Imagen 4 Ultra API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	imagen4-ultra
Type	Image generation (text-to-image)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

Imagen 4 Ultra text-to-image API for high-quality images from detailed prompts.

Production guidance

Pass callback.url at the top level in production to reduce polling.
Poll GET /v1/tasks/:id for local debugging.

Best suited for

Deliver high-detail finals

Product macros, portraits and material close-ups; 1:1 by default.

promptaspect_ratio

Fix the seed to fine-tune the final

Fix the string seed (up to 500 characters) and adjust only material, light and depth of field.

seednegative_prompt

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "imagen4-ultra",
  "input": {
    "prompt": "Create a macro product photo of a luxury watch. Show the brushed steel case and the dial markings resting on deep green silk. Keep the watch centered in a square frame with the silk folds visible. Controlled studio lighting with crisp reflections; the result should look like a premium catalog image. Do not add logos or text.",
    "aspect_ratio": "1:1"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "imagen4-ultra",
  "input": {
    "prompt": "Create a macro product photo of a luxury watch. Show the brushed steel case and the dial markings resting on deep green silk. Keep the watch centered in a square frame with the silk folds visible. Controlled studio lighting with crisp reflections; the result should look like a premium catalog image. Do not add logos or text.",
    "aspect_ratio": "1:1"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "imagen4-ultra",
  "input": {
    "prompt": "Create a macro product photo of a luxury watch. Show the brushed steel case and the dial markings resting on deep green silk. Keep the watch centered in a square frame with the silk folds visible. Controlled studio lighting with crisp reflections; the result should look like a premium catalog image. Do not add logos or text.",
    "aspect_ratio": "1:1"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value imagen4-ultra.

example imagen4-ultra

input object required

Put model parameters inside input.

prompt string required

Required image description, up to 5,000 characters.

aspect_ratio enum required

Output aspect ratio.

default 1:1 enum: 1:116:99:163:44:3auto

negative_prompt string optional

Optional negative prompt, up to 5,000 characters.

seed string optional

Optional string, up to 500 characters.

callback object optional

Optional terminal task callback.

url string required

HTTPS endpoint that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback timing; keep final.

default final enum: final

Example requests

Shoot a watch material macro

A four-part prompt: the task, what to show, what to keep, and texture and limits.

Request body

{
  "model": "imagen4-ultra",
  "input": {
    "prompt": "Create a macro product photo of a luxury watch. Show the brushed steel case and the dial markings resting on deep green silk. Keep the watch centered in a square frame with the silk folds visible. Controlled studio lighting with crisp reflections; the result should look like a premium catalog image. Do not add logos or text.",
    "aspect_ratio": "1:1"
  }
}

Create a high-detail aerial landscape

The prompt as submitted for an example on the model page.

Request body

{
  "model": "imagen4-ultra",
  "input": {
    "prompt": "Aerial view of a winding river through autumn forest; ultra high detail landscape",
    "aspect_ratio": "16:9"
  }
}

Getting the result

The response returns a taskId immediately.
Wait for callback.url or poll GET /v1/tasks/:id.
When status=success, download output[].url.

FAQ

Does it accept reference images?

No. Imagen 4 Ultra generates from text only.

What type is seed?

An optional string of up to 500 characters.

When should I use Ultra?

When a finished image is due. Explore with imagen4-fast first, then switch to imagen4-ultra.

How do I retrieve the result?

Use the taskId. The response returns it right away; download output[].url after the task succeeds.

How can I confirm the cost?

The task record is final. Check the pricing page and Playground estimate before submitting. View pricing