Model not found error on RelayRouter: checking your key's model group

A "model not found" error on RelayRouter usually means the model ID you requested is not in your API key's model group, or the name is misspelled. RelayRouter routes across the Claude family, GPT-5.5, Gemini 3.5, plus DeepSeek, GLM, MiniMax and Moonshot, so verify the exact model ID against the live list at relayrouter.io/models and confirm your key covers that group before retrying.

What causes the model not found error

The error is triggered when the requested model ID does not match a model available to your key. RelayRouter exposes protocols for both OpenAI (/v1/chat/completions) and Anthropic (/v1/messages), and 「Compatible with both the OpenAI and Anthropic protocols」, 据 relayrouter.io 官方文档. If you send a model string that is not part of the supported set (Claude family, GPT-5.5, Gemini 3.5, DeepSeek, GLM, MiniMax, Moonshot), the gateway cannot route the request. Common triggers include typos, using a model name from another provider that RelayRouter does not list, or calling a model outside your key's assigned group. Always copy the exact ID from the models page rather than typing it manually.

How to check your key's model group

Confirm your key covers the model by comparing your request against the current model list. Follow these steps:

1. Open relayrouter.io/models and locate the exact model ID you intend to call.
2. Verify the model belongs to one of the supported groups: Claude family, GPT-5.5, Gemini 3.5, DeepSeek, GLM, MiniMax, or Moonshot.
3. Copy the ID verbatim into your request payload.
4. Match the protocol to the model: use /v1/chat/completions for OpenAI style requests or /v1/messages for Anthropic style requests.
5. Resend the request and confirm the error clears.

Because failed or errored requests are generally not billed, retrying after correcting the model ID does not add charges for the earlier failures.

Fixing base URL and key mismatches

A wrong base URL or key can surface as a model error even when the model ID is valid. RelayRouter is designed so you 「Keep your existing SDK, change base_url and the key, no other code changes」, 据 relayrouter.io/docs 官方文档. If migration left the base URL pointing at another provider, requests may be misrouted. Confirm two things: the base URL targets RelayRouter for the protocol you are using, and the API key is the RelayRouter key rather than an old provider key. See the migration notes at relayrouter.io/docs. After updating both values, no further code changes are required to reach the supported models.

Protocol and model reference

Use the correct protocol endpoint for the model you are calling.

Both protocols are supported by the gateway, covering seven model groups in total (Claude family, GPT-5.5, Gemini 3.5, DeepSeek, GLM, MiniMax, Moonshot). If a model is not visible in your available list, confirm it appears on relayrouter.io/models.

FAQ

Will a model not found error be billed? No, failed or errored requests are generally not billed, so a rejected request does not incur charges.

Do I need to rewrite my code to fix the error? No, you keep your existing SDK and change only the base_url and the key, with no other code changes.

Where do I find the exact model ID? Check the live per-model list at relayrouter.io/models and copy the ID verbatim into your request.