LLM configuration
Set LLM_MODEL in backend/.env:
| Provider | Value |
|---|---|
| Google Gemini (default) | gemini-3.8-flash |
| OpenAI via LiteLLM | litellm:openai/gpt-6.1-sol |
| Anthropic via LiteLLM | litellm:anthropic/claude-sonnet-5-5 |
| Amazon Bedrock via LiteLLM | litellm:bedrock/global.anthropic.claude-sonnet-5-5 |
Every other backend setting has its own page under Configuration reference.
Gemini (default)
LLM_MODEL=gemini-3.8-flash
GOOGLE_API_KEY=your_google_api_key_here
OpenAI (via LiteLLM)
LLM_MODEL=litellm:openai/gpt-6.1-sol
OPENAI_API_KEY=your_openai_api_key_here
Anthropic (via LiteLLM)
LLM_MODEL=litellm:anthropic/claude-sonnet-5-5
ANTHROPIC_API_KEY=your_anthropic_api_key_here
Amazon Bedrock (via LiteLLM)
The boto3 and botocore[crt] packages this route needs ship with the backend, so there is no extra install step.
LLM_MODEL=litellm:bedrock/global.anthropic.claude-sonnet-5-5
AWS_BEARER_TOKEN_BEDROCK=your_bedrock_bearer_token_here