OpenAI

Use OpenAI models with an API key.

Configure

In the TUI — add or switch providers without restarting:

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

From the command line — set environment variables:

export YOTTACODE_PROVIDER=openai
export YOTTACODE_MODEL=<your-model-id>
export YOTTACODE_BASE_URL=https://api.openai.com/v1
export YOTTACODE_API_KEY=sk-...

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

yottacode --provider openai \
  --model <your-model-id> \
  --base-url https://api.openai.com/v1 \
  --api-key sk-...

OpenAI reasoning models such as o1*, o3*, o4*, and gpt-5* are routed to the Responses API automatically when appropriate.

Hosted tools:

web_search is enabled by default
code_interpreter can be enabled with YOTTACODE_ENABLE_CODE_INTERPRETER=1

Disable default hosted web search:

export YOTTACODE_DISABLE_WEB_SEARCH=1

Anthropic ChatGPT OAuth