Skip to content
Rapid Router

Rapid Router AI gatewayEvery AI model.
One API.

Rapid Router is an AI model gateway. Point the client you already use at it and reach every major model through one key and one balance. Priced in dollars, with an invoice on every top-up.

Get your API keyRead the docs
  • Works with the client library you already use
  • 624 live models, each priced per million tokens
  • Playground and usage logs on every account
624
Models callable right now
69
Model authors
USD
Top-ups in dollars, invoice included
    
Fee, charged once at top-up
QwenOpenAIGoogleMistralNovitaMetaDeepinfraNVIDIAAnthropicZ.aiBlack Forest LabsxAIBriaElevenlabsDeepseek AiDeepSeekMoonshotMicrosoftMinimaxSentence TransformersAllenaiSao10kQwenOpenAIGoogleMistralNovitaMetaDeepinfraNVIDIAAnthropicZ.aiBlack Forest LabsxAIBriaElevenlabsDeepseek AiDeepSeekMoonshotMicrosoftMinimaxSentence TransformersAllenaiSao10k

Built in, not bolted on

The work a gateway should do for you

Keys, balances, metering and spend tracking are the same problems for everyone. Solve them once, here, instead of in every service you own.

01

Switch models by changing one string

Move from Claude to GPT to Gemini without touching anything else. Same request shape, same response shape, same SDK you already use.

02

Priced in dollars, one invoice per top-up

Every model carries a per-million price in the catalog, and a dollar invoice follows every top-up. No local tax added, nothing hidden in the rate.

03

One balance behind every model

No separate account, card or quota per provider. Add credit once and spend it across the whole catalog.

04

See exactly where the money went

Every request is logged with its model, tokens and cost. Spend breaks down by key, and each key can carry its own monthly cap.

05

Rate limits you can plan against

Sixty requests a minute per key with the count in the response headers, and a ceiling on how many can be in flight at once.

06

Your key is a hash on our side

The secret is shown once at creation and never stored. Lose it and you replace it, which is the only safe way round.

Quickstart

Two lines, and
you are already done

Change the base URL and the model string. There is no new SDK to learn, nothing to rewrite, and no per-provider branching left in your code. The package your snippet imports is only an HTTP client, and every request comes here.

  1. 1
    Create an account
    Sign in with Google, GitHub or an email and password. Your account is ready immediately.
  2. 2
    Add credits
    Top up in dollars. One balance, valid against any model or provider.
  3. 3
    Ship it
    Issue a key, set a budget cap, start sending traffic.
curl https://rapidrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $RAPIDROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.7-flash",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Live now

Live on the gateway

A few of the models callable right now with your key.

Browse all models
openai/gpt-4o-miniServed by OpenAI$0.150 / $0.600Liveopenai/gpt-oss-120bServed by DeepInfra$0.037 / $0.170Liveopenai/gpt-6.1-solServed by OpenAI$2.00 / $10.00Liveopenai/gpt-5-miniServed by OpenAI$0.250 / $2.00Liveopenai/gpt-4.1-miniServed by OpenAI$0.400 / $1.60Liveopenai/gpt-5.6-lunaServed by OpenAI$0.200 / $1.20Live
Priced for everywhere else

Dollars in, provider list price out.

Credits are held in US dollars and every request is billed at the provider's own published price. Our      fee is charged once, when you top up, and that is the whole markup.

No local tax on the invoice

Your top-up is invoiced as an export of service: zero-rated, so no tax is added. What you see at checkout is what leaves your account.

One invoice, in dollars

Every top-up gets a numbered dollar invoice naming your company, downloadable from the dashboard the moment the payment settles.

Priced per model

API pricing, by model family

Every family below is live through one key. Each page lists the models with their price per million tokens, context window and what they support.

Claude API pricing
Every Anthropic model, priced
GPT API pricing
Every OpenAI model, priced
Gemini API pricing
Every Google model, priced
Llama API pricing
Every Meta model, priced
Mistral API pricing
Every Mistral model, priced
DeepSeek API pricing
Every DeepSeek model, priced
Qwen API pricing
Every Qwen model, priced
Grok API pricing
Every xAI model, priced

Plain answers

What is Rapid Router?

What is Rapid Router?
Rapid Router is an AI model gateway: one OpenAI-compatible API in front of 624 live models, Claude, GPT and Gemini among them. You hold one key and one balance, and switch models by changing one string.
Is this the Rapid Router coding game?
No. The Code for Life Rapid Router is a free coding game for schools by Ocado Technology. Rapid Router at rapidrouter.ai is an AI API gateway for developers. The two are unrelated.
How is Rapid Router different from OpenRouter?
Same idea, same request shape, so code written for OpenRouter works unchanged. The differences are image, video and speech models behind the same key, a batch API, a fee charged once at top-up, and support from people, not a form.
What does it cost?
Every model is billed at provider list price per million tokens, with a platform fee of      charged once when you buy credits. No seats, no subscription, no minimum.
Do I need to change my code?
No. Set the base URL to https://rapidrouter.ai/api/v1 and use your Rapid Router key in the OpenAI, Anthropic or any OpenAI-compatible SDK. Streaming, tools, images and audio work as before.
Is there a free tier?
Yes. Every account gets a daily allowance of free requests on eligible models before any top-up, and early-stage teams can apply to the startup program for starting credits.

Your first request is a minute away

Provider list price on every request, with a fee of      charged once when you buy credits. Top up in dollars, with an invoice on every top-up. No seats, no minimums.

Get your API key