# AI Reserve Developer Documentation

## Docs

- [Transcribe audio](https://docs.aireserve.com/api-reference/audio/transcribe-audio.md): Transcribe audio using OpenAI (gpt-4o-mini-transcribe)
- [Converse (Bedrock wire format)](https://docs.aireserve.com/api-reference/bedrock/converse-bedrock-wire-format.md): Bedrock Converse wire format for unmodified boto3 / AWS SDK clients. Accepts AI Reserve model IDs and supported AWS model ids / inference-profile ARNs.
- [Converse stream (Bedrock wire format)](https://docs.aireserve.com/api-reference/bedrock/converse-stream-bedrock-wire-format.md): Bedrock ConverseStream wire format — responses are real AWS binary event streams (application/vnd.amazon.eventstream) with per-frame CRC32 checksums.
- [Create chat completion](https://docs.aireserve.com/api-reference/chat/create-chat-completion.md): OpenAI-compatible chat completions. Every gateway model — GPT, Claude, Gemini, Grok, and more — answers the same call; streaming responses are server-sent events terminated by `data: [DONE]`.
- [Configuration](https://docs.aireserve.com/api-reference/configuration.md): SDK configuration options — API key, base URL, timeouts, and retries — with consistent semantics everywhere.
- [Create embeddings](https://docs.aireserve.com/api-reference/embeddings/create-embeddings.md): OpenAI-compatible embeddings.
- [Errors & retries](https://docs.aireserve.com/api-reference/errors.md): Every SDK raises the same Bedrock-named exceptions, with the same retryability semantics you already handle.
- [Create file upload slot](https://docs.aireserve.com/api-reference/files/create-file-upload-slot.md): Create a presigned upload slot for a video file
- [Get file upload status](https://docs.aireserve.com/api-reference/files/get-file-upload-status.md): Check upload status of a file
- [Generate images](https://docs.aireserve.com/api-reference/images/generate-images.md): Generate images. Synchronous — multi-image or high-quality generations can take tens of seconds, so set client timeouts accordingly.
- [Wire protocol](https://docs.aireserve.com/api-reference/index.md): Under every SDK sits one HTTP endpoint — the entire surface, and how the SDKs map Bedrock shapes onto it.
- [Count tokens](https://docs.aireserve.com/api-reference/messages/count-tokens.md): Anthropic-shape token counting. Free — no inference is performed.
- [Create message](https://docs.aireserve.com/api-reference/messages/create-message.md): Anthropic-compatible Messages endpoint. Claude Code, the Claude Agent SDK, and the Anthropic SDK connect here — and every gateway model answers, not just Claude.
- [List models](https://docs.aireserve.com/api-reference/models/list-models.md): Returns the OpenAI-shaped model list. Treat it as the source of truth for available model IDs.
- [Create response (Responses API)](https://docs.aireserve.com/api-reference/responses/create-response-responses-api.md): OpenAI Responses API — the wire format the Codex SDK and Codex CLI speak.
- [OpenAI & Anthropic formats — native in the AI Reserve SDKs](https://docs.aireserve.com/api-reference/sdk-wire-formats.md): All five AI Reserve SDKs speak all three gateway wire formats from one client — verbatim pass-throughs, no shape translation.
- [Versioning & support](https://docs.aireserve.com/api-reference/versioning-and-support.md): Semantic versioning, cross-language conformance, request IDs, and licensing for the AI Reserve SDKs.
- [Get video generation job](https://docs.aireserve.com/api-reference/videos/get-video-generation-job.md): Read the status/result of a video-generation job
- [Submit video generation job](https://docs.aireserve.com/api-reference/videos/submit-video-generation-job.md): Create an async video-generation job
- [Image generation](https://docs.aireserve.com/capabilities/image-generation.md): Generate images through an OpenAI-compatible endpoint with the same key, rate limits, and spend caps as chat.
- [Prompt caching](https://docs.aireserve.com/capabilities/prompt-caching.md): Cache long, stable prompt prefixes server-side — ~90% off cache reads on Anthropic models, automatic on OpenAI and Gemini.
- [Streaming](https://docs.aireserve.com/capabilities/streaming.md): ConverseStream returns the same Bedrock event union you already handle, in all five SDKs.
- [Tool use](https://docs.aireserve.com/capabilities/tool-use.md): Function calling with Bedrock's exact toolConfig / toolUse / toolResult shapes, in all five SDKs.
- [Video generation](https://docs.aireserve.com/capabilities/video-generation.md): Create video from a text prompt with an asynchronous job API — submit, poll, download.
- [Video input (understanding)](https://docs.aireserve.com/capabilities/video-input.md): Send a video to a model and ask questions about it — inline bytes up to 20 MB, or upload once and reference by URI up to 1 GB.
- [Images (vision)](https://docs.aireserve.com/capabilities/vision.md): Send images to vision-capable models — raw bytes or a hosted URL — with Bedrock-style image content blocks.
- [Anthropic SDK](https://docs.aireserve.com/connect/anthropic-sdk.md): Point the official anthropic package at the gateway — host root, no /v1 — and reach every gateway model.
- [AWS SDK (boto3) / Bedrock migration](https://docs.aireserve.com/connect/aws-sdk.md): Keep your unmodified boto3 / AWS SDK Bedrock code — override the endpoint and credentials, and every call site stays byte-identical.
- [Claude Code](https://docs.aireserve.com/connect/claude-code.md): Point Claude Code at the AI Reserve gateway with three environment variables — no code change, no plugin — including the full 1M-token context.
- [AI Reserve Code CLI](https://docs.aireserve.com/connect/code-cli.md): A local, Claude-Code-style coding agent for your terminal whose brain is your AI Reserve API key.
- [Codex](https://docs.aireserve.com/connect/codex.md): Connect the Codex SDK or Codex CLI to the AI Reserve gateway over the OpenAI Responses format.
- [Cursor](https://docs.aireserve.com/connect/cursor.md): Run the entire Cursor IDE — chat, agent mode, inline edits — through the AI Reserve gateway on your key.
- [Connect your tool](https://docs.aireserve.com/connect/index.md): Point the tool you already use — Claude Code, Codex, Cursor, or any OpenAI/Anthropic SDK — at the AI Reserve gateway.
- [MCP server](https://docs.aireserve.com/connect/mcp.md): Give your agents account operations — live catalog, analytics, key and team management, one-shot inference — over one hosted MCP endpoint.
- [OpenAI SDK](https://docs.aireserve.com/connect/openai-sdk.md): Point the official openai package — or any OpenAI-compatible framework — at the gateway with a base-URL swap.
- [Get an API key](https://docs.aireserve.com/getting-started/get-an-api-key.md): Every request authenticates with a single bearer key issued from your AI Reserve workspace — no region, no credential chain, no IAM role, and no signing.
- [SDK quickstart](https://docs.aireserve.com/getting-started/quickstart.md): Install an official AI Reserve SDK and make your first request — a complete round trip in five languages.
- [Every frontier model. One API key.](https://docs.aireserve.com/index.md): Developer documentation for the AI Reserve AI gateway.
- [Migrating from Anthropic](https://docs.aireserve.com/migrate/from-anthropic.md): Keep the official anthropic package and change two lines — the base URL (host root, no /v1) and the API key.
- [Migrating from Bedrock](https://docs.aireserve.com/migrate/from-bedrock.md): Imports and client construction change; message shapes, tool configs, streaming loops, and error handling carry over verbatim.
- [Migrating from OpenAI](https://docs.aireserve.com/migrate/from-openai.md): Two lines in client construction — the base URL and the API key. Everything else passes through verbatim.
- [Models](https://docs.aireserve.com/models/index.md): One API key unlocks every model in the catalog — chat, reasoning, vision, image generation, and video — through a single, flat ID namespace.
- [Data & privacy](https://docs.aireserve.com/trust/data-privacy.md): Where your prompts go, which subprocessors we use, and how each provider handles data — the authoritative disclosures.

## OpenAPI Specs

- [openapi](https://docs.aireserve.com/api-reference/openapi.json)