Skip to content

Imagen 4

Imagen 4 is a family of high-quality text-to-image generation models, offering standard, fast, and ultra variants that trade off generation speed and output quality.

POST https://llm.siraya.ai/v1/images/generations

Supported Models

Model ID Description
imagen-4.0-generate-001 Imagen 4 standard image generation
imagen-4-fast Imagen 4 Fast — optimized for faster generation
imagen-4-ultra Imagen 4 Ultra — optimized for the highest quality output
Authorization string Required
Your API Key (e.g., `Bearer `).

Body

model string Required
The ID of the model to use (e.g. imagen-4.0-generate-001).
prompt string Required
A text description of the desired image.
n integer Default: 1
The number of images to generate.
size string
The dimensions of the generated image. Mapped to aspect ratio internally. Supported values: 1024x1024 (1:1), 1792x1024 (16:9), 1024x1792 (9:16), 1280x896 (4:3), 896x1280 (3:4). Defaults to 1:1.
negative_prompt string
Negative prompt describing content to exclude from the generated image.
seed integer
Random seed for reproducibility. The same seed produces the same image. When set, watermark is automatically disabled.
output_format string Default: url
Result format (`url` or `b64_json`).
async boolean Default: false
When false, the request waits for generation to finish and returns the completed image. When true, it returns immediately with an image id while generation runs in the background. There is no status/poll endpoint for images — pass callbackUrl to receive the result. See Asynchronous generation.
callbackUrl string
Only used when async is true. A URL the router will POST to once generation completes (or fails). This is the only way to retrieve the result of an async image job.
extra_body object
Additional Imagen-specific parameters merged into the request. Keys are converted from snake_case to camelCase automatically. Supported keys include: person_generation, safety_setting, language, enhance_prompt (boolean), add_watermark (boolean), output_options (object with mimeType and compressionQuality), storage_uri. 
curl https://llm.siraya.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "imagen-4.0-generate-001",
    "n": 1,
    "prompt": "A child plays the guitar."
  }'

import requests

url = "https://llm.siraya.ai/v1/images/generations"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer <API_KEY>"
}
data = {
    "model": "imagen-4.0-generate-001",
    "n": 1,
    "prompt": "A child plays the guitar."
}

response = requests.post(url, headers=headers, json=data)
print(response.json())