Skip to content

Endpoints at a glance

Before you point a tool at the gateway, check that the calls it makes are ones the gateway carries. Chat reaches every provider; everything else reaches a provider of the same format; a few APIs aren't carried at all. The gateway never quietly sends a call somewhere it can't be served: it answers with a clear error instead.

Translated across providers

Path Format Reaches
POST /v1/chat/completions OpenAI OpenAI, Azure OpenAI, Anthropic, Gemini, Vertex AI, Amazon Bedrock
POST /v1/messages Anthropic the same
POST /v1beta/models/{model}:generateContent, :streamGenerateContent Gemini the same
Vertex AI's own …/publishers/{google\|anthropic}/models/{model}:generateContent Gemini (Vertex) the same

Same format only

A model of another kind of provider gets a 400 (bad_request) that names the problem.

Paths Format Page
/v1/responses OpenAI Responses API
/v1/completions OpenAI Legacy completions
/v1/embeddings OpenAI Embeddings
/v1/moderations OpenAI Moderations
/v1/images/* OpenAI Images
/v1/audio/* OpenAI Audio
/v1/video/generations, /v1/videos OpenAI Video
/v1/ocr, /v1/rerank, /v1/predictions OpenAI OCR, rerank and predictions
/v1/files, /v1/uploads OpenAI Files and uploads
/v1/batches OpenAI Batches
/v1/fine_tuning/* OpenAI Fine-tuning
/v1/messages/count_tokens Anthropic Token counting (another provider's model: counted by the gateway)
/v1/files with Anthropic headers Anthropic Files
:countTokens, :embedContent Gemini countTokens, embedContent
/v1beta/files, /upload/v1beta/files Gemini Files and uploads

Answered by the gateway itself

Path What you get
GET /v1/models, GET /v1beta/models The models your key may call
GET /health {"status":"ok"}, no key needed

Not carried

API Page
OpenAI Assistants (/v1/assistants, /v1/threads, /v1/vector_stores) Assistants API
OpenAI Realtime (/v1/realtime, WebSocket) Realtime API
Anthropic message batches (/v1/messages/batches) Message batches

Any other path gets a 404 with x-vidai-error-code: endpoint_not_found; a path the gateway carries, with a model it doesn't know, gets 404 model_not_found.

Good to know

  • Files, batches and uploads name no model, so the gateway sends them to the one provider that serves files, or the one you name with the x-provider header.
  • The full reference, with methods and every detail: Endpoints.