Skip to main content
The AI Router supports multiple input and output modalities through a single OpenAI-compatible API. Use the same endpoint patterns, authentication, and features (fallbacks, caching, load balancing, retries) regardless of the modality.

Vision

Analyze images alongside text. Pass image URLs or base64-encoded files in chat/completions messages.

PDF Input

Send PDF documents for extraction and analysis. Supported natively by compatible models.

Image Generation

Generate, edit, and vary images using DALL-E 2, DALL-E 3, and GPT Image 1.

Audio

Convert text to speech, transcribe audio files, and translate audio to English.

​
Modality compatibility

ModalityEndpointModels
Vision (image input)POST /v2/router/chat/completionsGPT-4o, Claude 3.x/4.x, Gemini, and others
PDF inputPOST /v2/router/chat/completionsModels with native file support
Image generationPOST /v2/router/images/generationsopenai/dall-e-2, openai/dall-e-3, openai/gpt-image-1
Image editingPOST /v2/router/images/editsopenai/dall-e-2, openai/gpt-image-1
Image variationsPOST /v2/router/images/variationsopenai/dall-e-2
Text to speechPOST /v2/router/audio/speechOpenAI TTS, ElevenLabs
TranscriptionPOST /v2/router/audio/transcriptionsopenai/whisper-1 and others
TranslationPOST /v2/router/audio/translationsopenai/whisper-1 and others

​
Unified API base URL

All modality endpoints share the same base URL and authentication: 
BASE_URL=https://my.orq.ai/v2/router
Authorization: Bearer $ORQ_API_KEY

​
Supported model list

To see which models support a specific modality, filter the Supported Models page or use the Providers page in orq.ai.