AI Gateway API

Generate messages, responses, embeddings, and images. Use provider-compatible endpoints for inference. Configure project inference policies to control where and how requests are served. Model discovery · Anthropic Messages · OpenAI Chat Completions · OpenAI Responses · Embeddings · Inference Models · Gemini Models · Image generation · Provider gateway · Project inference policy

​

Model discovery

Find available models and inspect their metadata. Provider-compatible model lists are grouped with inference models.

​

Anthropic Messages

Create Anthropic-compatible messages or count message tokens.

​

OpenAI Chat Completions

Create OpenAI-compatible chat completions.

​

OpenAI Responses

Create OpenAI-compatible responses.

​

Embeddings

Create embeddings.

​

Inference Models

List provider-compatible inference models.

​

Gemini Models

Call Gemini-compatible generateContent methods.

​

Image generation

Generate images from a prompt. Manage generated images through project upload endpoints.

​

Provider gateway

Use billing finalization when your integration manages gateway billing groups. Inspect spending limits through budgets.

​

Project inference policy

Read, replace, or clear project inference constraints. These endpoints require a signed-in project administrator. Record standard-tier consent through the opt-in endpoint. Back to REST API reference