---
title: "Models"
description: "Choose a Workers AI model, and read notes from tests on one account."
---

> Documentation Index
> Fetch the complete documentation index at: https://laravel-cf-workersai-docs.mdick85.workers.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

Workers AI hosts many open-weight models. See the [Cloudflare model catalog](https://developers.cloudflare.com/workers-ai/models/). You give the model name as a string. The package does not check that the model exists.

## Name prefixes

| Prefix | Models |
| --- | --- |
| `@cf/meta/...` | Llama |
| `@cf/openai/...` | OpenAI open-weight models |
| `@cf/google/...` | Gemma |
| `@cf/qwen/...`, `@cf/mistralai/...`, `@cf/microsoft/...` | Other vendors |
| `@cf/baai/...` | Embedding models |
| `@cf/cloudflare/clef`, `clef-flash`, `clef-omni` | Decision models. See [Clef](/docs/system-one/clef/). |
| `@cf/cloudflare/clairic` | Extraction model. See [Clairic](/docs/system-one/clairic/). |

Write the bare name, such as `@cf/openai/gpt-oss-120b`. Do not write `workers-ai/` before it. The package adds the prefix where the route needs it. See [Routes](/docs/concepts/routes/).

## Third-party models

The package sends a name that does not start with `@cf/`, such as `openai/gpt-5.5`, unchanged. On `/ai/v1`, a third-party model uses Cloudflare billing: AI Gateway credits (Unified Billing) or a stored provider key. See [AI Gateway](/docs/guides/ai-gateway/).

## Set the model

There are four ways. Each later item beats the earlier ones for that call:

1. The package default or a `models.*` config key.
2. `#[UseCheapestModel]` or `#[UseSmartestModel]` on the agent.
3. `#[Model('@cf/...')]` on the agent.
4. `model:` in the call.

Set defaults in config:

```php
'workers-ai' => [
    // ...
    'models' => [
        'text' => [
            'default'  => '@cf/openai/gpt-oss-120b',
            'cheapest' => '@cf/meta/llama-3.2-3b-instruct',
            'smartest' => '@cf/moonshotai/kimi-k2.6',
        ],
        'embeddings' => [
            'default'    => '@cf/baai/bge-large-en-v1.5',
            'dimensions' => 1024,
        ],
    ],
],
```

## Test notes

These notes come from tests on one Workers AI account. They are not a guarantee, because model behavior changes. Test the model you plan to use.

| Model | Notes |
| --- | --- |
| `@cf/openai/gpt-oss-120b` | Reasoning stays in proportion to the prompt. Obeys `reasoning_effort`. Calls tools. A safe default for agent work. |
| `@cf/meta/llama-3.3-70b-instruct-fp8-fast` | Package default text model. Does not call tools on the `/v1` endpoint. Stops at 256 tokens with no cap. |
| `@cf/meta/llama-4-scout-17b-16e-instruct` | Calls tools. |
| `@cf/zai-org/glm-5.3-flash` | Good on short inputs. Treats `reasoning_effort` as on or off. Ignores `chat_template_kwargs.thinking`. Ran 8,190 tokens in 369 seconds with no cap. Always set a cap. |
| `@cf/zai-org/glm-4.7-flash` | Returns `content` normally. Ignores `reasoning_effort`. Took about 29 seconds on a two-sentence question. |
| `@cf/moonshotai/kimi-k2.6` | Package "smartest" model. Reads `chat_template_kwargs.thinking`. Structured calls with thinking off returned valid JSON in about 4 seconds. With thinking on, they broke the schema and passed the 60-second timeout. |
| `@cf/meta/llama-3.2-3b-instruct` | Package "cheapest" model. |
| `@cf/baai/bge-large-en-v1.5` | Package default embedding model. |

## Model errors

| Cloudflare response | Meaning |
| --- | --- |
| `410 Model has been deprecated` | Cloudflare retired the model. Pick another. |
| `403 This account is not allowed to access` | Your plan does not include the model. `@cf/zai-org/glm-5.3` is not enabled on every account. |
| `400 No such model` | You sent a `workers-ai/`-prefixed name to the direct API. The package throws `InvalidArgumentException` before the request. |

`@cf/meta/llama-3.1-8b-instruct` is retired. It was the `#[UseCheapestModel]` default through version 0.6.1.

Source: https://laravel-cf-workersai-docs.mdick85.workers.dev/docs/guides/models/index.mdx