> This page is for version v2 (default).
> For other versions, use one of these documentation indexes:
> - v2 (default): https://developer.ideogram.ai/v2/llms.txt
> - v1: https://developer.ideogram.ai/v1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developer.ideogram.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developer.ideogram.ai/_mcp/server.

> Choose an Ideogram API model: the endpoint for each task, how the image models differ in inputs and controls, and the upscale, video and vector models.

Every v2 endpoint names its model in the path, `POST /v2/{content}/{action}/{model}`, so choosing a model means choosing an endpoint. Start from the task, then pick the model that has the inputs and controls you need.

## Pick an endpoint for the task

| Task                               | Endpoint                                                                                               | What to know                                                                                                    |
| ---------------------------------- | ------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------- |
| Generate images from a prompt      | [`POST /v2/image/generate/{model}`](/v2/api-reference/images/generate/ideogram-4-5)                    | Compare the models below, or send the request to `auto` and let Ideogram pick                                   |
| Edit an image and keep its size    | [`POST /v2/image/precise-edit/ideogram-4-5`](/v2/api-reference/images/precise-edit/ideogram-4-5)       | The result has the source image's width and height. Optional mask and up to 4 reference images                  |
| Transform an image with a prompt   | [`POST /v2/image/remix/{model}`](/v2/api-reference/images/remix/ideogram-4-5)                          | `image_weight`, from 1 to 100, sets how closely the result follows the source                                   |
| Repaint a masked region            | [`POST /v2/image/inpaint/ideogram-3`](/v2/api-reference/images/inpaint/ideogram-3)                     | The mask is required. Black marks the area to repaint                                                           |
| Change the aspect ratio            | [`POST /v2/image/reframe/{model}`](/v2/api-reference/images/reframe/ideogram-3)                        | Ideogram 3.0 keeps the source pixels in the center and fills the new area                                       |
| Replace the background             | [`POST /v2/image/replace-background/{model}`](/v2/api-reference/images/replace-background/ideogram-3)  | Ideogram 3.0 and GPT Image 2 follow a prompt. Ideogram 4.5 copies the setting in a `background_reference` image |
| Remove the background              | [`POST /v2/image/remove-background/ideogram-1`](/v2/api-reference/images/remove-background/ideogram-1) | Returns the foreground as a transparent PNG                                                                     |
| Remove an object                   | [`POST /v2/image/remove-object/ideogram-1`](/v2/api-reference/images/remove-object/ideogram-1)         | The mask is required. White marks the object to remove. Returns a `generation_id` to poll                       |
| Upscale                            | [`POST /v2/image/upscale/{model}`](/v2/api-reference/images/upscale/auto)                              | 2x, 4x or 8x. See [upscale models](#upscale-models)                                                             |
| Turn an image into a prompt        | [`POST /v2/image/describe/{model}`](/v2/api-reference/images/describe/ideogram-4)                      | Ideogram 4.0 returns a structured JSON prompt; Ideogram 3.0 returns text                                        |
| Make the text in an image editable | [`POST /v2/design/layerize/ideogram-3`](/v2/api-reference/images/layerize/ideogram-3)                  | Returns positioned text blocks with fonts, sizes and colors, plus the image without its text                    |
| Generate SVG artwork               | [`POST /v2/svg/generate/{model}`](/v2/api-reference/vectors/generate-svg)                              | Ideogram Vector 1, or GPT Image 2.6 Flare and Sunburst                                                          |
| Convert an image to SVG            | [`POST /v2/svg/vectorize/ideogram-vector-1`](/v2/api-reference/vectors/image-to-svg)                   | Runs asynchronously                                                                                             |
| Generate video                     | [`POST /v2/video/generate/{model}`](/v2/api-reference/video/generate/seedance-2-5-text-to-video)       | Always asynchronous. See [Generate video](/v2/ideogram-api/video)                                               |
| Adapt ads and product photos       | [`POST /v2/tool/{tool}`](/v2/api-reference/tools/ad-resizer)                                           | Resize, localize and vary ads; recolor and re-material products. Always asynchronous                            |

To edit or generate in the Ideogram app instead, see [Models](https://docs.ideogram.ai/create/models) in the user guide.

## Image generation models

| Model                    | Endpoint                                                       | Choose it for                                                                   | Inputs and controls                                                                                                                                                                                                                          |
| ------------------------ | -------------------------------------------------------------- | ------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Automatic                | `auto`                                                         | Not choosing a model yourself                                                   | Ideogram picks a model per request. Up to 10 source images to edit, and a `resolution_tier` of 1k, 2k or 4k                                                                                                                                  |
| Ideogram 4.6             | `ideogram-4-6`                                                 | The newest Ideogram model, for generating or editing at up to 4K                | Text or [JSON prompts](https://docs.ideogram.ai/prompting/json-prompting), up to 5 source images and a mask, `background` (`auto`, `transparent`, `opaque`), `quality` (`very_low`, `low`, `medium`, `high`) and exact sizes up to 4096x4096 |
| Ideogram 4.5             | `ideogram-4-5`                                                 | Editing or combining images with a prompt, and transparent output from a prompt | Text or [JSON prompts](https://docs.ideogram.ai/prompting/json-prompting), up to 5 source images and a mask, `background` (`auto`, `transparent`, `opaque`) and `quality` (`very_low` with source images, `low`, `medium`, `high`)           |
| Ideogram 4.0             | `ideogram-4`                                                   | Wide formats such as banners and headers, at 1K or 2K                           | Text or JSON prompts, `rendering_speed` (`turbo`, `default`, `quality`)                                                                                                                                                                      |
| Ideogram 4.0 Transparent | `ideogram-4-transparent`                                       | Stickers, icons and print designs with no background                            | `output_resolution` from 1k to 8k                                                                                                                                                                                                            |
| Ideogram 3.0             | `ideogram-3`                                                   | Logos, brand graphics and matching a set style                                  | Style types, presets and codes, up to 10 `style_reference_images`, a color palette and a negative prompt                                                                                                                                     |
| Ideogram 3.0 Character   | `ideogram-3-character`                                         | Keeping one character consistent across images                                  | One `character_reference_images` image and an optional mask                                                                                                                                                                                  |
| Ideogram 3.0 Transparent | `ideogram-3-transparent`                                       | Transparent output with Ideogram 3.0 styling                                    | `upscale_factor` of 1x, 2x or 4x in the same call                                                                                                                                                                                            |
| Custom models            | `ideogram-4-custom-model`, `ideogram-3-custom-model`           | A look trained on your own images                                               | `custom_model_uri`. Training uses the [v1 API](/v1/tutorials/custom-model-training)                                                                                                                                                          |
| P-Image Ideogram         | `p-image-ideogram`                                             | Fast, low-cost drafts and volume                                                | Quality from very low to very high, 1k or 2k, or custom dimensions                                                                                                                                                                           |
| GPT Image                | `gpt-image-2`, `gpt-image-2-5-flare`, `gpt-image-2-5-sunburst` | OpenAI's models, editing up to 16 source images                                 | A mask on the first source image limits the edit. Flare is the fast variant of GPT Image 2.5 and Sunburst the quality variant; both add `background` and `quality`                                                                           |
| Nano Banana              | `nano-banana-2`, `nano-banana-2-1`, `nano-banana-pro`          | Google's models, with up to 10 source images                                    | `resolution_tier` of 1K, 2K or 4K                                                                                                                                                                                                            |
| Z-Image                  | `z-image`                                                      | Exact output sizes up to 1,048,576 pixels                                       | `num_inference_steps` from 1 to 128                                                                                                                                                                                                          |
| Ideogram 2.0 and 2a      | `ideogram-2`, `ideogram-2a`                                    | Existing integrations                                                           | Still available. Use Ideogram 4.5 or 4.0 for new work                                                                                                                                                                                        |

Every generate endpoint takes `num_images` from 1 to 8. Ideogram models also take `seed`, which makes a generation repeatable, and most take `magic_prompt`, which rewrites your prompt with more detail before the model sees it. Turn it off when the model should follow your exact words.

### What image generation costs

Each model has its own rate, and some rates depend on quality, speed or output size. These are the rates per image on the [API pricing page](https://ideogram.ai/api-pricing) on November 15, 2026. The pricing page is the current source, and a [price quote](/v2/ideogram-api/price-quotes) gives the exact price of one request.

| Model                          | Price per image                                                                                                 |
| ------------------------------ | --------------------------------------------------------------------------------------------------------------- |
| Ideogram 4.6, no source images | \$0.008 very low, \$0.03 low, \$0.06 medium, \$0.10 high up to 2K; \$0.06 low, \$0.12 medium, \$0.20 high at 4K |
| Ideogram 4.5, no source images | \$0.03 low, \$0.06 medium, \$0.10 high                                                                          |
| Ideogram 4.0                   | \$0.03 turbo, \$0.06 default, \$0.10 quality                                                                    |
| Ideogram 3.0                   | \$0.03 turbo, \$0.06 default, \$0.09 quality                                                                    |
| Ideogram 3.0 Character         | \$0.10 turbo, \$0.15 default, \$0.20 quality                                                                    |
| P-Image Ideogram, 1K           | \$0.003 very low to \$0.033 very high                                                                           |
| Nano Banana 2                  | \$0.0672 at 1K, \$0.1008 at 2K, \$0.1512 at 4K                                                                  |
| Nano Banana Pro                | \$0.1344 at 1K or 2K, \$0.24 at 4K                                                                              |
| GPT Image                      | OpenAI's list token prices for the tokens each request uses                                                     |

Ideogram 4.6 without `quality` renders at `medium`. Ideogram 4.5 without `quality` renders at `high` when you send no source images, and at `medium` when you do.

## Upscale models

| Model                            | Endpoint                          | Choose it for                                                                                |
| -------------------------------- | --------------------------------- | -------------------------------------------------------------------------------------------- |
| Automatic                        | `auto`                            | Letting Ideogram pick per request. The choice may change over time                           |
| Topaz Standard V2                | `topaz-standard-2`                | A clean enlargement with no prompt                                                           |
| Topaz Text Refine                | `topaz-text-refine`               | Keeping lettering sharp on ads, labels and packaging                                         |
| Topaz Wonder 3.5                 | `topaz-wonder-3-5`                | Rebuilding detail, with `enhancement_strength`                                               |
| Topaz Wonder 4                   | `topaz-wonder-4`                  | Removing noise, blur and compression artifacts and recovering faces in one pass, at 2x or 4x |
| Topaz Bloom 2 and Topaz Redefine | `topaz-bloom-2`, `topaz-redefine` | Creative upscaling that regenerates detail, guided by an optional prompt                     |
| Nano Banana Pro                  | `nano-banana-pro`                 | Regenerating the image at a 1K, 2K or 4K tier                                                |

Topaz upscalers bill per output megapixel. The `auto`, Standard V2, Text Refine, Wonder 3.5, Bloom 2 and Redefine endpoints reject a request whose output would be wider or taller than 8,192 pixels. The user guide's [Upscale](https://docs.ideogram.ai/edit/upscale) page compares faithful and creative upscalers with examples.

## Video models

| Model             | Endpoints                                         | Inputs                                                                             | Length          |
| ----------------- | ------------------------------------------------- | ---------------------------------------------------------------------------------- | --------------- |
| Seedance 2.5      | Text to video, image to video, reference to video | First and last frames, up to 9 reference images and up to 10 reference audio clips | 4 to 30 seconds |
| Seedance 2.0      | Text to video, image to video, reference to video | First and last frames, up to 9 reference images and 3 reference audio clips        | 4 to 15 seconds |
| Kling 4.0         | One endpoint                                      | Up to 10 frames and 10 reference images                                            | 3 to 30 seconds |
| Kling v3 Standard | Text to video, image to video                     | First and last frames                                                              | 3 to 15 seconds |
| MiniMax H3        | Text to video, image to video, reference to video | First and last frames, up to 9 reference images and 3 reference audio clips        | 5 to 15 seconds |

[Generate video](/v2/ideogram-api/video) covers the request, polling and pricing.

## Vector models

| Model                            | Endpoint                                                                                    | Choose it for                                                                                |
| -------------------------------- | ------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- |
| Ideogram Vector 1                | `POST /v2/svg/generate/ideogram-vector-1`                                                   | SVG artwork from a prompt and up to 5 image references, at `low`, `medium` or `high` quality |
| Ideogram Vector 1                | `POST /v2/svg/vectorize/ideogram-vector-1`                                                  | Converting a raster image to SVG, in `simple`, `detailed` or `auto` mode                     |
| GPT Image 2.6 Flare and Sunburst | `POST /v2/svg/generate/gpt-image-2-6-flare`, `POST /v2/svg/generate/gpt-image-2-6-sunburst` | SVG artwork from OpenAI's models, with `quality` and `thinking_level`                        |

## Older models

The v1 API and Ideogram 2.0 and 2a keep working. See [Model lifecycle and deprecations](/v2/ideogram-api/deprecations) for what is legacy and how deprecations are announced.