# Rapid Router

> Rapid Router (rapidrouter.ai) is an AI model gateway: one OpenAI-compatible API in front of Claude, GPT, Gemini and 550+ other models. Pay as you go in dollars, or in rupees with UPI and a GST invoice in India. Built and run from Indore, India. Not related to the Code for Life coding game of the same name.

Base URL: https://rapidrouter.ai/api/v1 (drop-in for the OpenAI SDK; set the base URL and use a Rapid Router key).
Pricing: provider list price per million tokens, plus a flat platform fee charged once when buying credits. Pay as you go, no subscription. Free daily allowance on eligible models.
Support: support@rapidrouter.ai

## Docs: Quickstart

- [Quickstart](https://rapidrouter.ai/docs): Your first request in two minutes: create a key, set the base URL, and call any model with curl, Python or Node.
- [Authentication](https://rapidrouter.ai/docs/auth): Bearer API keys, per-key budget caps, and why a lost key is replaced rather than recovered.
- [Frameworks and SDKs](https://rapidrouter.ai/docs/integrations): The OpenAI SDKs, LangChain, the Vercel AI SDK and any tool with a custom base URL work after two changes.
- [MCP server](https://rapidrouter.ai/docs/mcp): Search the catalog and call any model from Claude Desktop, Claude Code, Cursor and other MCP clients.

## Docs: Guides

- [Guides](https://rapidrouter.ai/docs/guides): Task-by-task guides: streaming, tools, structured output, media, batches, routing, budgets, errors and limits.
- [Streaming](https://rapidrouter.ai/docs/streaming): Server-sent events in the standard chunk shape, ending with a usage chunk that carries the billed cost.
- [Tool calling](https://rapidrouter.ai/docs/tools): Let a model call your functions using the OpenAI tools shape, translated for Anthropic models.
- [Structured output](https://rapidrouter.ai/docs/structured-output): JSON mode and JSON schema through response_format, emulated on Anthropic models.
- [Response healing](https://rapidrouter.ai/docs/healing): Repair almost-JSON answers (fences, trailing commas, truncation) without a second model call.
- [Reasoning models](https://rapidrouter.ai/docs/reasoning): How thinking tokens are billed and reported, and the max_tokens setting that leaves no room to answer.
- [PDF, audio and video input](https://rapidrouter.ai/docs/multimodal): Attach PDFs, audio and video to chat messages; the same request body works on every model.
- [Web search](https://rapidrouter.ai/docs/websearch): Ground any model in live web results with the web plugin or the :online suffix, with citations.
- [Images, speech and video](https://rapidrouter.ai/docs/media): Generate and edit images, text to speech, transcription, translation and video, billed per unit.
- [Voice pipeline](https://rapidrouter.ai/docs/voice): Audio in, spoken answer out: transcription, a chat model and speech in one call.
- [Batch API](https://rapidrouter.ai/docs/batch): Queue up to 500 chat completions in one call; they run within 24 hours and results are kept 30 days.
- [Failover and routing](https://rapidrouter.ai/docs/routing): How a failing provider falls over to the next route, and the provider object that steers the choice.
- [Auto router](https://rapidrouter.ai/docs/auto-router): rapidrouter/auto picks the model per prompt: light, code, Indic or heavy.
- [Presets](https://rapidrouter.ai/docs/presets): Named, versioned request templates you change in the dashboard without a deploy.
- [Message transforms](https://rapidrouter.ai/docs/transforms): middle-out compression for conversations longer than the model can take.
- [Latency and performance](https://rapidrouter.ai/docs/performance): The four things that actually move response time, roughly in order of size.
- [Budgets](https://rapidrouter.ai/docs/budgets): Cap spend per key, per account and per workspace, and the error a request gets once a cap is hit.
- [Spend alerts](https://rapidrouter.ai/docs/alerts): Email, WhatsApp or webhook alerts on daily and monthly thresholds, plus automatic anomaly alerts.
- [Bring your own keys](https://rapidrouter.ai/docs/byok): Route requests on your own provider keys and pay only the platform fee.
- [Prompt caching](https://rapidrouter.ai/docs/caching): Cached input billed at the provider cache rate, reported on every response.
- [Response caching](https://rapidrouter.ai/docs/response-cache): Opt-in replay of an identical request, billed at zero.
- [Free tier](https://rapidrouter.ai/docs/free-tier): Which models are free, the daily limits per account, and the 429 when they run out.
- [Errors](https://rapidrouter.ai/docs/errors): Status codes, the one error envelope, and the health endpoint worth monitoring.
- [Rate limits](https://rapidrouter.ai/docs/limits): Requests per minute per key and requests in flight per account, both growing with your balance.
- [Idempotency](https://rapidrouter.ai/docs/idempotency): Retry a request whose response was lost without paying twice, with the Idempotency-Key header.
- [Tracing](https://rapidrouter.ai/docs/tracing): x-request-id and W3C traceparent on every response, and OTLP export for self-hosted gateways.
- [Sign in with Rapid Router](https://rapidrouter.ai/docs/oauth): An OAuth PKCE flow so your users pay for your app with their own credits.
- [App attribution](https://rapidrouter.ai/docs/attribution): The HTTP-Referer and X-Title headers, and the public Apps ranking they feed.
- [Teams](https://rapidrouter.ai/docs/orgs): Organisations, roles, invite links, per-member or shared balances, and per-member spend.
- [Data collection](https://rapidrouter.ai/docs/data): What is recorded per request, and why prompts and responses are not stored unless you turn on capture.
- [Provider logging](https://rapidrouter.ai/docs/provider-data): Where a prompt goes after the gateway: links to each provider's own policy.
- [Request capture](https://rapidrouter.ai/docs/capture): Opt-in, per-key storage of request and response bodies for debugging, deleted on a schedule.

## Docs: API reference

- [API reference](https://rapidrouter.ai/docs/reference): Base URL, authentication, the error envelope, and every endpoint in one table.
- [Chat completions](https://rapidrouter.ai/docs/chat): POST /chat/completions: the standard request and response, plus provider and usage.cost.
- [Responses API](https://rapidrouter.ai/docs/responses): POST /responses in the OpenAI Responses shape: stateless, on every model, streaming included.
- [Anthropic Messages](https://rapidrouter.ai/docs/messages): POST /messages in the native Anthropic format, so Anthropic SDKs work with a base URL change.
- [Embeddings and rerank](https://rapidrouter.ai/docs/embeddings): POST /embeddings and POST /rerank, billed on input tokens.
- [Fanout](https://rapidrouter.ai/docs/fanout): One prompt to up to 4 models in parallel, each result billed on its own.
- [Token counting](https://rapidrouter.ai/docs/tokenize): POST /tokenize counts tokens without calling a model; exact for OpenAI models, estimated for the rest.
- [Models](https://rapidrouter.ai/docs/models): GET /models: ids, prices, context length, modalities and capabilities, live.
- [Endpoints and uptime](https://rapidrouter.ai/docs/uptime): Per-provider price, latency, throughput and 72 hours of availability for one model.
- [Provisioning API](https://rapidrouter.ai/docs/provisioning): Create, limit, rotate and disable runtime keys with a management key.
- [Usage export](https://rapidrouter.ai/docs/usage-export): Your usage as CSV, one row per day, key, model, provider and status.
- [Release radar](https://rapidrouter.ai/docs/radar): Get told by email, WhatsApp or webhook when a new model becomes callable.
- [Audit log](https://rapidrouter.ai/docs/audit): Who created, changed or removed which key, budget or team member, and when.

## Pages

- [Model catalogue](https://rapidrouter.ai/models): every live model with price, context window and capabilities
- [Model rankings](https://rapidrouter.ai/models/rankings): LMArena and Epoch AI scores next to price
- [Compare models](https://rapidrouter.ai/models/compare)
- [Pricing](https://rapidrouter.ai/pricing)
- [Docs](https://rapidrouter.ai/docs): quickstart, guides and API reference; every docs page is listed above
- [Rapid Router vs OpenRouter](https://rapidrouter.ai/vs/openrouter)
- [Providers](https://rapidrouter.ai/providers)
- [Indic and Indian-language models](https://rapidrouter.ai/collections/indic)
- [GST on AI credits](https://rapidrouter.ai/learn/gst)
- [Startup program](https://rapidrouter.ai/startups)
- [Enterprise](https://rapidrouter.ai/enterprise)
- [Security](https://rapidrouter.ai/security)
- [Status](https://rapidrouter.ai/status)
- [About](https://rapidrouter.ai/about)
- [Contact](https://rapidrouter.ai/legal/contact)

## Machine-readable

- [Full docs as one Markdown file](https://rapidrouter.ai/llms-full.txt)
- [OpenAPI spec](https://rapidrouter.ai/api/openapi.json)
- [Catalog snapshot](https://rapidrouter.ai/catalog-snapshot.json)
- [Sitemap](https://rapidrouter.ai/sitemap.xml)
- [MCP server](https://rapidrouter.ai/docs/mcp)