Skip to main content
The AI Gateway exposes endpoints that are fully compatible with the OpenAI API, letting you use every model available in the AI Gateway without changing your application logic. Keep the existing OpenAI client, point it to the Orq.ai proxy baseURL, and continue as usual.
For the OpenAI API specification, see the API Reference
To move an existing application from the OpenAI SDK, the Anthropic SDK, OpenRouter, or LiteLLM, see Migrate to Orq.ai.
Drop-in Integration (No Code Changes)
  1. Keep your existing OpenAI SDK or HTTP integration.
  2. Set the base URL to https://my.orq.ai/v3/router
  3. Use the Orq.ai API Key in the Authorization header.
  4. Call the same endpoints and payloads already used with OpenAI.

​
Base URL

OpenAI-compatible endpoint:
All routes below are relative to this base URL and mirror OpenAI’s request/response formats.

​
Authentication

Authenticate with the Orq.ai API key via the Authorization: Bearer $ORQ_API_KEY header.
To learn more about Orq API Key, see API Key.
Minimum headers:
  • Authorization: Bearer $ORQ_API_KEY
  • Content-Type: application/json

​
Supported Endpoints

Schema, parameters, and response formats match the OpenAI API.
  • GET /models: List available models
  • GET /models/{model}: Get model details
  • POST /chat/completions: Chat completions (supports streaming, images, files, and tool calls)
  • POST /completions: Text completions
  • POST /embeddings: Vector embeddings (Embeddings)
  • POST /images/generations: Image generation
  • POST /images/edits: Image editing
  • POST /images/variations: Image variations
  • POST /moderations: Text moderation (Rerank and Moderations)
  • POST /rerank: Rerank results (Rerank and Moderations)
  • POST /audio/speech: Text-to-speech
  • POST /audio/transcriptions: Transcribe audio into the input language
  • POST /audio/translations: Translate audio into English
  • POST /responses: Create a model response with built-in tools (Responses API, Web Search)
  • GET /responses/{response_id}: Retrieve a stored response (Responses API)
  • POST /classify: Run typed classification questions against a classify model (Classify)
  • POST /ocr: Extract text and structure from a document or image (OCR)

​
Models

Use the model field exactly as you would with OpenAI, substituting the ID of any model available in the AI Gateway Models.

​
Error Handling & Compatibility Notes

  • HTTP status codes and error structures follow OpenAI’s conventions.
  • Streaming, function/tool calls, and multimodal inputs (images/files) are supported on /chat/completions.
  • The AI Gateway serves the current surface under /v3/router: target this path for new integrations. The earlier paths under /v2/router/ remain published for backward compatibility.