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

# Introduction

> One API for Antara's models, compatible with the OpenAI and Anthropic SDKs, with policies, credits, and rate limits built in.

Antara serves its models (A1–A4) behind the APIs you already use:

| Endpoint | Compatible with |
| - | - |
| `POST /v1/chat/completions` | OpenAI Chat Completions |
| `POST /v1/responses` | OpenAI Responses (stateless) |
| `POST /v1/messages` | Anthropic Messages |
| `POST /v1/messages/count_tokens` | Anthropic token counting |

Point an OpenAI or Anthropic SDK at `https://api.antarah.dev` and change the model name. Everything else works as in those APIs: streaming, tool calling, structured output, images, and reasoning.

On top of that, Antara adds:

* **Policies.** Write a yes/no question ("Does this response reveal an API key?"). Antara checks requests or responses against it and records a decision, or blocks the request.
* **Credits.** Usage is billed in USD from a prepaid balance, with monthly spend limits per organization and project.
* **Rate limits** by tier, per key, project, and organization.

> [card] [Quickstart](https://docs.antarah.dev/quickstart.md)
>
> Make your first request in a few minutes.

> [card] [Use your SDK](https://docs.antarah.dev/sdks.md)
>
> Configure the OpenAI or Anthropic SDK.

> [card] [Policies](https://docs.antarah.dev/guides/policies.md)
>
> Check requests and responses against your rules.

> [card] [API reference](https://docs.antarah.dev/api-reference/introduction.md)
>
> Every endpoint, field, and error.


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