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

# Ideogram 4 API

> Generate images with accurate, legible text using Ideogram 4. 15 aspect ratios at about 4 megapixels, three quality tiers, negative prompts and Magic Prompt control.

<Card title="Ideogram 4" icon="font">
  Generate images with accurate, legible text: posters, logos, packaging and social graphics.
</Card>

Ideogram 4 is a text-to-image model known for rendering text inside images. Put the words you want drawn in quotes in the `prompt` and the model lays them out as part of the design. It renders at about 4 megapixels in 15 aspect ratios, from `3:1` banners to `1:3` vertical panels.

### Key capabilities

* **Text rendering**: Headlines, logos and labels written exactly as quoted in the prompt
* **15 aspect ratios**: From `3:1` to `1:3`, at about 4 megapixels (`2048x2048` at `1:1`)
* **Three quality tiers**: `rendering_speed` `TURBO`, `DEFAULT` or `QUALITY`. It is the only parameter that changes the price
* **Negative prompt**: Describe what to leave out of the image
* **Magic Prompt**: Let the model expand a short prompt, or turn it `OFF` to render your prompt verbatim
* **Seed**: Optional `seed` for the generation
* **Prompt range**: 1 to 10,000 characters
* **Async processing**: Webhook notification or polling for task completion

### Use cases

* **Posters and flyers**: Event, travel and campaign posters with legible headlines
* **Logos and wordmarks**: Typographic concepts for brands and products
* **Social graphics**: Announcements and quote cards with exact copy
* **Banners and panels**: Wide `3:1` headers or tall `1:3` panels natively, without cropping

### API operations

Create an image with the POST endpoint, then track it with the list and status endpoints. Generation returns a task ID for async polling or webhook notification.

<div className="my-11">
  <Columns cols={2}>
    <Card title="POST /v1/ai/text-to-image/ideogram-4" icon="wand-magic-sparkles" href="/api-reference/text-to-image/ideogram-4/generate">
      Create a new image generation task
    </Card>

    <Card title="GET /v1/ai/text-to-image/ideogram-4" icon="list" href="/api-reference/text-to-image/ideogram-4/ideogram-4-tasks">
      List all Ideogram 4 tasks
    </Card>

    <Card title="GET /v1/ai/text-to-image/ideogram-4/{task-id}" icon="magnifying-glass" href="/api-reference/text-to-image/ideogram-4/task-by-id">
      Get task status and results by ID
    </Card>
  </Columns>
</div>

### Parameters

| Parameter | Type | Required | Default | Description |
| - | - | - | - | - |
| `prompt` | `string` | Yes | - | Text description of the image (1-10,000 characters). Put the text to draw in quotes |
| `rendering_speed` | `string` | No | `DEFAULT` | `TURBO`, `DEFAULT`, `QUALITY`. Sets the price |
| `aspect_ratio` | `string` | No | `1:1` | `1:1`, `16:9`, `9:16`, `16:10`, `10:16`, `4:3`, `3:4`, `3:2`, `2:3`, `5:4`, `4:5`, `2:1`, `1:2`, `3:1`, `1:3` |
| `negative_prompt` | `string` | No | - | What to leave out of the image (up to 2,000 characters) |
| `magic_prompt` | `string` | No | `AUTO` | `AUTO`, `ON`, `OFF` |
| `seed` | `integer` | No | random | 0 to 2147483647 |
| `webhook_url` | `string` | No | - | URL for async status notifications |

### Output sizes

The output is up to about 4 megapixels, shaped to the requested ratio. Measured examples:

| `aspect_ratio` | Output |
| - | - |
| `1:1` | 2048x2048 |
| `16:9` | 2560x1440 |
| `1:3` | 1024x3072 |

## Frequently Asked Questions

<AccordionGroup>
  <Accordion title="What is Ideogram 4 and how does it work?">
    Ideogram 4 is a text-to-image model specialised in rendering text inside images. You send a `prompt` (1-10,000 characters) and receive a task ID immediately. Poll the task endpoint or configure a `webhook_url` to receive the generated image URL when processing completes. Each request generates one image.
  </Accordion>

  <Accordion title="How do I get the exact text I want in the image?">
    Put the text in quotes inside the prompt, for example *a neon sign that reads "OPEN LATE"*. Keep it short: headlines and logos render best. Set `magic_prompt` to `OFF` if you want the model to follow your prompt literally instead of expanding it.
  </Accordion>

  <Accordion title="What is the difference between TURBO, DEFAULT and QUALITY?">
    They trade speed for quality. `TURBO` is the fastest and cheapest, `DEFAULT` balances both, and `QUALITY` gives the most detailed result. `rendering_speed` is the only parameter that changes the price.
  </Accordion>

  <Accordion title="What does Magic Prompt do?">
    Magic Prompt rewrites a short prompt into a more detailed one before generating. With `AUTO` (default) the model decides when to use it; `ON` always expands the prompt; `OFF` renders your prompt as written. It does not change the price.
  </Accordion>

  <Accordion title="Can I edit an existing image with Ideogram 4?">
    No, Ideogram 4 is text-to-image only. To edit an image, or to guide a generation with reference images, use [Ideogram 4.5](/api-reference/text-to-image/ideogram-4-5/overview).
  </Accordion>

  <Accordion title="How much does Ideogram 4 cost?">
    The price depends only on `rendering_speed`: `TURBO`, `DEFAULT` or `QUALITY`. The aspect ratio, negative prompt and Magic Prompt do not change it. See the [Pricing page](/pricing) for current rates.
  </Accordion>

  <Accordion title="What are the rate limits for Ideogram 4?">
    Rate limits depend on your subscription tier. See [Rate Limits](/ratelimits) for current limits.
  </Accordion>
</AccordionGroup>

## Best practices

* **Quote the text**: Write the exact words to render in quotes, and keep them short
* **Iterate with `TURBO`**: Explore ideas with `TURBO` and render the final asset with `QUALITY`
* **Use `negative_prompt` sparingly**: Describe what you want in the prompt first; descriptions in the prompt take precedence
* **Production integration**: Use `webhook_url` instead of polling for scalable applications
* **Error handling**: Implement retry logic with exponential backoff for 503 errors

## Related APIs

* **[Ideogram 4.5](/api-reference/text-to-image/ideogram-4-5/overview)**: Generation and editing with up to 5 input images
* **[Ideogram Image Edit](/api-reference/ideogram-image-edit/overview)**: Mask-based inpainting with Ideogram
* **[Magnific One](/api-reference/text-to-image/magnific-one/overview)**: Image model with art direction built in


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.