> For the complete documentation index, see [llms.txt](https://docs.avis.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.avis.net/guide/get-started/avis-choose-model.md).

# How to find and choose a model

Avis gives you 300+ models for text, image, video, audio, and embeddings, all with one API key. This guide shows how to browse the catalogue, compare models, and get the exact model ID to use in your code.

***

## Browse models on the website

**Step 1:** Go to the model catalogue at <https://www.avis.net/profile/models>.

**Step 2:** Filter by what you want to do: text, image, video, audio, or embedding.

**Step 3:** Copy the **model ID**. That's the value you pass as `model` in your request.

***

## List models with the API

```bash
# All active models
curl https://api.avis.net/api/v1/ai/models \
  -H "x-api-key: $AVIS_API_KEY"

# Only models that output video
curl "https://api.avis.net/api/v1/ai/models?outputModalities=video" \
  -H "x-api-key: $AVIS_API_KEY"

# One model, with its full capabilities
curl https://api.avis.net/api/v1/ai/models/wan-2-6 \
  -H "x-api-key: $AVIS_API_KEY"
```

Pass the `modelId` from the response as `model` in your generation request. The list only includes models that are currently active.

Full reference: [Model List](/api-reference/endpoints/model-list.md).

***

## How to choose

| If you need...                        | Look at...                                                                                                                                        |
| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| The lowest cost                       | The price on the model page, or run an [estimate](https://github.com/coin98/documentation/tree/docs_avis/guide/get-started/avis-estimate-cost.md) |
| A specific video length or resolution | `capabilities.video.params` for that model, since each model allows different values                                                              |
| Tools, JSON output, or reasoning      | `capabilities.text.supportedParameters`                                                                                                           |
| Image or file input                   | `inputModalities`                                                                                                                                 |
| Commercial use of the output          | The model provider's licence terms                                                                                                                |

**Note:** Don't assume one model's limits apply to another. For example, `wan-2-6` accepts any duration from 2 to 15 seconds, while `hailuo-2-3` only accepts exactly 6 or 10 seconds. Sending a value the model doesn't allow returns `400`.

***

## Commercial use

Each model comes with its own terms from its provider. Before using generated content commercially, check that model's licence. Output may also carry AI watermarks or metadata.

***

## FAQ

### Can I call a Claude model through the OpenAI endpoint?

Yes. Every API surface (OpenAI, Anthropic, Gemini) accepts every model in the Avis catalogue.

### Why did I get "unsupported model"?

The model ID is wrong, or the model is no longer active. Look it up again with `GET /api/v1/ai/models`.

### Are new models added often?

Yes. See the [Changelog](/guide/change-log.md) for new providers and models.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.avis.net/guide/get-started/avis-choose-model.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.