OpenAI

​

Supported Models

​

Setup

export OPENAI_API_KEY=sk-...

profclaw doctor --provider openai

​

Environment Variables

​

Configuration Example

OPENAI_API_KEY=sk-proj-...

providers:
  openai:
    api_key: "${OPENAI_API_KEY}"
    # Optional: override base URL for proxies
    # base_url: "https://your-proxy.example.com/v1"

# Any OpenAI-compatible API
OPENAI_API_KEY=your-key
OPENAI_BASE_URL=https://your-compatible-endpoint/v1

​

Model Aliases

​

Usage Examples

profclaw chat --model gpt "Summarize these release notes"
profclaw chat --model o3-mini "Solve this algorithm problem"
profclaw chat --model gpt-mini "Generate a commit message"

import { chat } from 'profclaw';

const response = await chat("Debug this TypeScript error", {
  model: "gpt",
  temperature: 0.2,
});

​

Notes

• OPENAI_BASE_URL can point to any OpenAI-compatible API (LiteLLM, LocalAI, etc.).
• GPT-4o is the default alias gpt - a good balance of capability and cost.
• o1/o3 models are reasoning models - use them for complex problem solving. They do not stream.

​

Related

• AI Providers Overview - Compare all 37 supported providers
• Anthropic - Claude models for best-in-class tool calling
• Azure OpenAI - OpenAI models via Azure with enterprise SLAs
• profclaw provider - Add and test providers from the CLI