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

# Images

> Generate images with the OpenAI-compatible API.

<Info>
  Base URL: `https://api.freemodel.app/v1`
</Info>

Generate one image from a text prompt. Image generation is synchronous and usually completes in 20 to 60 seconds. Set your client timeout to at least 120 seconds.

## Create an image

`POST /images/generations`

The response contains the generated image as base64 in `data[0].b64_json`. Decode it and write the bytes to an image file.

<CodeGroup>
  ```bash Curl theme={null}
  curl https://api.freemodel.app/v1/images/generations \
    -H "Authorization: Bearer $FREEMODEL_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-image-2",
      "prompt": "A clean indigo hexagon logo on a white background",
      "size": "1024x1024"
    }' \
    | jq -r '.data[0].b64_json' \
    | base64 --decode > image.png
  ```

  ```python Python theme={null}
  import base64
  import json
  import os
  from urllib.request import Request, urlopen

  request = Request(
      "https://api.freemodel.app/v1/images/generations",
      data=json.dumps({
          "model": "gpt-image-2",
          "prompt": "A clean indigo hexagon logo on a white background",
          "size": "1024x1024",
      }).encode(),
      headers={
          "Authorization": f"Bearer {os.environ['FREEMODEL_API_KEY']}",
          "Content-Type": "application/json",
      },
      method="POST",
  )

  with urlopen(request, timeout=120) as response:
      payload = json.load(response)

  with open("image.png", "wb") as image_file:
      image_file.write(base64.b64decode(payload["data"][0]["b64_json"]))
  ```

  ```javascript Node.js theme={null}
  const fs = require("node:fs/promises");

  async function main() {
    const response = await fetch(
      "https://api.freemodel.app/v1/images/generations",
      {
        method: "POST",
        headers: {
          Authorization: `Bearer ${process.env.FREEMODEL_API_KEY}`,
          "Content-Type": "application/json",
        },
        body: JSON.stringify({
          model: "gpt-image-2",
          prompt: "A clean indigo hexagon logo on a white background",
          size: "1024x1024",
        }),
        signal: AbortSignal.timeout(120_000),
      },
    );

    if (!response.ok) {
      throw new Error(await response.text());
    }

    const payload = await response.json();
    await fs.writeFile("image.png", Buffer.from(payload.data[0].b64_json, "base64"));
  }

  main();
  ```
</CodeGroup>

On macOS, replace `base64 --decode` in the curl example with `base64 -D`.

```json Response theme={null}
{
  "created": 1784045139,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUg..."
    }
  ]
}
```

## Request body

| Field    | Type    | Required | Description                                                                                                                                                                  |
| -------- | ------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model`  | string  | Yes      | Use `gpt-image-2`.                                                                                                                                                           |
| `prompt` | string  | Yes      | Describe the image you want to generate.                                                                                                                                     |
| `size`   | string  | No       | `1024x1024` creates a 1:1 image. `1536x1024` creates a 3:2 image. `1024x1536` creates a 2:3 image. Omit this field, or use another value, to use the automatic aspect ratio. |
| `n`      | integer | No       | Omit this field or set it to `1`. Multiple images are not supported.                                                                                                         |

<Note>
  Output quality is fixed at 1K in v1. Each image costs \$0.01. See the [models page](https://freemodel.app/models) for current rates.
</Note>