Skip to main content
Download the OpenAPI 3.0 specification for the Requesty Inference API. Use it with your favorite API client, code generator, or testing tool.

Inference API Spec

OpenAPI spec for inference endpoints (chat, embeddings, images, audio, models).

​
What’s included

The Inference API spec covers all endpoints on router.requesty.ai:
EndpointMethodDescription
/v1/chat/completionsPOSTCreate chat completion
/v1/messagesPOSTCreate message (Anthropic format)
/v1/responsesPOSTCreate response (Responses API)
/v1/embeddingsPOSTCreate embedding
/v1/audio/speechPOSTCreate speech (TTS)
/v1/audio/transcriptionsPOSTCreate transcription (STT)
/v1/images/generationsPOSTCreate image
/v1/images/editsPOSTEdit image
/v1/modelsGETList models

​
Usage examples

Import the spec into popular tools:
  • Postman: Import > Link > paste the spec URL
  • Insomnia: Application > Import > From URL
  • OpenAPI Generator: openapi-generator-cli generate -i <spec-url> -g <language>
  • Swagger UI: Paste the spec URL into the explore bar
Last modified on May 26, 2026