.29 + "input": 2.55, + "output": 12.75, + "cache_read": 0.256 }, "limit": { - "context": 974842, - "output": 974842 + "context": 1048576, + "output": 943718 } }, { @@ -86206,7 +86176,7 @@ }, "limit": { "context": 500000, - "output": 500000 + "output": 450000 } }, { @@ -88827,7 +88797,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -88919,7 +88889,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -89012,7 +88982,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -89044,7 +89014,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -89076,7 +89046,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -89107,7 +89077,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -89466,9 +89436,9 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.028 + "input": 0.44, + "output": 1.32, + "cache_read": 0.044 }, "limit": { "context": 1048576, @@ -89496,9 +89466,9 @@ }, "open_weights": true, "cost": { - "input": 1.69, - "output": 3.38, - "cache_read": 0.14 + "input": 1.32, + "output": 3.96, + "cache_read": 0.132 }, "limit": { "context": 1048576, @@ -89592,6 +89562,35 @@ "output": 131072 } }, + { + "id": "llmgateway-providers/baidu/glm-5.3", + "name": "GLM-5.3 (Baidu)", + "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": "llmgateway-providers/baidu/kimi-k2.6", "name": "Kimi K2.6 (Baidu)", @@ -90217,6 +90216,36 @@ "output": 8192 } }, + { + "id": "llmgateway-providers/consensusprotocol/deepseek-v4-flash", + "name": "DeepSeek V4 Flash (Consensus Protocol)", + "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": 0.13, + "output": 0.27, + "cache_read": 0.02 + }, + "limit": { + "context": 524288, + "output": 393216 + } + }, { "id": "llmgateway-providers/deepinfra/deepseek-v3.2", "name": "DeepSeek V3.2 (DeepInfra)", @@ -90692,6 +90721,36 @@ "output": 393216 } }, + { + "id": "llmgateway-providers/deepseek/deepseek-v4-flash-vision-exp", + "name": "DeepSeek V4 Flash Vision Exp (DeepSeek)", + "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": 1050000, + "output": 393216 + } + }, { "id": "llmgateway-providers/deepseek/deepseek-v4-pro", "name": "DeepSeek V4 Pro (DeepSeek)", @@ -91132,9 +91191,9 @@ }, "open_weights": true, "cost": { - "input": 0.075, - "output": 0.175, - "cache_read": 0.0155 + "input": 0.051, + "output": 0.104, + "cache_read": 0.0097 }, "limit": { "context": 390000, @@ -93250,7 +93309,7 @@ }, "limit": { "context": 1048576, - "output": 128000 + "output": 512000 } }, { @@ -95182,7 +95241,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -95213,7 +95272,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -95274,7 +95333,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -95306,7 +95365,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -95338,7 +95397,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -95369,7 +95428,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -97869,6 +97928,35 @@ "output": 128000 } }, + { + "id": "llmgateway-providers/zai/glm-5.3-flash", + "name": "GLM-5.3 Flash (Z AI)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "llmgateway/auto", "name": "Auto Route", @@ -98396,9 +98484,39 @@ }, "open_weights": true, "cost": { - "input": 0.076, - "output": 0.153, - "cache_read": 0.014 + "input": 0.051, + "output": 0.104, + "cache_read": 0.0097 + }, + "limit": { + "context": 1050000, + "output": 384000 + } + }, + { + "id": "llmgateway/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": 1050000, @@ -99495,7 +99613,39 @@ "cache_read": 0.26 }, "limit": { - "context": 1000000, + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, "output": 131072 } }, @@ -99935,7 +100085,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -100028,7 +100178,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -100121,7 +100271,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -100153,7 +100303,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -100185,7 +100335,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -100216,7 +100366,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -101533,7 +101683,7 @@ }, "limit": { "context": 196608, - "output": 128000 + "output": 131072 } }, { @@ -101740,7 +101890,7 @@ }, "limit": { "context": 1048576, - "output": 128000 + "output": 512000 } }, { @@ -103454,6 +103604,35 @@ "output": 4096 } }, + { + "id": "llmtech/unsloth/Qwen3.8-27B-NVFP4", + "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" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 2.09, + "cache_read": 0.04 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "llmtr/gemma-4", "name": "Gemma 4", @@ -107935,7 +108114,7 @@ "attachment": true, "reasoning": false, "tool_call": false, - "temperature": true, + "temperature": false, "knowledge": "2024-09-30", "release_date": "2025-08-07", "last_updated": "2025-08-07", @@ -108031,7 +108210,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -108095,7 +108274,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -108191,7 +108370,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -108223,7 +108402,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -108255,7 +108434,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -108367,8 +108546,8 @@ }, "open_weights": false, "cost": { - "input": 4.0, - "output": 24.0, + "input": 5.0, + "output": 30.0, "cache_read": 0.5 }, "limit": { @@ -108947,7 +109126,7 @@ }, { "id": "merge-gateway/qwen/qwen3-next-80b-a3b-instruct", - "name": "Qwen3 Next 80B A3B Instruct", + "name": "Qwen3-Next 80B-A3B Instruct", "family": "qwen", "attachment": false, "reasoning": false, @@ -108977,7 +109156,7 @@ }, { "id": "merge-gateway/qwen/qwen3-next-80b-a3b-thinking", - "name": "Qwen3 Next 80B A3B Thinking", + "name": "Qwen3-Next 80B-A3B (Thinking)", "family": "qwen", "attachment": false, "reasoning": true, @@ -109101,7 +109280,7 @@ "id": "merge-gateway/qwen/qwen3.5-122b-a10b", "name": "Qwen3.5 122B A10B", "family": "qwen", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -109109,8 +109288,7 @@ "last_updated": "2026-02-23", "modalities": { "input": [ - "text", - "image" + "text" ], "output": [ "text" @@ -109123,8 +109301,8 @@ "cache_read": 0.023 }, "limit": { - "context": 256000, - "output": 64000 + "context": 131072, + "output": 32768 } }, { @@ -109161,7 +109339,7 @@ "id": "merge-gateway/qwen/qwen3.5-35b-a3b", "name": "Qwen3.5 35B A3B", "family": "qwen", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -109169,8 +109347,7 @@ "last_updated": "2026-02-23", "modalities": { "input": [ - "text", - "image" + "text" ], "output": [ "text" @@ -109183,15 +109360,15 @@ "cache_read": 0.020357 }, "limit": { - "context": 256000, - "output": 64000 + "context": 131072, + "output": 32768 } }, { "id": "merge-gateway/qwen/qwen3.5-397b-a17b", "name": "Qwen3.5 397B A17B", "family": "qwen", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -109199,8 +109376,7 @@ "last_updated": "2026-02-15", "modalities": { "input": [ - "text", - "image" + "text" ], "output": [ "text" @@ -109213,8 +109389,8 @@ "cache_read": 0.0344 }, "limit": { - "context": 256000, - "output": 64000 + "context": 131072, + "output": 32768 } }, { @@ -110258,6 +110434,38 @@ "output": 131072 } }, + { + "id": "merge-gateway/zai/glm-5.3-flash", + "name": "GLM-5.3 Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.25, + "cache_read": 0.015 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "meta-llama/cerebras-llama-4-maverick-17b-128e-instruct", "name": "Cerebras-Llama-4-Maverick-17B-128E-Instruct", @@ -110585,8 +110793,8 @@ "output": 0.0 }, "limit": { - "context": 196608, - "output": 128000 + "context": 204800, + "output": 131072 } }, { @@ -110767,8 +110975,8 @@ "cache_write": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -110795,8 +111003,8 @@ "output": 1.2 }, "limit": { - "context": 196608, - "output": 128000 + "context": 204800, + "output": 131072 } }, { @@ -110976,8 +111184,8 @@ "cache_read": 0.06 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -111004,8 +111212,8 @@ "output": 0.0 }, "limit": { - "context": 196608, - "output": 128000 + "context": 204800, + "output": 131072 } }, { @@ -111186,8 +111394,8 @@ "cache_write": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -111214,8 +111422,8 @@ "output": 1.2 }, "limit": { - "context": 196608, - "output": 128000 + "context": 204800, + "output": 131072 } }, { @@ -111395,8 +111603,8 @@ "cache_read": 0.06 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -112062,6 +112270,35 @@ "output": 32000 } }, + { + "id": "mistralai/zai-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": 1.4, + "output": 4.4, + "cache_read": 0.14 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "mixlayer/qwen/qwen3.5-122b-a10b", "name": "Qwen3.5 122B A10B", @@ -112601,7 +112838,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -112629,7 +112866,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -112656,7 +112893,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -114248,6 +114485,64 @@ "output": 8192 } }, + { + "id": "nano-gpt/Gemma-4-26B-A4B-MeroMero", + "name": "Gemma 4 26B A4B MeroMero", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "nano-gpt/Gemma-4-26B-A4B-MeroMero:thinking", + "name": "Gemma 4 26B A4B MeroMero Thinking", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "nano-gpt/Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled", "name": "Gemma 4 31B Claude 4.6 Opus Reasoning Distilled", @@ -114389,7 +114684,7 @@ "cache_read": 0.04 }, "limit": { - "context": 65536, + "context": 262144, "output": 32768 } }, @@ -114418,7 +114713,7 @@ "cache_read": 0.04 }, "limit": { - "context": 65536, + "context": 262144, "output": 32768 } }, @@ -115302,15 +115597,14 @@ "id": "nano-gpt/TEE/gemma-4-26b-a4b-uncensored", "name": "Gemma 4 26B A4B Uncensored TEE", "family": "gemma", - "attachment": true, + "attachment": false, "reasoning": false, "tool_call": true, "release_date": "2026-05-23", "last_updated": "2026-05-23", "modalities": { "input": [ - "text", - "image" + "text" ], "output": [ "text" @@ -116649,6 +116943,37 @@ "output": 65536 } }, + { + "id": "nano-gpt/alibaba/qwen3.8-flash", + "name": "Qwen3.8 Flash", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.16, + "output": 0.47, + "cache_read": 0.016, + "cache_write": 0.2 + }, + "limit": { + "context": 991808, + "output": 131072 + } + }, { "id": "nano-gpt/amazon/nova-2-lite-v1", "name": "Amazon Nova 2 Lite", @@ -118814,16 +119139,14 @@ { "id": "nano-gpt/claw-high", "name": "Claw High", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "release_date": "2026-05-11", "last_updated": "2026-05-11", "modalities": { "input": [ - "text", - "image", - "pdf" + "text" ], "output": [ "text" @@ -118831,29 +119154,26 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 25.0, - "cache_read": 2.5 + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { "id": "nano-gpt/claw-low", "name": "Claw Low", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "release_date": "2026-05-11", "last_updated": "2026-05-11", "modalities": { "input": [ - "text", - "image", - "video", - "pdf" + "text" ], "output": [ "text" @@ -118861,14 +119181,14 @@ }, "open_weights": false, "cost": { - "input": 0.25, - "output": 1.5, - "cache_read": 0.025, + "input": 1.4, + "output": 4.4, + "cache_read": 0.26, "cache_write": 0.08333 }, "limit": { "context": 1048576, - "output": 65536 + "output": 131072 } }, { @@ -118889,12 +119209,12 @@ }, "open_weights": false, "cost": { - "input": 0.315, - "output": 1.26, - "cache_read": 0.1575 + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 }, "limit": { - "context": 204800, + "context": 1048576, "output": 131072 } }, @@ -122016,7 +122336,7 @@ "cache_read": 0.04 }, "limit": { - "context": 131072, + "context": 262144, "output": 32768 } }, @@ -122045,7 +122365,7 @@ "cache_read": 0.04 }, "limit": { - "context": 131072, + "context": 262144, "output": 32768 } }, @@ -122113,16 +122433,14 @@ "id": "nano-gpt/hermes-high", "name": "Hermes High", "family": "hermes", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "release_date": "2026-05-11", "last_updated": "2026-05-11", "modalities": { "input": [ - "text", - "image", - "pdf" + "text" ], "output": [ "text" @@ -122130,30 +122448,27 @@ }, "open_weights": false, "cost": { - "input": 5.0, - "output": 25.0, - "cache_read": 2.5 + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { "id": "nano-gpt/hermes-low", "name": "Hermes Low", "family": "hermes", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "release_date": "2026-05-11", "last_updated": "2026-05-11", "modalities": { "input": [ - "text", - "image", - "video", - "pdf" + "text" ], "output": [ "text" @@ -122161,14 +122476,14 @@ }, "open_weights": false, "cost": { - "input": 0.25, - "output": 1.5, - "cache_read": 0.025, + "input": 1.4, + "output": 4.4, + "cache_read": 0.26, "cache_write": 0.08333 }, "limit": { "context": 1048576, - "output": 65536 + "output": 131072 } }, { @@ -122190,12 +122505,12 @@ }, "open_weights": false, "cost": { - "input": 0.315, - "output": 1.26, - "cache_read": 0.1575 + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 }, "limit": { - "context": 204800, + "context": 1048576, "output": 131072 } }, @@ -125651,7 +125966,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -125777,7 +126092,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -125841,7 +126156,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -125873,7 +126188,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -125905,7 +126220,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -125937,7 +126252,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -126799,7 +127114,7 @@ "cache_read": 0.025 }, "limit": { - "context": 131072, + "context": 262144, "output": 32768 } }, @@ -126828,7 +127143,7 @@ "cache_read": 0.025 }, "limit": { - "context": 131072, + "context": 262144, "output": 32768 } }, @@ -128008,7 +128323,7 @@ "cache_read": 0.075 }, "limit": { - "context": 65536, + "context": 262144, "output": 32768 } }, @@ -128037,10 +128352,43 @@ "cache_read": 0.075 }, "limit": { - "context": 65536, + "context": 262144, "output": 32768 } }, + { + "id": "nano-gpt/qwen/qwen3.8-2.4t-a95b", + "name": "Qwen3.8 2.4T A95B (Max)", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.25, + "cache_write": 2.5 + }, + "limit": { + "context": 991000, + "output": 65536 + } + }, { "id": "nano-gpt/qwen/qwen3.8-27b-obliterated", "name": "Qwen 3.8 27B Obliterated", @@ -128099,6 +128447,64 @@ "output": 32768 } }, + { + "id": "nano-gpt/qwen/qwen3.8-27b-uncensored", + "name": "Qwen 3.8 27B Uncensored", + "family": "qwen", + "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": 0.18, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "nano-gpt/qwen/qwen3.8-27b-uncensored:thinking", + "name": "Qwen 3.8 27B Uncensored Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-25", + "last_updated": "2026-08-25", + "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", @@ -129384,35 +129790,6 @@ "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", @@ -130565,6 +130942,37 @@ "output": 131072 } }, + { + "id": "nano-gpt/z-ai/glm-5.3-flash", + "name": "GLM 5.3 Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.25, + "cache_read": 0.015 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "nano-gpt/z-ai/glm-5v-turbo", "name": "GLM 5V Turbo", @@ -132258,7 +132666,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -132289,7 +132697,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -132320,7 +132728,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -132352,7 +132760,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -132383,7 +132791,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -134975,6 +135383,126 @@ "output": 25000 } }, + { + "id": "neosmith/neosmith.intelligent-basic", + "name": "NeoSmith Basic", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-26", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.17, + "output": 4.37, + "cache_read": 0.22, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "neosmith/neosmith.intelligent-maestro", + "name": "NeoSmith Maestro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-03", + "last_updated": "2026-08-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.4, + "output": 12.0, + "cache_read": 0.35, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "neosmith/neosmith.intelligent-pro", + "name": "NeoSmith Pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-26", + "last_updated": "2026-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.81, + "output": 8.39, + "cache_read": 0.3, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "neosmith/neosmith.neolite", + "name": "NeoSmith NeoLite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-20", + "last_updated": "2026-08-03", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 2.4, + "cache_read": 0.08, + "cache_write": 0.0 + }, + "limit": { + "context": 512000, + "output": 64000 + } + }, { "id": "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8", "name": "Qwen3.5 397B A17B FP8", @@ -135055,15 +135583,75 @@ }, "open_weights": true, "cost": { - "input": 0.104, - "output": 0.207, - "cache_read": 0.026 + "input": 0.14, + "output": 0.28, + "cache_read": 0.028 }, "limit": { "context": 1048560, "output": 65536 } }, + { + "id": "neuralwatt/deepseek-v4-flash-flex", + "name": "DeepSeek V4 Flash Flex", + "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": 0.091, + "output": 0.182, + "cache_read": 0.0182 + }, + "limit": { + "context": 1048560, + "output": 65536 + } + }, + { + "id": "neuralwatt/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": 1.0, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 1048560, + "output": 393216 + } + }, { "id": "neuralwatt/gemma-4-31b", "name": "Gemma 4 31B", @@ -135569,6 +136157,36 @@ "output": 262144 } }, + { + "id": "neuralwatt/qwen-3.8-27b", + "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": 0.25 + }, + "limit": { + "context": 262128, + "output": 65536 + } + }, { "id": "neuralwatt/qwen3.5-397b-fast", "name": "Qwen3.5 397B Fast", @@ -143165,8 +143783,8 @@ "output": 1.2 }, "limit": { - "context": 200000, - "output": 131000 + "context": 65536, + "output": 2048 } }, { @@ -143195,8 +143813,8 @@ "cache_write": 0.375 }, "limit": { - "context": 196608, - "output": 128000 + "context": 204800, + "output": 131072 } }, { @@ -143406,8 +144024,8 @@ "cache_read": 0.12 }, "limit": { - "context": 512000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -143797,7 +144415,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -143890,7 +144508,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -143953,7 +144571,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -143985,7 +144603,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -144017,7 +144635,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -144048,7 +144666,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -144266,7 +144884,7 @@ "id": "ofox/volcengine/doubao-seed-1.6-flash", "name": "Seed 1.6 Flash", "family": "seed", - "attachment": false, + "attachment": true, "reasoning": false, "tool_call": true, "temperature": true, @@ -144274,7 +144892,8 @@ "last_updated": "2025-08-28", "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -144325,7 +144944,7 @@ "id": "ofox/volcengine/doubao-seed-1.8", "name": "Seed 1.8", "family": "seed", - "attachment": false, + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, @@ -144333,7 +144952,8 @@ "last_updated": "2025-12-28", "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -145933,7 +146553,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -145964,7 +146584,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -146087,7 +146707,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -146151,7 +146771,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -146183,7 +146803,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -146214,7 +146834,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -146354,10 +146974,10 @@ }, "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, @@ -146420,10 +147040,10 @@ }, "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, @@ -147086,6 +147706,38 @@ "output": 131072 } }, + { + "id": "opencode-go/glm-5.3-flash", + "name": "GLM-5.3-Flash (2x usage)", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.25, + "cache_read": 0.015 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "opencode-go/gpt-5.6-luna", "name": "GPT-5.6 Luna", @@ -147139,6 +147791,37 @@ ] }, "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 0.3 + }, + "limit": { + "context": 500000, + "output": 500000 + } + }, + { + "id": "opencode-go/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, @@ -149121,7 +149804,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -149428,7 +150111,7 @@ "cost": { "input": 2.0, "output": 6.0, - "cache_read": 0.5 + "cache_read": 0.3 }, "limit": { "context": 500000, @@ -150797,7 +151480,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 29491 } }, { @@ -150825,7 +151508,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -151592,7 +152275,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -151830,7 +152513,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -152091,7 +152774,7 @@ }, "limit": { "context": 163840, - "output": 163840 + "output": 147456 } }, { @@ -152121,7 +152804,7 @@ }, "limit": { "context": 163840, - "output": 161000 + "output": 144900 } }, { @@ -152179,7 +152862,7 @@ }, "limit": { "context": 8192, - "output": 8192 + "output": 7372 } }, { @@ -152239,7 +152922,7 @@ }, "limit": { "context": 163840, - "output": 163840 + "output": 147456 } }, { @@ -152292,9 +152975,9 @@ }, "open_weights": true, "cost": { - "input": 0.056, - "output": 0.112, - "cache_read": 0.0112 + "input": 0.07952, + "output": 0.15904, + "cache_read": 0.015904 }, "limit": { "context": 1048576, @@ -152352,9 +153035,9 @@ }, "open_weights": true, "cost": { - "input": 0.522, - "output": 1.044, - "cache_read": 0.0435 + "input": 0.87, + "output": 1.74, + "cache_read": 0.0725 }, "limit": { "context": 1048576, @@ -152386,7 +153069,7 @@ }, "limit": { "context": 512000, - "output": 512000 + "output": 460800 } }, { @@ -152756,7 +153439,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -152822,7 +153505,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -153157,7 +153840,7 @@ }, "limit": { "context": 262144, - "output": 131072 + "output": 117964 } }, { @@ -153190,35 +153873,6 @@ "output": 16384 } }, - { - "id": "openrouter/google/gemma-3n-e4b-it", - "name": "Gemma 3n 4B", - "family": "gemma", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "knowledge": "2024-08-31", - "release_date": "2025-05-20", - "last_updated": "2025-05-20", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.06, - "output": 0.12 - }, - "limit": { - "context": 32768, - "output": 32768 - } - }, { "id": "openrouter/google/gemma-4-26b-a4b-it", "name": "Gemma 4 26B A4B IT", @@ -153301,13 +153955,13 @@ }, "open_weights": true, "cost": { - "input": 0.1, + "input": 0.09, "output": 0.34, - "cache_read": 0.1 + "cache_read": 0.05 }, "limit": { "context": 262144, - "output": 262144 + "output": 16384 } }, { @@ -153425,7 +154079,7 @@ }, "limit": { "context": 8192, - "output": 4096 + "output": 3686 } }, { @@ -153453,7 +154107,7 @@ }, "limit": { "context": 131000, - "output": 131000 + "output": 117900 } }, { @@ -153482,7 +154136,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -153772,7 +154426,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -153801,7 +154455,7 @@ }, "limit": { "context": 60000, - "output": 60000 + "output": 54000 } }, { @@ -153830,7 +154484,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -153854,12 +154508,13 @@ }, "open_weights": true, "cost": { - "input": 0.1, - "output": 0.32 + "input": 0.71, + "output": 0.71, + "cache_read": 0.71 }, "limit": { "context": 131072, - "output": 16384 + "output": 115200 } }, { @@ -153914,12 +154569,13 @@ }, "open_weights": true, "cost": { - "input": 0.1, - "output": 0.3 + "input": 0.11, + "output": 0.34, + "cache_read": 0.055 }, "limit": { "context": 1310720, - "output": 16384 + "output": 8192 } }, { @@ -153948,7 +154604,7 @@ "output": 0.18 }, "limit": { - "context": 1048576, + "context": 163840, "output": 16384 } }, @@ -153980,7 +154636,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -154013,7 +154669,7 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 943718 } }, { @@ -154046,7 +154702,7 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 943718 } }, { @@ -154079,7 +154735,7 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 943718 } }, { @@ -154108,7 +154764,7 @@ }, "limit": { "context": 16384, - "output": 16384 + "output": 14745 } }, { @@ -154166,7 +154822,7 @@ }, "limit": { "context": 1000192, - "output": 1000192 + "output": 900172 } }, { @@ -154342,6 +154998,34 @@ "output": 131072 } }, + { + "id": "openrouter/minimax/minimax-m2.7:free", + "name": "MiniMax M2.7 (free)", + "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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 196608, + "output": 176947 + } + }, { "id": "openrouter/minimax/minimax-m3", "name": "MiniMax-M3", @@ -154373,6 +155057,36 @@ "output": 512000 } }, + { + "id": "openrouter/minimax/minimax-m3:free", + "name": "MiniMax M3 (free)", + "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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1048576, + "output": 943718 + } + }, { "id": "openrouter/mistralai/codestral", "name": "Codestral 2508", @@ -154401,7 +155115,7 @@ }, "limit": { "context": 256000, - "output": 256000 + "output": 204800 } }, { @@ -154432,7 +155146,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 209715 } }, { @@ -154462,7 +155176,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 209715 } }, { @@ -154492,7 +155206,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 104857 } }, { @@ -154521,7 +155235,7 @@ }, "limit": { "context": 128000, - "output": 128000 + "output": 102400 } }, { @@ -154552,7 +155266,7 @@ }, "limit": { "context": 128000, - "output": 128000 + "output": 102400 } }, { @@ -154584,7 +155298,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 104857 } }, { @@ -154616,7 +155330,7 @@ }, "limit": { "context": 131072, - "output": 262144 + "output": 104857 } }, { @@ -154646,7 +155360,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 209715 } }, { @@ -154706,7 +155420,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 26214 } }, { @@ -154737,7 +155451,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 209715 } }, { @@ -154796,7 +155510,7 @@ }, "limit": { "context": 128000, - "output": 128000 + "output": 102400 } }, { @@ -154857,7 +155571,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 52428 } }, { @@ -154888,7 +155602,7 @@ }, "limit": { "context": 32000, - "output": 32000 + "output": 25600 } }, { @@ -154978,7 +155692,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -155009,7 +155723,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -155034,13 +155748,13 @@ }, "open_weights": true, "cost": { - "input": 0.67, + "input": 0.66, "output": 3.4, - "cache_read": 0.19 + "cache_read": 0.18 }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -155071,7 +155785,7 @@ }, "limit": { "context": 1048576, - "output": 1048576 + "output": 943718 } }, { @@ -155157,7 +155871,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -155187,7 +155901,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -155274,7 +155988,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -155303,7 +156017,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -155328,11 +156042,11 @@ "cost": { "input": 0.05, "output": 0.2, - "cache_read": 0.03 + "cache_read": 0.025 }, "limit": { "context": 262144, - "output": 262144 + "output": 228000 } }, { @@ -155419,7 +156133,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -155448,7 +156162,7 @@ }, "limit": { "context": 512288, - "output": 16384 + "output": 461059 } }, { @@ -155649,7 +156363,7 @@ }, "limit": { "context": 4095, - "output": 4096 + "output": 3685 } }, { @@ -156911,7 +157625,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -156940,7 +157654,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -157409,7 +158123,7 @@ }, "limit": { "context": 127072, - "output": 127072 + "output": 114364 } }, { @@ -157437,7 +158151,7 @@ }, "limit": { "context": 128000, - "output": 128000 + "output": 115200 } }, { @@ -157524,7 +158238,7 @@ }, "limit": { "context": 128000, - "output": 128000 + "output": 115200 } }, { @@ -157696,7 +158410,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 29491 } }, { @@ -157725,7 +158439,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 29491 } }, { @@ -157759,35 +158473,6 @@ "output": 32768 } }, - { - "id": "openrouter/qwen/qwen-plus-2025-07-28:thinking", - "name": "Qwen Plus 0728 (thinking)", - "family": "qwen", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-03-31", - "release_date": "2025-09-08", - "last_updated": "2025-09-08", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.26, - "output": 0.78 - }, - "limit": { - "context": 1000000, - "output": 32768 - } - }, { "id": "openrouter/qwen/qwen2.5-vl-72b-instruct", "name": "Qwen2.5 VL 72B Instruct", @@ -157810,13 +158495,12 @@ }, "open_weights": true, "cost": { - "input": 0.8, - "output": 1.0, - "cache_read": 0.4 + "input": 0.25, + "output": 0.75 }, "limit": { "context": 128000, - "output": 128000 + "output": 28800 } }, { @@ -157903,7 +158587,7 @@ }, "limit": { "context": 131072, - "output": 32768 + "output": 117964 } }, { @@ -158106,7 +158790,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -158167,7 +158851,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -158287,7 +158971,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -158554,7 +159238,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -158615,7 +159299,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -158640,13 +159324,12 @@ }, "open_weights": true, "cost": { - "input": 0.5, - "output": 3.6, - "cache_read": 0.3 + "input": 0.39, + "output": 2.34 }, "limit": { "context": 262144, - "output": 262144 + "output": 65536 } }, { @@ -158676,7 +159359,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -158793,12 +159476,13 @@ }, "open_weights": true, "cost": { - "input": 0.32, - "output": 3.2 + "input": 0.6, + "output": 3.6, + "cache_read": 0.12 }, "limit": { "context": 262144, - "output": 81920 + "output": 235929 } }, { @@ -158823,13 +159507,13 @@ }, "open_weights": true, "cost": { - "input": 0.14, - "output": 1.0, + "input": 0.1, + "output": 0.9, "cache_read": 0.05 }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -159070,9 +159754,42 @@ }, "open_weights": true, "cost": { - "input": 0.4, - "output": 3.0, - "cache_read": 0.05 + "input": 0.425, + "output": 2.55, + "cache_read": 0.085, + "cache_write": 0.53125 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "openrouter/qwen/qwen3.8-flash", + "name": "Qwen3.8 Flash", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.47, + "cache_read": 0.016, + "cache_write": 0.2 }, "limit": { "context": 1000000, @@ -159138,7 +159855,7 @@ }, "limit": { "context": 16384, - "output": 16384 + "output": 14745 } }, { @@ -159167,7 +159884,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -159311,7 +160028,7 @@ }, "limit": { "context": 8192, - "output": 16384 + "output": 7372 } }, { @@ -159372,36 +160089,6 @@ "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", @@ -159458,7 +160145,7 @@ }, "limit": { "context": 262144, - "output": 256000 + "output": 230400 } }, { @@ -159487,7 +160174,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -159629,7 +160316,7 @@ }, "limit": { "context": 262144, - "output": 262144 + "output": 235929 } }, { @@ -159658,7 +160345,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -159686,7 +160373,7 @@ }, "limit": { "context": 65536, - "output": 65536 + "output": 58982 } }, { @@ -159715,7 +160402,7 @@ }, "limit": { "context": 32768, - "output": 32768 + "output": 29491 } }, { @@ -159743,7 +160430,7 @@ }, "limit": { "context": 1024000, - "output": 32768 + "output": 26214 } }, { @@ -159768,9 +160455,9 @@ }, "open_weights": true, "cost": { - "input": 1.0, + "input": 0.95, "output": 4.05, - "cache_read": 0.17 + "cache_read": 0.16 }, "limit": { "context": 1048576, @@ -159922,7 +160609,7 @@ }, "limit": { "context": 131072, - "output": 131072 + "output": 117964 } }, { @@ -160011,7 +160698,7 @@ }, "limit": { "context": 2000000, - "output": 2000000 + "output": 1800000 } }, { @@ -160043,7 +160730,7 @@ }, "limit": { "context": 2000000, - "output": 2000000 + "output": 1800000 } }, { @@ -160074,7 +160761,7 @@ }, "limit": { "context": 1000000, - "output": 1000000 + "output": 900000 } }, { @@ -160105,7 +160792,7 @@ }, "limit": { "context": 500000, - "output": 500000 + "output": 450000 } }, { @@ -160137,7 +160824,7 @@ }, "limit": { "context": 500000, - "output": 500000 + "output": 450000 } }, { @@ -160168,7 +160855,7 @@ }, "limit": { "context": 256000, - "output": 256000 + "output": 230400 } }, { @@ -160346,13 +161033,13 @@ }, "open_weights": true, "cost": { - "input": 0.5, - "output": 2.0, - "cache_read": 0.1 + "input": 0.43, + "output": 1.75, + "cache_read": 0.08 }, "limit": { "context": 204800, - "output": 131072 + "output": 16384 } }, { @@ -160525,13 +161212,13 @@ }, "open_weights": true, "cost": { - "input": 0.966, - "output": 3.036, - "cache_read": 0.1794 + "input": 1.26, + "output": 3.96, + "cache_read": 0.234 }, "limit": { "context": 204800, - "output": 128000 + "output": 182476 } }, { @@ -160554,13 +161241,13 @@ }, "open_weights": true, "cost": { - "input": 0.966, - "output": 3.036, - "cache_read": 0.1932 + "input": 1.19, + "output": 3.74, + "cache_read": 0.221 }, "limit": { "context": 1048576, - "output": 131072 + "output": 262144 } }, { @@ -160588,7 +161275,7 @@ }, "limit": { "context": 256000, - "output": 256000 + "output": 230400 } }, { @@ -160620,6 +161307,37 @@ "output": 131072 } }, + { + "id": "openrouter/z-ai/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.25, + "cache_read": 0.015 + }, + "limit": { + "context": 1310720, + "output": 131072 + } + }, { "id": "openrouter/z-ai/glm-5v-turbo", "name": "GLM-5V-Turbo", @@ -160800,13 +161518,13 @@ }, "open_weights": false, "cost": { - "input": 0.035, - "output": 0.12, - "cache_read": 0.01 + "input": 0.03, + "output": 0.1, + "cache_read": 0.007 }, "limit": { "context": 1310720, - "output": 1048576 + "output": 131072 } }, { @@ -160901,13 +161619,13 @@ }, "open_weights": false, "cost": { - "input": 2.6, - "output": 13.0, - "cache_read": 0.29 + "input": 2.55, + "output": 12.75, + "cache_read": 0.256 }, "limit": { "context": 1048576, - "output": 974842 + "output": 943718 } }, { @@ -161003,7 +161721,7 @@ }, "limit": { "context": 500000, - "output": 1000000 + "output": 450000 } }, { @@ -161562,7 +162280,7 @@ }, "limit": { "context": 1048576, - "output": 128000 + "output": 512000 } }, { @@ -161723,7 +162441,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -161755,7 +162473,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -161787,7 +162505,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -161818,7 +162536,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -163630,7 +164348,7 @@ "attachment": true, "reasoning": true, "tool_call": false, - "temperature": true, + "temperature": false, "knowledge": "2024-09-30", "release_date": "2025-08-07", "last_updated": "2025-08-07", @@ -163784,7 +164502,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -163939,7 +164657,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -164094,7 +164812,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -164126,7 +164844,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -164158,7 +164876,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -164189,7 +164907,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -165142,6 +165860,179 @@ "output": 16384 } }, + { + "id": "pendra/deepseek-v4-flash", + "name": "DeepSeek V4 Flash", + "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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, + { + "id": "pendra/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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "pendra/gpt-oss:120b", + "name": "GPT OSS 120B", + "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": "pendra/llama3.3:70b", + "name": "Llama-3.3-70B-Instruct", + "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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "pendra/qwen3-coder:30b", + "name": "Qwen3-Coder 30B-A3B Instruct", + "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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "pendra/qwen3.6:27b", + "name": "Qwen3.6 27B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "perplexity-agent/anthropic/claude-haiku-4.5", "name": "Claude Haiku 4.5", @@ -167800,7 +168691,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -167832,7 +168723,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -167865,7 +168756,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -167898,7 +168789,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -167930,7 +168821,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -178233,6 +179124,38 @@ "output": 128000 } }, + { + "id": "requesty/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.135, + "output": 0.45, + "cache_read": 0.027 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "requesty/gpt-4.1-mini@eu", "name": "GPT-4.1 mini (EU)", @@ -178429,7 +179352,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -178489,7 +179412,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -178521,7 +179444,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -178553,7 +179476,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -178584,7 +179507,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -178646,7 +179569,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -182599,7 +183522,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -182630,7 +183553,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -183964,8 +184887,8 @@ "cache_read": 0.0 }, "limit": { - "context": 512000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -187349,7 +188272,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2024-09-30", "release_date": "2025-11-13", "last_updated": "2025-11-13", @@ -187376,7 +188299,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -187403,7 +188326,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -187789,6 +188712,35 @@ "output": 8192 } }, + { + "id": "standardcompute/standardcompute", + "name": "Standard Compute", + "family": "auto", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-01", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1000000, + "output": 24576 + } + }, { "id": "stepfun-ai-step-plan/step-3.5-flash", "name": "Step 3.5 Flash", @@ -192471,7 +193423,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -192501,7 +193453,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -192532,7 +193484,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -193394,10 +194346,10 @@ }, "open_weights": false, "cost": { - "input": 3.0, - "output": 15.0, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2.0, + "output": 10.000000000000002, + "cache_read": 0.2, + "cache_write": 2.5000000000000004 }, "limit": { "context": 1000000, @@ -193683,9 +194635,9 @@ }, "open_weights": false, "cost": { - "input": 1.875, - "output": 9.375, - "cache_read": 0.1875 + "input": 0.9375, + "output": 4.6875, + "cache_read": 0.09375 }, "limit": { "context": 1000000, @@ -193716,9 +194668,9 @@ }, "open_weights": false, "cost": { - "input": 1.875, - "output": 9.375, - "cache_read": 0.1875 + "input": 0.9375, + "output": 4.6875, + "cache_read": 0.09375 }, "limit": { "context": 1000000, @@ -194615,7 +195567,7 @@ "attachment": false, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-13", "last_updated": "2026-06-11", @@ -194676,7 +195628,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-24", "last_updated": "2026-06-11", @@ -194707,7 +195659,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-06-11", @@ -194738,7 +195690,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-27", "last_updated": "2026-06-11", @@ -195580,36 +196532,6 @@ "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", @@ -195757,6 +196679,37 @@ "output": 131072 } }, + { + "id": "venice/z-ai-glm-5.3-flash", + "name": "GLM 5.3 Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-21", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, { "id": "venice/z-ai-glm-5v-turbo", "name": "GLM 5V Turbo", @@ -196857,6 +197810,37 @@ "output": 131072 } }, + { + "id": "vercel/alibaba/qwen3.8-flash", + "name": "Qwen 3.8 Flash", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.16, + "output": 0.47, + "cache_read": 0.016, + "cache_write": 0.2 + }, + "limit": { + "context": 991000, + "output": 128000 + } + }, { "id": "vercel/alibaba/qwen3.8-max", "name": "Qwen 3.8 Max", @@ -197088,6 +198072,31 @@ "output": 0 } }, + { + "id": "vercel/alibaba/wan-v3.0-video", + "name": "Wan v3.0 Video", + "family": "o", + "attachment": true, + "reasoning": false, + "tool_call": false, + "release_date": "2026-08-23", + "last_updated": "2026-08-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/amazon/nova-2-lite", "name": "Nova 2 Lite", @@ -199380,6 +200389,57 @@ "output": 65000 } }, + { + "id": "vercel/google/gemini-3.5-transcribe", + "name": "Gemini 3.5 Transcribe", + "family": "gemini", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0 + }, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/google/gemini-3.5-transcribe-live", + "name": "Gemini 3.5 Transcribe Live", + "family": "gemini", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", @@ -200372,6 +201432,31 @@ "output": 131072 } }, + { + "id": "vercel/meta/muse-image-1.0", + "name": "Muse Image 1.0", + "family": "muse", + "attachment": true, + "reasoning": false, + "tool_call": false, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "vercel/meta/muse-spark-1.1", "name": "Muse Spark 1.1", @@ -200671,6 +201756,34 @@ "output": 131000 } }, + { + "id": "vercel/minimax/minimax-m2.7-free", + "name": "Minimax M2.7 (Free)", + "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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 196608, + "output": 196608 + } + }, { "id": "vercel/minimax/minimax-m2.7-highspeed", "name": "MiniMax M2.7 High Speed", @@ -200732,6 +201845,36 @@ "output": 1000000 } }, + { + "id": "vercel/minimax/minimax-m3-free", + "name": "MiniMax M3 (Free)", + "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" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1048576, + "output": 1048576 + } + }, { "id": "vercel/mistral/codestral", "name": "Codestral (latest)", @@ -201545,40 +202688,13 @@ }, "open_weights": true, "cost": { - "input": 0.0, - "output": 0.0 + "input": 0.05, + "output": 0.15, + "cache_read": 0.05 }, "limit": { - "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 + "context": 262144, + "output": 131072 } }, { @@ -202522,7 +203638,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2025-12-11", "last_updated": "2025-12-11", @@ -202617,7 +203733,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-05", "last_updated": "2026-02-05", @@ -202681,7 +203797,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -202745,7 +203861,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -203300,6 +204416,34 @@ "output": 8192 } }, + { + "id": "vercel/openai/gpt-oss-safeguard-120b", + "name": "GPT OSS Safeguard 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-29", + "last_updated": "2025-10-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 16000 + } + }, { "id": "vercel/openai/gpt-oss-safeguard-20b", "name": "gpt-oss-safeguard-20b", @@ -203321,13 +204465,12 @@ }, "open_weights": false, "cost": { - "input": 0.075, - "output": 0.3, - "cache_read": 0.037 + "input": 0.07, + "output": 0.2 }, "limit": { - "context": 131072, - "output": 65536 + "context": 128000, + "output": 16000 } }, { @@ -204591,8 +205734,9 @@ "attachment": true, "reasoning": true, "tool_call": true, - "release_date": "2026-04-30", - "last_updated": "2026-04-30", + "temperature": true, + "release_date": "2026-04-17", + "last_updated": "2026-04-17", "modalities": { "input": [ "text", @@ -204621,6 +205765,7 @@ "attachment": true, "reasoning": true, "tool_call": true, + "temperature": true, "release_date": "2026-07-08", "last_updated": "2026-07-08", "modalities": { @@ -204651,6 +205796,8 @@ "attachment": true, "reasoning": true, "tool_call": true, + "temperature": true, + "knowledge": "2026-02-01", "release_date": "2026-08-12", "last_updated": "2026-08-12", "modalities": { @@ -204680,8 +205827,9 @@ "attachment": true, "reasoning": true, "tool_call": true, - "release_date": "2026-05-20", - "last_updated": "2026-05-20", + "temperature": true, + "release_date": "2026-04-16", + "last_updated": "2026-04-16", "modalities": { "input": [ "text", @@ -204733,6 +205881,7 @@ "attachment": false, "reasoning": false, "tool_call": false, + "temperature": false, "release_date": "2026-08-07", "last_updated": "2026-08-07", "modalities": { @@ -204781,8 +205930,9 @@ "attachment": false, "reasoning": false, "tool_call": false, - "release_date": "2026-06-22", - "last_updated": "2026-06-22", + "temperature": false, + "release_date": "2026-05-30", + "last_updated": "2026-05-30", "modalities": { "input": [ "text" @@ -205898,6 +207048,36 @@ "output": 12800 } }, + { + "id": "vercel/zai/glm-5.3-flash", + "name": "GLM 5.3 Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1000000, + "output": 131000 + } + }, { "id": "vercel/zai/glm-5v-turbo", "name": "GLM 5V Turbo", @@ -206087,6 +207267,40 @@ "output": 65536 } }, + { + "id": "vivgrid/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": "vivgrid/glm-5.2", "name": "GLM-5.2", @@ -206558,6 +207772,461 @@ "output": 131072 } }, + { + "id": "volcengine/deepseek-v4-flash-ga-260731", + "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": 0.4453, + "output": 1.3359, + "cache_read": 0.01484 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, + { + "id": "volcengine/deepseek-v4-pro-ga-260813", + "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": 1.3359, + "output": 4.00771, + "cache_read": 0.04453 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, + { + "id": "volcengine/doubao-seed-1.6-251015", + "name": "Seed 1.6", + "family": "seed", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11875, + "output": 1.18747, + "cache_read": 0.02375 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "volcengine/doubao-seed-1.6-flash-250828", + "name": "Seed 1.6 Flash", + "family": "seed", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-28", + "last_updated": "2025-08-28", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02227, + "output": 0.22265, + "cache_read": 0.00445 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "volcengine/doubao-seed-1.6-vision-250815", + "name": "Seed 1.6 Vision", + "family": "seed", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-15", + "last_updated": "2025-08-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11875, + "output": 1.18747, + "cache_read": 0.02375 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "volcengine/doubao-seed-1.8-251228", + "name": "Seed 1.8", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-28", + "last_updated": "2025-12-28", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11875, + "output": 1.18747, + "cache_read": 0.02375 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "volcengine/doubao-seed-2.0-code-preview-260215", + "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": 0.47499, + "output": 2.37494, + "cache_read": 0.095 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "volcengine/doubao-seed-2.0-lite-260428", + "name": "Seed 2.0 Lite", + "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": 0.08906, + "output": 0.53436, + "cache_read": 0.01781 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "volcengine/doubao-seed-2.0-mini-260428", + "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": 0.02969, + "output": 0.29687, + "cache_read": 0.00594 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "volcengine/doubao-seed-2.0-pro-260215", + "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": 0.47499, + "output": 2.37494, + "cache_read": 0.095 + }, + "limit": { + "context": 256000, + "output": 128000 + } + }, + { + "id": "volcengine/doubao-seed-2.1-pro-260628", + "name": "Seed 2.1 Pro", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-23", + "last_updated": "2026-06-23", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8906, + "output": 4.45301, + "cache_read": 0.17812 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "volcengine/doubao-seed-2.1-turbo-260628", + "name": "Seed 2.1 Turbo", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-23", + "last_updated": "2026-06-23", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4453, + "output": 2.22651, + "cache_read": 0.08906 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "volcengine/doubao-seed-character-260628", + "name": "Seed Character", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-23", + "last_updated": "2026-06-23", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11875, + "output": 0.29687, + "cache_read": 0.02375 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "volcengine/doubao-seed-evolving", + "name": "Seed Evolving", + "family": "seed", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-06-23", + "last_updated": "2026-06-23", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8906, + "output": 4.45301, + "cache_read": 0.17812 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "volcengine/glm-5.2-260617", + "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": 1.18747, + "output": 4.15615, + "cache_read": 0.29687 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "vultr/MiniMaxAI/MiniMax-M2.7", "name": "MiniMax-M2.7", @@ -206972,7 +208641,7 @@ }, "limit": { "context": 1048576, - "output": 128000 + "output": 512000 } }, { @@ -207033,35 +208702,6 @@ "output": 131072 } }, - { - "id": "wandb/MiniMaxAI/MiniMax-M2.5", - "name": "MiniMax M2.5", - "family": "minimax-m2.5", - "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": 0.3 - }, - "limit": { - "context": 196608, - "output": 196608 - } - }, { "id": "wandb/MiniMaxAI/MiniMax-M3", "name": "MiniMax M3", @@ -207150,36 +208790,6 @@ "output": 262144 } }, - { - "id": "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct", - "name": "Qwen3 Coder 480B A35B", - "family": "qwen", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2025-04", - "release_date": "2025-07-22", - "last_updated": "2025-07-22", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 1.0, - "output": 1.5, - "cache_read": 1.0 - }, - "limit": { - "context": 262144, - "output": 262144 - } - }, { "id": "wandb/Qwen/Qwen3.5-35B-A3B", "name": "Qwen3.5-35B-A3B", @@ -207448,6 +209058,35 @@ "output": 131072 } }, + { + "id": "wandb/ibm-granite/granite-4.2-8b", + "name": "Granite 4.2 8B", + "family": "granite", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-24", + "last_updated": "2026-08-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.15, + "cache_read": 0.05 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, { "id": "wandb/meta-llama/Llama-3.1-70B-Instruct", "name": "Llama 3.1 70B", @@ -207473,8 +209112,8 @@ "cache_read": 0.8 }, "limit": { - "context": 128000, - "output": 128000 + "context": 131072, + "output": 131072 } }, { @@ -207503,8 +209142,8 @@ "cache_read": 0.22 }, "limit": { - "context": 128000, - "output": 128000 + "context": 131072, + "output": 131072 } }, { @@ -207629,35 +209268,6 @@ "output": 1048576 } }, - { - "id": "wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", - "name": "Nemotron 3 Super", - "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": 0.2, - "output": 0.8, - "cache_read": 0.2 - }, - "limit": { - "context": 262144, - "output": 262144 - } - }, { "id": "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "name": "Nemotron 3 Ultra", @@ -207774,35 +209384,6 @@ "output": 131072 } }, - { - "id": "wandb/zai-org/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": 1.4, - "output": 4.4, - "cache_read": 0.26 - }, - "limit": { - "context": 202752, - "output": 202752 - } - }, { "id": "wandb/zai-org/GLM-5.2", "name": "GLM 5.2", @@ -207828,8 +209409,8 @@ "cache_read": 0.14 }, "limit": { - "context": 262144, - "output": 262144 + "context": 1048576, + "output": 1048576 } }, { @@ -209287,7 +210868,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-05", "last_updated": "2026-03-05", @@ -209318,7 +210899,7 @@ "attachment": true, "reasoning": true, "tool_call": true, - "temperature": false, + "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-03-17", "last_updated": "2026-03-17", @@ -209678,6 +211259,69 @@ "output": 131072 } }, + { + "id": "zai-coding-plan/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "zai-coding-plan/glm-5.3-highspeed", + "name": "GLM-5.3 Highspeed", + "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": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "zai/glm-4.5", "name": "GLM-4.5", @@ -210077,6 +211721,69 @@ "output": 131072 } }, + { + "id": "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, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "zai/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.25, + "cache_read": 0.015, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "zai/glm-5v-turbo", "name": "GLM-5V-Turbo", @@ -211404,8 +213111,8 @@ "output": 2.4 }, "limit": { - "context": 512000, - "output": 128000 + "context": 1048576, + "output": 512000 } }, { @@ -214028,6 +215735,69 @@ "output": 131072 } }, + { + "id": "zhipuai-coding-plan/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "zhipuai-coding-plan/glm-5.3-highspeed", + "name": "GLM-5.3 Highspeed", + "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": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "zhipuai-coding-plan/glm-5v-turbo", "name": "GLM-5V-Turbo", @@ -214430,6 +216200,69 @@ "output": 131072 } }, + { + "id": "zhipuai/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, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "zhipuai/glm-5.3-flash", + "name": "GLM-5.3-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-08-26", + "last_updated": "2026-08-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.25, + "cache_read": 0.015, + "cache_write": 0.0 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, { "id": "zhipuai/glm-5v-turbo", "name": "GLM-5V-Turbo", 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 f3d8425cd..4bbc279bd 100644 --- a/crates/goose-provider-types/src/canonical/data/provider_metadata.json +++ b/crates/goose-provider-types/src/canonical/data/provider_metadata.json @@ -43,6 +43,17 @@ ], "model_count": 3 }, + { + "id": "agnes", + "display_name": "Agnes AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://apihub.agnes-ai.com/v1", + "doc": "https://agnes-ai.com/doc", + "env": [ + "AGNES_API_KEY" + ], + "model_count": 3 + }, { "id": "ai-router", "display_name": "AI-ROUTER", @@ -65,6 +76,17 @@ ], "model_count": 9 }, + { + "id": "aixy", + "display_name": "Aixy", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.aixy-gateway.com/v1", + "doc": "https://docs.aixy-gateway.com/integrations/overview", + "env": [ + "AIXY_API_KEY" + ], + "model_count": 1 + }, { "id": "aki-io", "display_name": "AKI.IO", @@ -228,7 +250,7 @@ "env": [ "BASETEN_API_KEY" ], - "model_count": 19 + "model_count": 20 }, { "id": "berget", @@ -294,7 +316,7 @@ "env": [ "CLINE_API_KEY" ], - "model_count": 11 + "model_count": 13 }, { "id": "cloudferro-sherlock", @@ -317,7 +339,7 @@ "CLOUDFLARE_ACCOUNT_ID", "CLOUDFLARE_API_KEY" ], - "model_count": 25 + "model_count": 26 }, { "id": "coralbricks", @@ -406,7 +428,7 @@ "env": [ "DEEPSEEK_API_KEY" ], - "model_count": 5 + "model_count": 3 }, { "id": "digitalocean", @@ -472,7 +494,7 @@ "env": [ "EDENAI_API_KEY" ], - "model_count": 232 + "model_count": 235 }, { "id": "empiriolabs", @@ -483,7 +505,7 @@ "env": [ "EMPIRIOLABS_API_KEY" ], - "model_count": 55 + "model_count": 57 }, { "id": "evroc", @@ -494,7 +516,7 @@ "env": [ "EVROC_API_KEY" ], - "model_count": 15 + "model_count": 16 }, { "id": "fastrouter", @@ -571,7 +593,7 @@ "env": [ "GMICLOUD_API_KEY" ], - "model_count": 13 + "model_count": 15 }, { "id": "greenpt", @@ -626,7 +648,7 @@ "env": [ "HF_TOKEN" ], - "model_count": 69 + "model_count": 71 }, { "id": "hyper", @@ -637,7 +659,7 @@ "env": [ "HYPER_API_KEY" ], - "model_count": 26 + "model_count": 29 }, { "id": "iflowcn", @@ -728,6 +750,17 @@ ], "model_count": 17 }, + { + "id": "iteracompute", + "display_name": "IteraCompute", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.iteracompute.com/v1", + "doc": "https://iteracompute.com/docs.html", + "env": [ + "ITERACOMPUTE_API_KEY" + ], + "model_count": 1 + }, { "id": "jalapeno", "display_name": "Jalapeno Cloud", @@ -770,7 +803,7 @@ "env": [ "KILO_API_KEY" ], - "model_count": 365 + "model_count": 366 }, { "id": "kimi-for-coding", @@ -825,7 +858,7 @@ "env": [ "LLMGATEWAY_API_KEY" ], - "model_count": 187 + "model_count": 189 }, { "id": "llmgateway-providers", @@ -836,7 +869,18 @@ "env": [ "LLMGATEWAY_API_KEY" ], - "model_count": 377 + "model_count": 381 + }, + { + "id": "llmtech", + "display_name": "LLM Tech", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.llmtech.eu/v1", + "doc": "https://llmtech.eu/models/qwen3.8-27b", + "env": [ + "LLMTECH_API_KEY" + ], + "model_count": 1 }, { "id": "llmtr", @@ -1078,7 +1122,7 @@ "env": [ "NANO_GPT_API_KEY" ], - "model_count": 606 + "model_count": 612 }, { "id": "nearai", @@ -1114,6 +1158,17 @@ ], "model_count": 42 }, + { + "id": "neosmith", + "display_name": "NeoSmith", + "npm": "@ai-sdk/openai", + "api": "https://router.neosmith.ai/v1", + "doc": "https://neosmith.ai/docs", + "env": [ + "NEOSMITH_API_KEY" + ], + "model_count": 4 + }, { "id": "neuralwatt", "display_name": "Neuralwatt", @@ -1123,7 +1178,7 @@ "env": [ "NEURALWATT_API_KEY" ], - "model_count": 22 + "model_count": 25 }, { "id": "nova", @@ -1200,7 +1255,7 @@ "env": [ "OPENCODE_API_KEY" ], - "model_count": 29 + "model_count": 31 }, { "id": "opper", @@ -1235,6 +1290,17 @@ ], "model_count": 14 }, + { + "id": "pendra", + "display_name": "Pendra", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.pendra.ai/api/v1", + "doc": "https://pendra.ai/docs/integrations/opencode", + "env": [ + "PENDRA_API_KEY" + ], + "model_count": 6 + }, { "id": "perplexity-agent", "display_name": "Perplexity Agent", @@ -1333,7 +1399,7 @@ "env": [ "REQUESTY_API_KEY" ], - "model_count": 139 + "model_count": 140 }, { "id": "routing-run", @@ -1457,6 +1523,17 @@ ], "model_count": 8 }, + { + "id": "standardcompute", + "display_name": "Standard Compute", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.stdcmpt.com/v1", + "doc": "https://standardcompute.com/models", + "env": [ + "STANDARDCOMPUTE_API_KEY" + ], + "model_count": 1 + }, { "id": "stepfun", "display_name": "StepFun (China)", @@ -1675,7 +1752,18 @@ "env": [ "VIVGRID_API_KEY" ], - "model_count": 20 + "model_count": 21 + }, + { + "id": "volcengine", + "display_name": "Volcengine Ark", + "npm": "@ai-sdk/openai-compatible", + "api": "https://ark.cn-beijing.volces.com/api/v3", + "doc": "https://www.volcengine.com/docs/82379/1330310", + "env": [ + "ARK_API_KEY" + ], + "model_count": 15 }, { "id": "vultr", @@ -1708,7 +1796,7 @@ "env": [ "WANDB_API_KEY" ], - "model_count": 29 + "model_count": 26 }, { "id": "xiaomi", @@ -1774,7 +1862,7 @@ "env": [ "ZHIPU_API_KEY" ], - "model_count": 14 + "model_count": 16 }, { "id": "zai-coding-plan", @@ -1785,7 +1873,7 @@ "env": [ "ZHIPU_API_KEY" ], - "model_count": 5 + "model_count": 7 }, { "id": "zeldoc", @@ -1829,7 +1917,7 @@ "env": [ "ZHIPU_API_KEY" ], - "model_count": 13 + "model_count": 15 }, { "id": "zhipuai-coding-plan", @@ -1840,6 +1928,6 @@ "env": [ "ZHIPU_API_KEY" ], - "model_count": 8 + "model_count": 10 } ] \ No newline at end of file diff --git a/crates/goose-provider-types/src/canonical/name_builder.rs b/crates/goose-provider-types/src/canonical/name_builder.rs index 91381e420..69e19caeb 100644 --- a/crates/goose-provider-types/src/canonical/name_builder.rs +++ b/crates/goose-provider-types/src/canonical/name_builder.rs @@ -473,12 +473,12 @@ mod tests { // === DeepSeek === assert_eq!( - map_to_canonical_model("databricks", "databricks-deepseek-chat", r), - Some("deepseek/deepseek-chat".to_string()) + map_to_canonical_model("databricks", "databricks-deepseek-v4-flash", r), + Some("deepseek/deepseek-v4-flash".to_string()) ); assert_eq!( - map_to_canonical_model("databricks", "deepseek-reasoner", r), - Some("deepseek/deepseek-reasoner".to_string()) + map_to_canonical_model("databricks", "deepseek-v4-pro", r), + Some("deepseek/deepseek-v4-pro".to_string()) ); // === Grok (X.AI) === @@ -524,8 +524,8 @@ mod tests { Some("mistralai/codestral".to_string()) ); assert_eq!( - map_to_canonical_model("databricks", "deepseek-deepseek-chat", r), - Some("deepseek/deepseek-chat".to_string()) + map_to_canonical_model("databricks", "deepseek-deepseek-v4-flash", r), + Some("deepseek/deepseek-v4-flash".to_string()) ); assert_eq!( map_to_canonical_model("databricks", "x-ai-grok-4.3", r), diff --git a/crates/goose/src/providers/formats/bedrock.rs b/crates/goose/src/providers/formats/bedrock.rs index af8dda57d..1add61af8 100644 --- a/crates/goose/src/providers/formats/bedrock.rs +++ b/crates/goose/src/providers/formats/bedrock.rs @@ -1670,25 +1670,7 @@ mod tests { #[test] fn test_bedrock_inference_config_omits_temperature_for_unsupported_model() { - // The Anthropic canonical registry maps this id and reports whether a - // custom temperature may be sent; when it cannot, temperature is left - // unset so the server default is used. - let mut config = ModelConfig::new("us.anthropic.claude-sonnet-4-5-20250929-v1:0"); - config.temperature = Some(0.5); - - let supported = bedrock_model_supports_temperature(&config); - let inference_config = bedrock_inference_config(&config); - - if supported { - assert_eq!(inference_config.temperature(), Some(0.5)); - } else { - assert_eq!(inference_config.temperature(), None); - } - } - - #[test] - fn test_bedrock_inference_config_omits_temperature_for_bedrock_registry_unsupported_model() { - let mut config = ModelConfig::new("openai.gpt-5.4"); + let mut config = ModelConfig::new("global.anthropic.claude-sonnet-5"); config.temperature = Some(0.5); let inference_config = bedrock_inference_config(&config);