OpenAI-compatible

Point yottacode at any endpoint that speaks the OpenAI wire protocol. Use provider kind openai-compatible or pass the base URL directly.

Configure

In the TUI — add or switch providers without restarting:

/provider                        # open the picker → Add a profile: kind=openai-compatible, base URL, API key, model
/provider use openai-compatible  # switch to a saved profile
/model <model-id>                # switch model for this session

From the command line — set environment variables:

export YOTTACODE_PROVIDER=openai-compatible
export YOTTACODE_MODEL=llama-3.1-70b
export YOTTACODE_BASE_URL=https://example.com/v1
export YOTTACODE_API_KEY=...

…or pass flags at launch (they override the environment):

yottacode --provider openai-compatible \
  --model llama-3.1-70b \
  --base-url https://example.com/v1 \
  --api-key ...

This works with many gateways and self-hosted runtimes that expose /v1/chat/completions and /v1/models.

Tested examples include NVIDIA NIM, Groq, vLLM, and Llama Stack. Other gateways that speak the same wire protocol should work but are not formally validated.