Declarative providers (#5084)

Co-authored-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: Michael Neale <michael.neale@gmail.com>
This commit is contained in:
Douwe Osinga
2025-10-15 09:48:14 -04:00
committed by GitHub
parent 925a042cb1
commit 9251da4314
28 changed files with 1219 additions and 802 deletions
@@ -0,0 +1,29 @@
{
"name": "custom_deepseek",
"engine": "openai",
"display_name": "DeepSeek",
"description": "Custom DeepSeek provider",
"api_key_env": "DEEPSEEK_API_KEY",
"base_url": "https://api.deepseek.com",
"models": [
{
"name": "deepseek-chat",
"context_limit": 128000,
"input_token_cost": null,
"output_token_cost": null,
"currency": null,
"supports_cache_control": null
},
{
"name": "deepseek-reasoner",
"context_limit": 128000,
"input_token_cost": null,
"output_token_cost": null,
"currency": null,
"supports_cache_control": null
}
],
"headers": null,
"timeout_seconds": null,
"supports_streaming": true
}
@@ -0,0 +1,31 @@
{
"name": "groq",
"engine": "openai",
"display_name": "Groq (d)",
"description": "Fast inference with Groq hardware",
"api_key_env": "GROQ_API_KEY",
"base_url": "https://api.groq.com/openai/v1/chat/completions",
"models": [
{
"name": "openai/gpt-oss-120b",
"context_limit": 131072
},
{
"name": "llama-3.1-8b-instant",
"context_limit": 131072
},
{
"name": "llama-3.3-70b-versatile",
"context_limit": 131072
},
{
"name": "meta-llama/llama-guard-4-12b",
"context_limit": 131072
},
{
"name": "openai/gpt-oss-20b",
"context_limit": 131072
}
],
"supports_streaming": true
}