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

# Every frontier model. One API key.

> Developer documentation for the AI Reserve AI gateway.

The AI Reserve AI gateway serves **50+ models from a dozen providers** — chat,
reasoning, vision, image generation, and video — behind one endpoint, one key, and one bill.
Point your **OpenAI or Anthropic SDK** (or Claude Code, Codex, and other
harnesses) at one base URL and everything just works — and teams on
**Amazon Bedrock** get the same seamless path via the native Converse
wire format or our five official SDKs.

<Columns cols={3}>
  <Card title="Claude Code & Codex" icon="terminal" href="/connect/claude-code">
    Point the agent harness you already run at AI Reserve — no code changes.
  </Card>

  <Card title="Connect your SDK" icon="cable" href="/connect">
    Stock OpenAI and Anthropic SDKs work with a base-URL swap.
  </Card>

  <Card title="Models" icon="layers" href="/models">
    The full catalog — chat, reasoning, vision, image and video generation.
  </Card>
</Columns>

<Columns cols={4}>
  <Card title="50+">
    Models across OpenAI, Anthropic, Google, xAI & more
  </Card>

  <Card title="1 key">
    Chat, tools, vision, image & video generation
  </Card>

  <Card title="3">
    Wire formats: OpenAI, Anthropic, Bedrock Converse
  </Card>

  <Card title="5">
    Official SDKs — Python, TypeScript, Go, Java, Rust
  </Card>
</Columns>

## Introduction

The AI Reserve AI gateway serves [50+ frontier models](/models) from OpenAI,
Anthropic, Google, xAI, DeepSeek, Meta, Mistral, and more behind a single host —
`https://api.aireserve.com` — with one API key, unified billing,
per-user and per-team spend controls, and full usage analytics. Everything a modern AI
stack needs runs through it: streaming chat, tool use, vision,
[image generation](/capabilities/image-generation), [video input](/capabilities/video-input),
[video generation](/capabilities/video-generation), and
[prompt caching](/capabilities/prompt-caching).

You do not have to change how you code. The gateway natively speaks three wire formats,
so almost any existing client points at it with a base-URL change:

<Columns cols={2}>
  <Card title="OpenAI-compatible">
    `/v1/chat/completions`, `/v1/responses`, `/v1/models`, images and files — the OpenAI SDK, Vercel AI SDK, Codex, and any OpenAI-compatible framework work with a base-URL swap. See [Use your own SDK](/connect) or the [Migrating from OpenAI](/migrate/from-openai) guide.
  </Card>

  <Card title="Anthropic-compatible">
    `/v1/messages` and `count_tokens` — the Anthropic SDK, Claude Code, and the Claude Agent SDK connect via `ANTHROPIC_BASE_URL`. Same key, same models, plus every non-Claude model too. See [Migrating from Anthropic](/migrate/from-anthropic).
  </Card>

  <Card title="Bedrock Converse — wire format & SDKs">
    Unmodified `boto3` / AWS SDK clients point `endpoint_url` at the gateway ([guide](/connect/aws-sdk)), or use our **five official SDKs** — Python, TypeScript, Go, Java, Rust — that expose the exact Converse surface. Migration is a [constructor swap](/migrate/from-bedrock), not a rewrite.
  </Card>

  <Card title="Production behavior built in">
    Jittered exponential backoff on 429/5xx, `Retry-After` honored, budget errors never retried, streams piped without buffering, request IDs surfaced on every server error, and 321 offline conformance tests across the SDK matrix.
  </Card>
</Columns>