> ## 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

> Access models and inference.

Access models and inference.

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

Configure domains, environment variables, and servers. Manage release asset manifests and inspect deployment records.

[Models](#models) · [Inference](#inference)

## Models

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

List provider-compatible inference models.

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/ai-gateway-models-project-inference-policy/opt-in-to-standard-tier-serving).

Read, record, or revoke the account standard-tier opt-in, which decides where account API keys that name no project are served. These endpoints require a signed-in account owner or admin.

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/models` | [GET](/docs/cloud/rest/api-reference/ai-gateway-models-model-discovery/list-models) | List models |
| `/catalog/models` | [GET](/docs/cloud/rest/api-reference/ai-gateway-models-model-discovery/list-public-model-catalog) | List public model catalog |
| `/ai/v1beta/models` | [GET](/docs/cloud/rest/api-reference/ai-gateway-models-inference-models/list-models-in-gemini-format) | List models in Gemini format |
| `/ai/v1/models` | [GET](/docs/cloud/rest/api-reference/ai-gateway-models-inference-models/list-models-in-openai-format) | List models in OpenAI format |
| `/projects/{project_reference}/inference-policy` | [GET](/docs/cloud/rest/api-reference/ai-gateway-models-project-inference-policy/get-inference-policy), [PUT](/docs/cloud/rest/api-reference/ai-gateway-models-project-inference-policy/replace-inference-policy), [DELETE](/docs/cloud/rest/api-reference/ai-gateway-models-project-inference-policy/clear-inference-policy) | Get inference policy; Replace inference policy; Clear inference policy |
| `/projects/{project_reference}/inference-policy/standard-tier-opt-in` | [POST](/docs/cloud/rest/api-reference/ai-gateway-models-project-inference-policy/opt-in-to-standard-tier-serving) | Opt in to standard tier serving |
| `/accounts/{account_id}/inference-policy` | [GET](/docs/cloud/rest/api-reference/ai-gateway-models-account-inference-policy/get-account-inference-policy) | Get account inference policy |
| `/accounts/{account_id}/inference-policy/standard-tier-opt-in` | [POST](/docs/cloud/rest/api-reference/ai-gateway-models-account-inference-policy/opt-account-in-to-standard-tier-serving), [DELETE](/docs/cloud/rest/api-reference/ai-gateway-models-account-inference-policy/revoke-account-standard-tier-opt-in) | Opt account in to standard tier serving; Revoke account standard tier opt-in |

## Inference

Create Anthropic-compatible messages or count message tokens.

Create OpenAI-compatible chat completions.

Create OpenAI-compatible responses.

Create embeddings.

Call Gemini-compatible generateContent methods.

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

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

Read routing or access metadata for proxy requests. These endpoints have separate freshness and authorization requirements.

| Endpoint | Methods | Description |
| - | - | - |
| `/ai/v1/chat/completions` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-openai-chat-completions/create-chat-completion) | Create chat completion |
| `/ai/v1/embeddings` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-embeddings/create-embeddings) | Create embeddings |
| `/ai/v1/responses` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-openai-responses/create-response) | Create response |
| `/projects/-/proxy-access/{lookup_key}` | [GET](/docs/cloud/rest/api-reference/ai-gateway-inference-proxy-metadata/get-proxy-access-metadata) | Get proxy access metadata |
| `/projects/-/proxy-routing/{lookup_key}` | [GET](/docs/cloud/rest/api-reference/ai-gateway-inference-proxy-metadata/get-proxy-routing-metadata) | Get proxy routing metadata |
| `/ai/v1/messages/count_tokens` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-anthropic-messages/reject-token-counting) | Reject token counting |
| `/ai/v1/messages` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-anthropic-messages/create-message) | Create message |
| `/ai/gateway/billing/finalize` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-provider-gateway/finalize-gateway-billing-group) | Finalize gateway billing group |
| `/ai/v1beta/models/{model_method}` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-gemini-inference/call-gemini-model-method) | Call Gemini model method |
| `/ai/v1beta/models/{vendor}/{model_method}` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-gemini-inference/call-prefixed-gemini-model-method) | Call prefixed Gemini model method |
| `/projects/{project_reference}/images/generate` | [POST](/docs/cloud/rest/api-reference/ai-gateway-inference-image-generation/generate-images) | Generate images |

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


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