> ## Documentation Index
> Fetch the complete documentation index at: https://manifest.build/llm-gateway/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# M302: Model not available

> M302 is returned when the requested model is unavailable to the authenticated harness.

## What you saw

```text theme={"theme":{"light":"github-light","dark":"github-dark"}}
[🦚 Manifest M302] Model "openai/gpt-4o" is not available for this agent. Use GET /v1/models to list available model IDs, or make the provider available for this agent here: https://app.manifest.build/...
See https://manifest.build/llm-gateway/docs/errors/M302
```

The model name varies based on the `model` value your client sent.

## Why it happened

You sent a concrete model ID instead of `auto` to an OpenAI-format endpoint, but that model is not available to this harness.

This can happen when:

1. The model ID is misspelled or retired.
2. The provider is not connected yet, or it is connected but not enabled for this harness.
3. You used a provider-native name when the gateway expects the exact ID returned by `GET /v1/models`.
4. The gateway refuses the request instead of falling back to automatic routing.

## How to fix it

1. Call `GET /v1/models` with the same harness key.
2. Use `auto` to let the gateway route, or copy one of the listed model IDs exactly.
3. If the model should be available, open the dashboard link in the error and enable or connect that provider for this harness.
4. Retry the request.

## Related

* [Routing: Route a specific model](/llm-gateway/docs/llm-gateway/docs/llm-gateway#route-a-specific-model)
* [API reference: Listing models](/llm-gateway/docs/llm-gateway/docs/reference/api#listing-models)
* [M300: Missing messages array](/llm-gateway/docs/llm-gateway/docs/errors/M300)
* [M303: Local provider unavailable on LLM Gateway Cloud](/llm-gateway/docs/llm-gateway/docs/errors/M303)
* [All error codes](/llm-gateway/docs/llm-gateway/docs/errors)