Supported LLMs

Site admins can configure Cody via modelConfiguration on a Sourcegraph Enterprise instance. See Model Configuration for more details.

Chat and Prompts

Cody supports a variety of cutting-edge large language models for use in chat and prompts, allowing you to select the best model for your use case.

Provider	Model	Status	Vision Support
Anthropic	Claude Sonnet 4.5	✅	✅
Anthropic	Claude Sonnet 4.5 with Thinking	✅	✅
Anthropic	Claude Opus 4.5	✅	✅
Anthropic	Claude Opus 4.5 with Thinking	✅	✅
Anthropic	Claude Haiku 4.5	✅	✅
Anthropic	Claude Haiku 4.5 with Thinking	✅	✅
Google	Gemini 2.0 Flash	✅	✅
Google	Gemini 2.5 Flash	✅	✅
Google	Gemini 2.0 Flash-Lite	✅	✅
Google	Gemini 2.5 Pro	✅	✅
Google	Gemini 3 Pro	✅ (experimental)	❌
Google	Gemini 3 Flash	✅ (experimental)	❌
OpenAI	GPT-5.1	✅	✅
OpenAI	GPT-5	✅	✅
OpenAI	GPT-5 mini	✅	✅
OpenAI	GPT-5 nano	✅	✅
OpenAI	GPT-4o	✅	✅
OpenAI	GPT-4.1	✅	✅
OpenAI	GPT-4o-mini	✅	✅
OpenAI	GPT-4.1-mini	✅	✅
OpenAI	GPT-4.1-nano	✅	✅
OpenAI	o3	✅	❌
OpenAI	o4-mini	✅	❌

While Gemini models support vision capabilities, Cody clients do not currently support image uploads to Gemini models.

Cody uses a set of models for autocomplete which are suited for the low latency use case.

Provider	Model	Status
Anthropic	Claude Haiku 4.5	✅
Anthropic	Claude Haiku 4.5 with Thinking	✅
Fireworks.ai	StarCoder	✅
Fireworks.ai	DeepSeek V2 Lite Base	✅
Fireworks.ai	AutoEdits Fireworks Default	✅ (experimental)
Fireworks.ai	Autoedits DeepSeek Coder V2	✅ (beta)
Fireworks.ai	Autoedits Long Suggestion Default	✅ (beta)
Fireworks.ai	Autoedits DeepSeek Coder V2	✅ (beta)
Fireworks.ai	Autoedits DeepSeek Coder V2	✅ (beta)
Fireworks.ai	Autoedits Long Suggestion V4 Warm Start SFT	✅ (beta)
Mistral	AutoEdits Mixtral V2	✅ (experimental)
OpenAI	GPT-4.1-nano	✅

Provider	Model	Status
Fireworks.ai	Smart Apply Qwen Default	✅
Fireworks.ai	Smart Apply Qwen 32B V1	✅ (experimental)

The following models are used by default for each feature when no specific model is configured: