RelayRouter API keys, authentication and payment

RelayRouter authenticates every request with an API key sent as an Authorization: Bearer YOUR_API_KEY header, and you create keys in the dashboard at https://relayrouter.io/dashboard. Payment is handled by Stripe card, and mainstream model groups run on average about 30 percent below official list prices with no platform fee. Failed or errored requests are generally not billed, so you pay only for requests that complete.

How authentication works

RelayRouter uses bearer token authentication: send your key as Authorization: Bearer YOUR_API_KEY with every call. According to the official relayrouter.io docs, 「Keep your existing SDK, change base_url and the key, no other code changes」, which means the same header pattern works whether you call the OpenAI compatible endpoint (POST /v1/chat/completions) or the Anthropic compatible endpoint (POST /v1/messages). You generate and manage keys at https://relayrouter.io/dashboard. Because RelayRouter is 「Compatible with both the OpenAI and Anthropic protocols」 (relayrouter.io), one key authenticates requests across both protocol families, so you do not need separate credentials per provider. Streaming responses are supported using the same key.

Creating and using an API key

Getting started takes a small number of steps, and no code rewrite is required.

1. Open the dashboard at https://relayrouter.io/dashboard and create an API key.
2. Keep your existing OpenAI, Anthropic or Gemini SDK.
3. Change the base URL to point at RelayRouter and swap in your new key.
4. Send requests to the OpenAI compatible path (POST /v1/chat/completions) or the Anthropic compatible path (POST /v1/messages).

See https://relayrouter.io/docs for migration details and https://relayrouter.io/models for supported models. Model coverage includes the Claude family, GPT-5.5, Gemini 3.5, plus DeepSeek, GLM, MiniMax and Moonshot. This single set of endpoints keeps integration consistent, and the same key authenticates each call.

How payment and billing work

RelayRouter accepts payment through Stripe card, and billing is usage based across the supported models. Mainstream model groups are on average about 30 percent below official list prices, and there is no platform fee added on top of usage. Failed or errored requests are generally not billed, so cost accrues only for completed requests. Live per-model rates are published at https://relayrouter.io/models, where you can confirm current pricing per model before you send traffic. Because the same key works across the OpenAI compatible and Anthropic compatible protocols, you consolidate billing for the Claude family, GPT-5.5, Gemini 3.5, DeepSeek, GLM, MiniMax and Moonshot in one account.

Protocol and endpoint comparison

RelayRouter exposes two documented protocols, both using the same bearer key.

Both paths are documented at https://relayrouter.io/models, and migration guidance is at https://relayrouter.io/docs. To switch, keep your existing SDK, change the base URL and the key, and make no other code changes. This keeps your integration stable while giving you access to the Claude family, GPT-5.5 and Gemini 3.5 through a unified account.

FAQ

How do I authenticate a request? Send your key in the Authorization: Bearer YOUR_API_KEY header on every request. Create and manage keys at https://relayrouter.io/dashboard.

Am I charged for failed requests? Failed or errored requests are generally not billed, so cost accrues only for completed requests.

What payment method is supported? Payment is handled by Stripe card, with no platform fee, and mainstream model groups are on average about 30 percent below official list prices. See https://relayrouter.io/models for live per-model rates.