> ## Documentation Index
> Fetch the complete documentation index at: https://veryfront.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Gateway API

> Generate messages, responses, embeddings, and images.

Generate messages, responses, embeddings, and images.

Use provider-compatible endpoints for inference. Configure [project inference policies](/docs/cloud/rest/apis/ai-gateway-api#project-inference-policy) to control where and how requests are served.

[Model discovery](#model-discovery) · [Anthropic Messages](#anthropic-messages) · [OpenAI Chat Completions](#openai-chat-completions) · [OpenAI Responses](#openai-responses) · [Embeddings](#embeddings) · [Inference Models](#inference-models) · [Gemini Models](#gemini-models) · [Image generation](#image-generation) · [Provider gateway](#provider-gateway) · [Project inference policy](#project-inference-policy)

## Model discovery

Find available models and inspect their metadata. Provider-compatible model lists are grouped with [inference models](/docs/cloud/rest/apis/ai-gateway-api#inference-models).

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/models` | [GET](/docs/cloud/rest/api-reference/model-discovery/list-models) | List models |
| `/catalog/models` | [GET](/docs/cloud/rest/api-reference/model-discovery/list-public-model-catalog) | List public model catalog |

## Anthropic Messages

Create Anthropic-compatible messages or count message tokens.

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/v1/messages` | [POST](/docs/cloud/rest/api-reference/anthropic-messages/messages-vendor-neutral) | Messages (vendor-neutral) |
| `/ai/v1/messages/count_tokens` | [POST](/docs/cloud/rest/api-reference/anthropic-messages/count-message-tokens-vendor-neutral) | Count Message Tokens (vendor-neutral) |

## OpenAI Chat Completions

Create OpenAI-compatible chat completions.

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/v1/chat/completions` | [POST](/docs/cloud/rest/api-reference/openai-chat-completions/create-a-chat-completion) | Create a chat completion |

## OpenAI Responses

Create OpenAI-compatible responses.

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/v1/responses` | [POST](/docs/cloud/rest/api-reference/openai-responses/create-a-response) | Create a response |

## Embeddings

Create embeddings.

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/v1/embeddings` | [POST](/docs/cloud/rest/api-reference/embeddings/create-embeddings) | Create embeddings |

## Inference Models

List provider-compatible inference models.

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/v1/models` | [GET](/docs/cloud/rest/api-reference/inference-models/list-models-openai-or-anthropic-format) | List Models (OpenAI or Anthropic format) |
| `/ai/v1beta/models` | [GET](/docs/cloud/rest/api-reference/inference-models/list-models-gemini-format) | List Models (Gemini format) |

## Gemini Models

Call Gemini-compatible generateContent methods.

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/v1beta/models/{model_method}` | [POST](/docs/cloud/rest/api-reference/gemini-models/gemini-model-method-vendor-neutral) | Gemini model method (vendor-neutral) |
| `/ai/v1beta/models/{vendor}/{model_method}` | [POST](/docs/cloud/rest/api-reference/gemini-models/gemini-model-method-vendor-prefixed-model-id-vendor-neutral) | Gemini model method, vendor-prefixed model id (vendor-neutral) |

## Image generation

Generate images from a prompt. Manage generated images through [project upload endpoints](/docs/cloud/rest/apis/projects-api#project-uploads).

| Endpoint | Methods | Description |
| - | - | - |
| `/projects/{project_reference}/images/generate` | [POST](/docs/cloud/rest/api-reference/image-generation/generate-project-images) | Generate project images |

## Provider gateway

Use [billing finalization](/docs/cloud/rest/api-reference/provider-gateway/finalize-gateway-billing-group) when your integration manages gateway billing groups. Inspect spending limits through [budgets](/docs/cloud/rest/apis/billing-and-usage-api#budgets).

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/gateway/billing/finalize` | [POST](/docs/cloud/rest/api-reference/provider-gateway/finalize-gateway-billing-group) | Finalize gateway billing group |

## 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](/docs/cloud/rest/api-reference/project-inference-policy/opt-in-to-standard-tier-serving).

| Endpoint | Methods | Description |
| - | - | - |
| `/projects/{project_reference}/inference-policy` | [GET](/docs/cloud/rest/api-reference/project-inference-policy/get-project-inference-policy), [PUT](/docs/cloud/rest/api-reference/project-inference-policy/replace-project-inference-policy), [DELETE](/docs/cloud/rest/api-reference/project-inference-policy/clear-project-inference-policy) | Get project inference policy; Replace project inference policy; Clear project inference policy |
| `/projects/{project_reference}/inference-policy/standard-tier-opt-in` | [POST](/docs/cloud/rest/api-reference/project-inference-policy/opt-in-to-standard-tier-serving) | Opt in to standard tier serving |

[Back to REST API reference](/docs/cloud/rest)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.