OpenAI

OpenAI integration via the /v1/chat/completions endpoint.

Configuration

1export OPENAI_API_KEY=sk-...

Supported Models

ModelInput (per 1M)Output (per 1M)
gpt-4o$2.50$10.00
gpt-4o-mini$0.15$0.60
gpt-4.1$2.00$8.00
gpt-4-turbo$10.00$30.00
gpt-3.5-turbo$0.50$1.50

Endpoint

Base URL: https://api.openai.com/v1

Requests to OpenAI use the native /v1/chat/completions format — no conversion needed. Authentication uses Authorization: Bearer header.

Model Detection

RelayPlane auto-detects OpenAI models by prefix. Any model starting with these prefixes routes to OpenAI:

  • gpt-*
  • o1-*, o3-*
  • chatgpt-*
  • text-*, dall-e*, whisper*, tts-*
When routing sends a request from the Anthropic format to OpenAI, RelayPlane automatically converts messages, tools, and tool_choice between formats.