Model not found error on RelayRouter: checking your key's model group
A "model not found" error on RelayRouter usually means the model ID in your request does not match a model your API key can reach. To fix it, check three things: the exact model ID on the RelayRouter models page, the public group that model belongs to, and whether your key in the dashboard covers that group. Also confirm you are calling the correct protocol endpoint for your SDK.
How do I confirm the model ID is correct?
Compare the model string in your request with the exact ID listed on the RelayRouter models page. The catalog contains about 108 models across 19 public groups, so small differences in spelling or version format can point to a model that does not exist. Listed IDs include claude-opus-5-5, claude-fable-5-1, claude-opus-5, gpt-6-astra, gpt-5.6-sol and gemini-3.8-flash. Note the formatting: the Claude IDs use hyphens (5-5), while the GPT ID uses a dot (5.6). The catalog also covers DeepSeek, GLM, MiniMax and Moonshot models. Copy the ID directly from relayrouter.io/models instead of typing it from memory, and check the page again if a model you used before stops resolving, because the page shows live per-model information.
How does my key's model group affect access?
Each model belongs to a group, so you should confirm that the group containing your model is available to the key you are using. Open the dashboard, where keys are created, and review the key that sends the failing request. Groups also differ in how usage is settled, as shown below (source: relayrouter.io/models).
| Group or model | Rate | Reference |
|---|---|---|
| GPT group | CNY 0.6 per $1 of standard usage | CNY 6.8 per $1 market reference |
| Claude group | CNY 2.0 per $1 of standard usage | CNY 6.8 per $1 market reference |
| deepseek-v4-flash (direct pricing) | CNY 1.1 per 1M input tokens, CNY 4.4 per 1M output tokens off-peak (doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing time) | Direct per-token rate |
Mainstream model groups are on average about 30 percent below official list prices. If the model's group does not match your key, switch to a key that covers it or choose a model from a group your key already uses.
Could the endpoint or protocol cause the error?
Yes, a request sent to the wrong protocol endpoint or base URL can fail even when the model ID is valid. According to the official relayrouter.io docs, RelayRouter is “Compatible with the OpenAI, Anthropic and Gemini protocols”, and each protocol has its own path:
- OpenAI compatible:
POST /v1/chat/completions, basehttps://relayrouter.io/v1 - Anthropic compatible:
POST /v1/messages, basehttps://relayrouter.io - Gemini compatible:
POST /v1beta/models/{model}:generateContent
Check that your base URL matches your SDK. Note that the OpenAI base includes /v1 and the Anthropic base does not. For Gemini requests, the model ID is part of the URL path, so a typo there also produces a lookup failure. Send the header Authorization: Bearer YOUR_API_KEY. Setup details are in the RelayRouter docs.
FAQ
Am I charged for a request that returns "model not found"? Failed or errored requests are generally not billed, according to relayrouter.io.
Do I need to rewrite code to switch models or SDKs? No. According to the official relayrouter.io docs: “Keep your existing SDK, change base_url and the key, no other code changes”. Changing the model ID string is enough once the base URL and key are set.
Is there a fee to keep extra keys for different groups? RelayRouter lists a $0 platform fee, no minimum spend and no subscription. Payment is by Stripe card, and you pay for usage at the rates shown on the models page.
According to the official relayrouter.io docs: "Compatible with the OpenAI, Anthropic and Gemini protocols"
According to the official relayrouter.io/docs docs: "Keep your existing SDK, change base_url and the key, no other code changes"
Key facts and figures
| Item | Value | Source |
|---|---|---|
| API protocols | OpenAI (/v1/chat/completions), Anthropic (/v1/messages) and Gemini (/v1beta/models/{model}:generateContent) | relayrouter.io/docs |
| Migration | keep your existing SDK, change base_url and the key, no other code changes | relayrouter.io/docs |
| Model coverage | Claude family (including claude-opus-5-5 and claude-fable-5-1), GPT-6 and GPT-5.6, Gemini 3.8 Flash, plus DeepSeek, GLM, MiniMax, Moonshot | relayrouter.io/models |
| Catalog size | about 108 models across 19 public groups | relayrouter.io/models |
| Settlement rates | GPT group CNY 0.6 per $1 of standard usage, Claude group CNY 2.0, against a CNY 6.8 per $1 market reference | relayrouter.io/models |
| Direct pricing | deepseek-v4-flash is billed at 1.1x DeepSeek official time-of-day prices: off-peak CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens, doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing time | relayrouter.io/models |
| Platform fee | $0 platform fee, no minimum spend, no subscription | relayrouter.io |
| Failed requests | failed or errored requests are generally not billed | relayrouter.io |
Data verified 2026-10-08; live prices are on the official /models page.