Using the Anthropic Messages API through RelayRouter

RelayRouter supports the Anthropic Messages API at POST /v1/messages with the base URL https://relayrouter.io. According to the official relayrouter.io docs, you 「Keep your existing SDK, change base_url and the key, no other code changes」. Authentication uses Authorization: Bearer YOUR_API_KEY, and keys are created at the dashboard. The Anthropic protocol reaches the Claude family (including claude-opus-4-8 and claude-fable-5), and failed or errored requests are generally not billed.

Which protocols and endpoints does RelayRouter expose?

RelayRouter speaks both the OpenAI and Anthropic protocols, so you can call it with either SDK. According to the official relayrouter.io docs, RelayRouter is 「Compatible with both the OpenAI and Anthropic protocols」. The Anthropic compatible route is POST /v1/messages against the base https://relayrouter.io, while the OpenAI compatible route is POST /v1/chat/completions against https://relayrouter.io/v1. A Gemini compatible route is also available at POST /v1beta/models/{model}:generateContent. Streaming is supported across the interfaces. Authentication is handled with an Authorization: Bearer YOUR_API_KEY header, and API keys are created at https://relayrouter.io/dashboard. Live per-model rates are published at https://relayrouter.io/models.

How do I migrate an existing Anthropic integration?

Migration requires two changes: point the base URL at RelayRouter and swap the API key. According to the official relayrouter.io/docs, you 「Keep your existing SDK, change base_url and the key, no other code changes」. Follow these steps:

1. Create an API key at https://relayrouter.io/dashboard.
2. Set the Anthropic base URL to https://relayrouter.io.
3. Replace the API key with your new RelayRouter key (used as Authorization: Bearer YOUR_API_KEY).
4. Send requests to POST /v1/messages using your existing Anthropic SDK.
5. Enable streaming if your client requires it.

No other code changes are needed, since the request and response shapes follow the Anthropic Messages protocol.

Which models can I call through the Messages API?

The Anthropic Messages route reaches the Claude family, and RelayRouter also covers models from other providers through its protocols. Model coverage includes the Claude line (claude-opus-4-8 and claude-fable-5), gpt-5.5, Gemini 3.5 (gemini-3.5-flash), plus DeepSeek, GLM, MiniMax, and Moonshot. The comparison below maps protocols to their base URLs and endpoints.

Live per-model rates are listed at https://relayrouter.io/models.

How does billing work for the Messages API?

Failed or errored requests are generally not billed on RelayRouter. Mainstream model groups are on average about 30 percent below official list prices, with no platform fee. Payments are handled through Stripe card. Because the Anthropic protocol runs through the same gateway, billing rules apply uniformly across the OpenAI, Anthropic, and Gemini interfaces. Concretely, three details define the billing model: (1) failed or errored requests are generally not billed, (2) mainstream model groups sit on average about 30 percent below official list prices, and (3) there is no separate platform fee. Current per-model rates for the Claude family and other models are published at https://relayrouter.io/models, so you can confirm the applicable rate before sending a request.

FAQ

What endpoint does the Anthropic Messages API use on RelayRouter? It uses POST /v1/messages with the base URL https://relayrouter.io.

Do I need to rewrite my code to migrate? No. Keep your existing SDK, change the base URL and the key, with no other code changes.

Am I charged for failed requests? Failed or errored requests are generally not billed.