# `AI_APICallError: 403 model_not_allowed — Model requires privacy mode 'all' or is not in the catalog`

**Where it appears:** Terminal or Vercel runtime logs

**What it means:** Your code asked Tokentide for a model that your key's privacy setting doesn't allow, or used a misspelled model ID. Unlike 503 or 429, 403 `model_not_allowed` should be fixed in configuration, not sent to the fallback.

## Likely causes

- Calling a Claude, GPT or Gemini model using a Tokentide key set to `private` mode (open-weight models only) instead of `all`.
- Passing a Vercel AI Gateway model ID (with a provider prefix like `anthropic/...`) to the Tokentide client instead of Tokentide's catalog ID.

## Message for your agent

```text
Tokentide returned `403 model_not_allowed`. Check `GET /v1/models` to verify our Tokentide and Gateway model ID pair in configuration, and tell me if my key needs privacy mode `all` or if we should pick an open-weight `private` model.
```

**Prevention:** Keep model IDs in one config file as a checked pair (Tokentide ID ↔ Gateway ID) and match your key's privacy mode.

---
Source: [Agentic Makers](https://agenticmakers.app/en/help/errors/tokentide-403-model-not-allowed-privacy-mode) · License: CC BY 4.0