OpenAI

Use GPT-4o, GPT-5, GPT-5-mini, and other OpenAI models with docker-agent.

Setup

# Set your API key
export OPENAI_API_KEY="sk-..."

agents:
  root:
    model: openai/gpt-4o

models:
  gpt:
    provider: openai
    model: gpt-4o
    temperature: 0.7
    max_tokens: 4000

Model	Best For
`gpt-5`	Most capable, complex reasoning
`gpt-5-mini`	Fast, cost-effective, good reasoning
`gpt-4o`	Multimodal, balanced performance
`gpt-4o-mini`	Cheapest, fast for simple tasks

Find more model names at modelname.ai.

OpenAI uses effort level strings:

models:
  gpt-thinking:
    provider: openai
    model: gpt-5-mini
    thinking_budget: low # minimal | low | medium (default) | high

💡 Custom endpoints

Use base_url for proxies and OpenAI-compatible services. See Custom Providers for full setup.

Use base_url to connect to OpenAI-compatible APIs:

models:
  custom:
    provider: openai
    model: gpt-4o
    base_url: https://your-proxy.example.com/v1

For OpenAI Responses API models (gpt-4.1+, o-series, gpt-5), you can use WebSocket streaming instead of the default SSE (Server-Sent Events):

models:
  fast-gpt:
    provider: openai
    model: gpt-4.1
    provider_opts:
      transport: websocket  # Use WebSocket instead of SSE