Supported LLMs

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.

Newer versions of Sourcegraph Enterprise, starting from v5.6, it will be even easier to add support for new models and providers, see Model Configuration for more information.

Provider	Model	Free	Pro	Enterprise
OpenAI	GPT-4 Turbo	-	✅	✅
OpenAI	GPT-4o	-	✅	✅
OpenAI	GPT-4o-mini	✅	✅	✅
OpenAI	o3-mini-medium (experimental)	✅	✅	✅
OpenAI	o3-mini-high (experimental)	-	-	✅
OpenAI	o3	-	✅	✅
OpenAI	o4-mini	✅	✅	✅
OpenAI	GPT-4.1	-	✅	✅
OpenAI	GPT-4.1-mini	✅	✅	✅
OpenAI	GPT-4.1-nano	✅	✅	✅
Anthropic	Claude 3.5 Haiku	✅	✅	✅
Anthropic	Claude 3.5 Sonnet	✅	✅	✅
Anthropic	Claude 3.7 Sonnet	-	✅	✅
Anthropic	Claude Sonnet 4	✅	✅	✅
Anthropic	Claude Sonnet 4 w/Thinking	-	✅	✅
Anthropic	Claude Opus 4	-	-	✅
Anthropic	Claude Opus 4 w/Thinking	-	-	✅
Google	Gemini 1.5 Pro	✅	✅	✅ (beta)
Google	Gemini 2.0 Flash	✅	✅	✅
Google	Gemini 2.0 Flash	✅	✅	✅
Google	Gemini 2.5 Pro Preview	-	✅	✅
Google	Gemini 2.5 Flash Preview (experimental)	✅	✅	✅

To use Claude 3 Sonnet models with Cody Enterprise, make sure you've upgraded your Sourcegraph instance to the latest version.

Claude 3.7 and 4 Sonnet have two variants; the base version, and the extended thinking version which supports deep reasoning and fast, responsive edit workflows. Cody enables using both, and lets the user select which to use in the model dropdown selector, so the user can choose whether to use extended thinkig depending on their work task.

Claude 4 models support is available with Sourcegraph versions v6.4+ and v6.3.4167. It also depends on the deployement type and whether it's thinking or not.

Claude 3.7 and 4 via Google Vertex, via AWS Bedrock

Starting in Sourcegraph v6.4+ and v6.3.416, Claude 3.7 Extended Thinking - as well as Claude 4 base and extended thinking variants - are available in Sourcegraph when using Claude through either Google Vertex or AWS Bedrock.

See Model Configuration: Reasoning models for more information.

Autocomplete

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

Provider	Model	Free	Pro	Enterprise
Fireworks.ai	DeepSeek-Coder-V2	✅	✅	✅
Anthropic	claude Instant	-	-	✅

The default autocomplete model for Cody Free, Pro and Enterprise users is DeepSeek-Coder-V2.

The DeepSeek model used by Sourcegraph is hosted by Fireworks.ai, and is hosted as a single-tenant service in a US-based data center. For more information see our Cody FAQ.

Smart Apply

Provider	Model	Free	Pro	Enterprise
Fireworks.ai	Qwen 2.5 Coder	✅	✅	✅

Fireworks.ai is the default model for cody-gateway, but if you wish to switch to Claude models, Site admins can do it following these steps-

Go to "Site admin"

Click on the "Feature flags"

Search for cody-smart-apply-instant-mode-enabled feature flag

Turn off/delete the "cody-smart-apply-instant-mode-enabled" feature flag