Image Generation

Generate Image

post

Generates images from text prompts. Supports OpenAI models and Leonardo AI models.

OpenAI models (gpt-image-1, gpt-image-1-mini, dall-e-2, dall-e-3) respond synchronously — the image URL is returned directly.

Leonardo models (leonardo/...) respond asynchronously — the response contains a taskId. To retrieve the image, poll POST /api/v1/getAsyncResponse with the taskId:

{ "taskId": "leo_abc123xyz" }

Poll every few seconds until the status is succeed, then use the returned image URL.

Authorizations

bearerAuth

AuthorizationstringRequired

FastRouter API Key. Get yours at https://fastrouter.ai

Format: Authorization: Bearer YOUR_API_KEY

Body

application/json

promptstringRequired

Text description of the desired image

Example: A cute baby sea otter wearing a beret

modelstring · enumRequired

Image generation model to use. OpenAI models return images synchronously. Leonardo models (leonardo/...) return a taskId — poll POST /api/v1/getAsyncResponse to retrieve the result.

Example: openai/gpt-image-1Possible values:

ninteger · min: 1 · max: 10 · nullableOptional

Number of images to generate. Note: Only n=1 is supported for dall-e-3

Default: 1

sizestring · nullableOptional

Image dimensions. Supported values vary by model:

• gpt-image-1/mini: auto, 1024×1024, 1536×1024, 1024×1536
• dall-e-2: 256×256, 512×512, 1024×1024
• dall-e-3: 1024×1024, 1792×1024, 1024×1792

Default: autoExample: 1024x1024

qualitystring · enum · nullableOptional

Image quality level:

• gpt-image-1/mini: auto, high, medium, low
• dall-e-3: auto, hd, standard
• dall-e-2: standard only

Default: autoPossible values:

output_formatstring · enum · nullableOptional

Output image format. Only supported for gpt-image-1 and gpt-image-1-mini

Default: pngPossible values:

backgroundstring · enum · nullableOptional

Background style. Only for gpt-image-1 and gpt-image-1-mini. Note: transparent requires png or webp format

Default: autoPossible values:

stylestring · enumOptional

Image style (DALL-E 3 only)

Default: vividPossible values:

response_formatstring · enumOptional

Format of the response data

Default: urlPossible values:

Responses

200

Successful response. For OpenAI models: image URL returned directly. For Leonardo models: taskId returned — poll POST /api/v1/getAsyncResponse to retrieve the image once ready.

application/json

createdintegerOptional

Unix timestamp of when the image was created

400

Bad Request - Invalid parameters

401

Unauthorized - Invalid API key

429

Rate Limit Exceeded

500

Internal Server Error

post

/api/v1/images/generations

HTTPcURLJavaScriptPython

POST /api/v1/images/generations HTTP/1.1
Host: api.fastrouter.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 127

{
  "model": "openai/gpt-image-1",
  "prompt": "A cute baby sea otter",
  "n": 1,
  "size": "1024x1024",
  "quality": "high",
  "output_format": "png"
}

GPT Image 1 (Latest)DALL-E 3DALL-E 2Transparent Background (GPT Image 1)Leonardo Phoenix (Async — poll getAsyncResponse)

{
  "created": 1704892800,
  "data": [
    {
      "url": "https://example.com/image.png",
      "revised_prompt": "A cute baby sea otter floating on its back in clear blue water"
    }
  ]
}