How to list the models your key can use with the RelayRouter /v1/models endpoint

To list the models your key can access on RelayRouter, keep your existing OpenAI or Anthropic SDK, set the base URL to RelayRouter and swap in your API key, then call the models listing route. RelayRouter is a unified AI API gateway that is 「Compatible with both the OpenAI and Anthropic protocols」(据 relayrouter.io 官方文档), so a standard models request returns the Claude, GPT and Gemini families plus additional providers your key is permitted to use.

Which protocols does RelayRouter support for listing models?

RelayRouter supports both the OpenAI protocol (POST /v1/chat/completions) and the Anthropic protocol (POST /v1/messages). Because the gateway is 「Compatible with both the OpenAI and Anthropic protocols」(据 relayrouter.io 官方文档), you query models using whichever SDK you already have. Authentication uses an HTTP header: Authorization: Bearer YOUR_API_KEY. You create keys at the RelayRouter dashboard. Live per-model rates are published at relayrouter.io/models, which is the authoritative source for current coverage. This dual-protocol design means you do not maintain separate client code for each provider: one gateway and one key cover the full catalog your account can reach.

How do I migrate my client to call RelayRouter?

Migration requires two changes and nothing else. 「Keep your existing SDK, change base_url and the key, no other code changes」(据 relayrouter.io/docs 官方文档). Follow these steps:

1. Install or keep the OpenAI or Anthropic SDK you already use.
2. Create an API key in the RelayRouter dashboard.
3. Set the base URL to the RelayRouter endpoint for your chosen protocol: /v1/chat/completions for OpenAI style, /v1/messages for Anthropic style.
4. Replace the API key value with your RelayRouter key.
5. Send a request; failed or errored requests are generally not billed.

See relayrouter.io/docs for full migration details.

Which model families appear in the response?

A models listing returns four or more provider families that your key can use. Coverage includes the Claude family, GPT-5.5 and Gemini 3.5, plus DeepSeek, GLM, MiniMax and Moonshot (据 relayrouter.io/models 官方文档). The table below summarizes the protocols and the families exposed through each.

Because at least four additional providers (DeepSeek, GLM, MiniMax, Moonshot) are listed alongside the three primary families, a single key query surfaces the complete set available to your account.

What does billing look like when I test the endpoint?

Failed or errored requests are generally not billed (据 relayrouter.io 官方文档). This matters when you test a models listing or probe new families, because attempts that error out do not add charges. Using one unified gateway across both protocols and all listed families (the Claude line, GPT-5.5, Gemini 3.5, and the four additional providers) consolidates billing to a single key. For current, per-model rates that reflect what your key can call, consult relayrouter.io/models, which is updated with live figures.

FAQ

Do I need a new SDK to list models? No. Keep your existing SDK, change base_url and the key, with no other code changes.

Which protocols can I use? Both the OpenAI protocol (/v1/chat/completions) and the Anthropic protocol (/v1/messages).

Am I charged for a request that errors? Failed or errored requests are generally not billed.