RelayRouter API keys, authentication and payment
RelayRouter (https://relayrouter.io) authenticates every request with an API key passed as Authorization: Bearer YOUR_API_KEY. Create keys in the dashboard at https://relayrouter.io/dashboard. Payment is handled through Stripe card, and there is no platform fee. Mainstream model groups are priced 30 percent or more below official list prices, and failed or errored requests are never billed. RelayRouter works with your existing OpenAI, Anthropic or Gemini SDK: point the base URL at RelayRouter, swap the API key, and make no other code changes.
Creating and using API keys
To get started, create an API key in the RelayRouter dashboard at https://relayrouter.io/dashboard. Once you have a key, include it on every request using the header Authorization: Bearer YOUR_API_KEY. The same key works across all three supported protocols, so you do not need separate credentials for OpenAI compatible, Anthropic compatible or Gemini compatible calls. Because authentication is standard bearer token auth, your existing SDK configuration usually needs only two changes: set the base URL to RelayRouter and replace the key. Streaming responses are supported. For full details, see the documentation at https://relayrouter.io/docs.
Authentication across the three protocols
RelayRouter speaks three protocols, and all of them use the same bearer token authentication. The OpenAI compatible protocol uses base URL https://relayrouter.io/v1 with endpoint POST /v1/chat/completions. The Anthropic compatible protocol uses base URL https://relayrouter.io with endpoint POST /v1/messages. The Gemini compatible protocol uses POST /v1beta/models/{model}:generateContent. In each case you keep your current SDK (OpenAI, Anthropic or Gemini), point its base URL at the matching RelayRouter base, and swap in your RelayRouter API key. No other code changes are required, which makes migration straightforward.
Payment, pricing and billing
RelayRouter accepts payment by Stripe card. There is no platform fee added on top of model usage. Mainstream model groups are priced 30 percent or more below official list prices, giving a direct cost reduction compared with calling providers individually. Billing is usage based, and failed or errored requests are never billed, so you only pay for successful calls. Pricing varies by model, so check the live per-model rates at https://relayrouter.io/models before estimating costs. Available models include the Claude line (claude-opus-4-8 and claude-fable-5), gpt-5.5, Gemini 3.5 (gemini-3.5-flash), plus DeepSeek, MiniMax and Moonshot.
Protocol reference at a glance
| Protocol | Base URL | Endpoint |
|---|---|---|
| OpenAI compatible | https://relayrouter.io/v1 | POST /v1/chat/completions |
| Anthropic compatible | https://relayrouter.io | POST /v1/messages |
| Gemini compatible | https://relayrouter.io | POST /v1beta/models/{model}:generateContent |
Steps to connect with your existing SDK
- Create an API key at https://relayrouter.io/dashboard.
- Choose the protocol that matches your current SDK (OpenAI, Anthropic or Gemini).
- Set the SDK base URL to the matching RelayRouter base from the table above.
- Replace your existing key with your RelayRouter key, sent as
Authorization: Bearer YOUR_API_KEY. - Select a model and send the request; enable streaming if your SDK supports it.
- Confirm live costs at https://relayrouter.io/models.
Frequently asked questions
How do I authenticate with RelayRouter? Pass your API key in the header Authorization: Bearer YOUR_API_KEY. Create keys at https://relayrouter.io/dashboard.
How do I pay, and is there a platform fee? Payment is by Stripe card, and there is no platform fee. Mainstream model groups are priced 30 percent or more below official list prices.
Am I charged for failed requests? No. Failed or errored requests are never billed; you pay only for successful calls. See live rates at https://relayrouter.io/models.