> For the complete documentation index, see [llms.txt](https://docs.flora.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flora.ai/api/guides/models.md).

# Models

List the FLORA models your API key can use, with each model's ID, parameters, typical run time and base price in US dollars.

The models endpoint lists the generation models available to your account, so you can pass a valid `model` ID and `params` to [Generations](/api/guides/generations.md). Filter by `type` to see only image, video, audio, text or 3D models.

## List models

{% tabs %}
{% tab title="curl" %}

```bash
curl "https://app.flora.ai/api/v1/models?type=image" \
  -H "Authorization: Bearer $FLORA_API_KEY"
```

{% endtab %}

{% tab title="TypeScript" %}

```ts
import { FloraClient } from "@flora-ai/flora"

const client = new FloraClient()

const { models } = await client.models.list({ type: "video" })
for (const model of models) {
  console.log(model.model_id, model.name, `$${model.estimated_cost_usd}`)
}
```

{% endtab %}
{% endtabs %}

Response (trimmed):

```json
{
  "models": [
    {
      "model_id": "t2i-flux-2-pro",
      "name": "Flux 2 Pro",
      "type": "image",
      "provider": "fal",
      "capabilities": ["text-to-image"],
      "estimated_cost_usd": 0.036,
      "estimated_seconds": 30,
      "params": [
        { "name": "aspect_ratio", "type": "string", "default": "square_1_1", "options": [{ "label": "Landscape (16:9)", "value": "landscape_16_9" }] },
        { "name": "seed", "type": "seed", "min": 0, "max": 1000000000 }
      ]
    }
  ],
  "featured": [{ "model_id": "t2i-flux-2-pro", "name": "Flux 2 Pro", "type": "image" }]
}
```

| Field                | Notes                                                                                                                                               |
| -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model_id`           | Pass this as `model` on `POST /generate`                                                                                                            |
| `capabilities`       | What the model does, such as `text-to-image` or `image-to-video`                                                                                    |
| `estimated_cost_usd` | Base price of one generation in US dollars. Parameters can change it; get an exact figure with a [quote](/api/guides/generations.md#price-it-first) |
| `estimated_seconds`  | Typical run time                                                                                                                                    |
| `params`             | Accepted parameters: names, types, defaults, ranges and allowed values. Media inputs such as `image_url` or `image_urls` are listed here too        |
| `featured`           | FLORA's curated picks, when present; each `model_id` matches an entry in `models`                                                                   |

`type` accepts `image`, `video`, `audio`, `text` or `model3d`.

## Common endpoints

| Method | Path                  | Description                                                                     |
| ------ | --------------------- | ------------------------------------------------------------------------------- |
| GET    | `/models?type={type}` | [List models, optionally filtered by type](/api/reference/models/listmodels.md) |

## Notes

* Model availability changes over time. Store the `model_id` the API returns, never a display name, and re-list when a model is rejected.
* Quote prices to people in US dollars from `estimated_cost_usd`. The response also has `estimated_credits`, a legacy unit kept for compatibility.
* Comparing models and rates? See [Model pricing](/plans-and-billing/model-pricing.md) and the model pages in these docs, such as [Flux 2 Pro](/models/image-models/flux-2-pro-by-black-forest-labs.md).
* Working from a Technique? Its `inputs` already define what it needs; start from [Techniques](/api/guides/techniques.md).
* From an AI client, FLORA MCP's `flora_list_models` returns the same IDs; see [Model and LoRA tools](/mcp/tools/models-and-loras.md).


---

# 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.flora.ai/api/guides/models.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.
