> 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.

# Generate with a custom Ideogram 4.0 model

POST https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model
Content-Type: application/json

Generate images with a custom Ideogram 4.0 model that you or your
organization can access, selected by `custom_model_uri`. Returns results
directly by default; set `async` or supply a `webhook_url` to get a
`generation_id` and poll `GET /v2/generations/{generation_id}`.

Reference: https://developer.ideogram.ai/api-reference/images/generate/ideogram-4-custom-model

## Authentication

- `Api-Key` header (required) — API key for access control. Use in the header with the name \"Api-Key\"

## Request

### Query parameters

- `dry_run` (boolean, optional, default: false) — When true, the request is validated and priced but not run: nothing is generated, stored, or billed, and no safety review is performed. The response is a `PriceQuote` object instead of the usual response for this endpoint. Send exactly the request you would send to generate, so the quote reflects the same options.

### Body (application/json)

This endpoint expects a GenerateImageIdeogramV4CustomModelRequest.

- `prompt` (string, required) — The prompt to generate images from, in natural language or as a structured Ideogram 4.0 JSON prompt. A structured JSON prompt is used as is and skips magic prompt.
- `custom_model_uri` (string, required) — The custom model URI, in the form `model/<model_name>/version/<version_name>`. You or your organization must have access to the model. The model determines which rendering speeds are supported.
- `magic_prompt` (enum, optional, default: auto) — Controls how a natural-language prompt is prepared. `auto` (the default) and `on` rewrite and expand the prompt before generation. `off` keeps your wording and only converts it into a structured prompt. A valid structured JSON prompt skips magic prompt unless `magic_prompt` is `on`.
  - Allowed values: `auto`, `on`, `off`
- `seed` (integer, optional) — Random seed. Set for reproducible generation.
- `num_images` (integer, optional, default: 1) — The number of images to generate.
- `resolution` (enum, optional) — Optional. When supplied, the images are generated at this resolution. When omitted, an aspect ratio is picked automatically based on the prompt.
  - Allowed values: `2048x2048`, `1440x2880`, `2880x1440`, `1664x2496`, `2496x1664`, `1792x2240`, `2240x1792`, `1440x2560`, `2560x1440`, `1600x2560`, `2560x1600`, `1728x2304`, `2304x1728`, `1296x3168`, `3168x1296`, `1152x2944`, `2944x1152`, `1248x3328`, `3328x1248`, `1280x3072`, `3072x1280`, `1024x3072`, `3072x1024`, `1024x1024`, `896x1120`, `1120x896`, `864x1152`, `1152x864`, `832x1248`, `1248x832`, `800x1280`, `1280x800`, `720x1280`, `1280x720`, `720x1440`, `1440x720`, `512x1536`, `1536x512`
- `rendering_speed` (enum, optional) — The rendering speed to use. When omitted, a speed supported by the custom model is used.
  - Allowed values: `turbo`, `default`, `quality`
- `enable_copyright_detection` (boolean, optional, nullable) — Optional. Run copyright detection on the generated images. Adds latency; flagged images are returned with `is_image_safe: false`.
- `async` (boolean, optional, default: false) — When false (the default), the request waits until the images are ready and returns them in `data`. When true, the request returns as soon as it is accepted; poll `GET /v2/generations/{generation_id}` with the returned `generation_id` for the result.
- `webhook_url` (string, optional) — HTTPS URL that Ideogram delivers the generated result to. Ideogram sends a JSON POST to this URL once all images for the request have finished generating. The body mirrors the synchronous generate response: `request_id`, `created`, and a `data` array containing every generated image (`url`, `prompt`, `resolution`, `seed`, `is_image_safe`). Each delivery is signed with Ed25519 and verifiable against the public keys at `https://api.ideogram.ai/v1/.well-known/jwks.json`. Must be HTTPS; private and loopback hosts and the cloud metadata service are rejected.

## Response

### 200

The generated images (synchronous requests), or an acknowledgement to poll with `GET /v2/generations/{generation_id}` (`async` requests).

- `generation_id` (string, required) — URL-safe base64 ID of the generation. Use it to poll `GET /v2/generations/{generation_id}`.
- `seed` (integer, required) — Random seed. Set for reproducible generation.
- `data` (list of GeneratedImageObject, optional) — The generated images, in generation order. Present only for synchronous requests (`async` omitted or false).

## Errors

### 400 Bad Request Error

Invalid input or an unsupported model option.

- `any`

### 401 Unauthorized Error

Unauthorized.

- `any`

### 402 Payment Required Error

Insufficient credits or quota.

- `error` (string, required) — A message describing why the generation request was rejected.
- `reject_reason` (enum, required) — The account or usage limit that rejected a generation request.
  - Allowed values: `insufficient_funds`, `subscription_required`, `daily_limit`, `priority_credit_required`, `inflight_limit`, `feature_limit`
- `max_inflight_requests` (integer, optional) — How many generations the account may have in progress at once on the queue this request resolved to. Present when `reject_reason` is `inflight_limit`.
- `task_completion_speed` (enum, optional) — The queue this request resolved to. Present when `reject_reason` is `inflight_limit`.
  - Allowed values: `fast`, `slow`

### 403 Forbidden Error

The custom model does not exist or is not accessible to this user or organization.

- `any`

### 422 Unprocessable Entity Error

The prompt did not pass safety checks.

- `any`

### 429 Too Many Requests Error

Too many requests.

- `error` (string, required) — A message describing why the generation request was rejected.
- `reject_reason` (enum, required) — The account or usage limit that rejected a generation request.
  - Allowed values: `insufficient_funds`, `subscription_required`, `daily_limit`, `priority_credit_required`, `inflight_limit`, `feature_limit`
- `max_inflight_requests` (integer, optional) — How many generations the account may have in progress at once on the queue this request resolved to. Present when `reject_reason` is `inflight_limit`.
- `task_completion_speed` (enum, optional) — The queue this request resolved to. Present when `reject_reason` is `inflight_limit`.
  - Allowed values: `fast`, `slow`

### 500 Internal Server Error

Internal server error.

- `any`

### 503 Service Unavailable Error

The endpoint is temporarily unavailable.

- `any`

## Types

### GeneratedImageObject

One generated output image.

- `prompt` (string, required) — The final prompt the image was generated from.
- `resolution` (string, required) — The resolution of the generated image, formatted as "WIDTHxHEIGHT".
- `is_image_safe` (boolean, required) — Whether the image passed safety checks. If false, `url` is empty.
- `seed` (integer, required) — Random seed. Set for reproducible generation.
- `url` (string, optional, nullable) — The direct link to the generated image. Empty when the image did not pass safety checks.

## Examples

**Request**

```json
{
  "prompt": "prompt",
  "custom_model_uri": "model/my-custom-v4-model/version/1",
  "magic_prompt": "auto",
  "seed": 12345,
  "num_images": 1,
  "resolution": "2048x2048",
  "rendering_speed": "turbo",
  "enable_copyright_detection": true,
  "async": false,
  "webhook_url": "https://api.example.com/webhooks/ideogram"
}
```

**Response**

```json
{
  "generation_id": "generation_id",
  "seed": 12345,
  "data": [
    {
      "prompt": "prompt",
      "resolution": "1024x1024",
      "is_image_safe": true,
      "seed": 12345,
      "url": "https://openapi-generator.tech"
    },
    {
      "prompt": "prompt",
      "resolution": "1024x1024",
      "is_image_safe": true,
      "seed": 12345,
      "url": "https://openapi-generator.tech"
    }
  ]
}
```

**SDK Code**

```python
import requests

url = "https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model"

payload = {
    "prompt": "prompt",
    "custom_model_uri": "model/my-custom-v4-model/version/1",
    "magic_prompt": "auto",
    "seed": 12345,
    "num_images": 1,
    "resolution": "2048x2048",
    "rendering_speed": "turbo",
    "enable_copyright_detection": True,
    "async": False,
    "webhook_url": "https://api.example.com/webhooks/ideogram"
}
headers = {
    "Api-Key": "<apiKey>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript
const url = 'https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model';
const options = {
  method: 'POST',
  headers: {'Api-Key': '<apiKey>', 'Content-Type': 'application/json'},
  body: '{"prompt":"prompt","custom_model_uri":"model/my-custom-v4-model/version/1","magic_prompt":"auto","seed":12345,"num_images":1,"resolution":"2048x2048","rendering_speed":"turbo","enable_copyright_detection":true,"async":false,"webhook_url":"https://api.example.com/webhooks/ideogram"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model"

	payload := strings.NewReader("{\n  \"prompt\": \"prompt\",\n  \"custom_model_uri\": \"model/my-custom-v4-model/version/1\",\n  \"magic_prompt\": \"auto\",\n  \"seed\": 12345,\n  \"num_images\": 1,\n  \"resolution\": \"2048x2048\",\n  \"rendering_speed\": \"turbo\",\n  \"enable_copyright_detection\": true,\n  \"async\": false,\n  \"webhook_url\": \"https://api.example.com/webhooks/ideogram\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Api-Key", "<apiKey>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Api-Key"] = '<apiKey>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"prompt\": \"prompt\",\n  \"custom_model_uri\": \"model/my-custom-v4-model/version/1\",\n  \"magic_prompt\": \"auto\",\n  \"seed\": 12345,\n  \"num_images\": 1,\n  \"resolution\": \"2048x2048\",\n  \"rendering_speed\": \"turbo\",\n  \"enable_copyright_detection\": true,\n  \"async\": false,\n  \"webhook_url\": \"https://api.example.com/webhooks/ideogram\"\n}"

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model")
  .header("Api-Key", "<apiKey>")
  .header("Content-Type", "application/json")
  .body("{\n  \"prompt\": \"prompt\",\n  \"custom_model_uri\": \"model/my-custom-v4-model/version/1\",\n  \"magic_prompt\": \"auto\",\n  \"seed\": 12345,\n  \"num_images\": 1,\n  \"resolution\": \"2048x2048\",\n  \"rendering_speed\": \"turbo\",\n  \"enable_copyright_detection\": true,\n  \"async\": false,\n  \"webhook_url\": \"https://api.example.com/webhooks/ideogram\"\n}")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model', [
  'body' => '{
  "prompt": "prompt",
  "custom_model_uri": "model/my-custom-v4-model/version/1",
  "magic_prompt": "auto",
  "seed": 12345,
  "num_images": 1,
  "resolution": "2048x2048",
  "rendering_speed": "turbo",
  "enable_copyright_detection": true,
  "async": false,
  "webhook_url": "https://api.example.com/webhooks/ideogram"
}',
  'headers' => [
    'Api-Key' => '<apiKey>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model");
var request = new RestRequest(Method.POST);
request.AddHeader("Api-Key", "<apiKey>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"prompt\": \"prompt\",\n  \"custom_model_uri\": \"model/my-custom-v4-model/version/1\",\n  \"magic_prompt\": \"auto\",\n  \"seed\": 12345,\n  \"num_images\": 1,\n  \"resolution\": \"2048x2048\",\n  \"rendering_speed\": \"turbo\",\n  \"enable_copyright_detection\": true,\n  \"async\": false,\n  \"webhook_url\": \"https://api.example.com/webhooks/ideogram\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = [
  "Api-Key": "<apiKey>",
  "Content-Type": "application/json"
]
let parameters = [
  "prompt": "prompt",
  "custom_model_uri": "model/my-custom-v4-model/version/1",
  "magic_prompt": "auto",
  "seed": 12345,
  "num_images": 1,
  "resolution": "2048x2048",
  "rendering_speed": "turbo",
  "enable_copyright_detection": true,
  "async": false,
  "webhook_url": "https://api.example.com/webhooks/ideogram"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.ideogram.ai/v2/image/generate/ideogram-4-custom-model")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```