Google

Imagen 4

imagen-4.0

Google's text-to-image series, focused on in-image text rendering and complex lighting, offering Fast, Standard, and Ultra tiers that trade off quality against cost

imagen-4.0 imagen-4.0-fast imagen-4.0-ultra

Try imagen-4.0

Input

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

imagen-4.0 per image

Unit Price	$0.060

Positioning Overview

imagen-4.0 is the standard-tier text-to-image model in the Imagen 4 series. It accepts only text prompts and is suited to everyday generation needs that balance image quality against generation cost. It supports prompts up to 5,000 characters and negative prompts up to 500 characters, lets you specify an aspect ratio from 1:1, 16:9, 9:16, 3:4, 4:3, and auto, and lets you use a seed to make the same configuration reproducible. Compared with the Fast version, it is better suited to batch generation that requires consistent output quality but does not chase extreme detail. Developers can call it through the unified HiAPI.ai interface and plug it into their own generation workflows.

Key Highlights

Targeted improvements to text rendering within images — research shows this series has noticeably improved in-image text generation over the previous generation, making it suitable for design drafts that need to carry readable text in the frame.
Supports negative prompts and seed reproducibility — use negative_prompt to exclude unwanted elements, and use seed to fix and reproduce the same generation configuration, making iteration and regression verification easy.
Six aspect ratios specified directly — aspect_ratio covers square, landscape, portrait, as well as 3:4 and 4:3, and also offers auto selection, saving you post-processing crops.
Clear standard-tier positioning — the same series also has Fast and Ultra tiers; the standard version is a good default choice for everyday batch generation, with an upgrade path when final-output requirements grow.

Capabilities

Text-to-image generation: Enter a text description and receive an image. Prompts can be up to 5,000 characters, enough to carry fairly complete descriptions of subject, style, and composition.

Generation control parameters: negative_prompt declares elements to exclude, and seed reproduces the same result. Together they make the generation process adjustable and traceable.

Aspect ratio adaptation: Output ratios can be chosen among square, landscape, portrait, 4:3, and 3:4, or left to auto, which decides composition ratio based on prompt content.

Readable text presentation: When prompt content describes on-image text, the model handles text rendering better than the previous generation, but final glyphs still need manual verification.

Use Cases

Social media visuals for marketing teams — describe the scene in text based on the campaign theme, choose landscape or portrait ratios, and batch-produce visuals for direct publishing to content channels.
Poster and presentation sketches for designers — use prompts containing headline copy to generate poster or cover drafts with text, serving as visual direction references before layout.
Product concept images that need a fixed style — fix the seed and aspect ratio, repeatedly fine-tune prompts around the same product, and produce style-consistent concept images for solution reviews.
Automated integration into generation workflows — make text-to-image a step in the pipeline, with programs passing prompts and ratio parameters to batch-produce assets that then enter downstream review.

Limitations and Selection Advice

Input supports text only; it cannot edit or inpaint based on an existing image. Parameters include only prompt, negative prompt, aspect ratio, and seed, with no finer controls such as steps or style strength. Although text in images is improved over the previous generation, it is still recommended to verify each image before delivery. If you need stronger prompt adherence and detail, consider the Ultra tier in the same series; if generation speed matters more, choose the Fast tier. This model is not suitable for scenarios that require image input or fine-grained local control.

What's new

View changelog →

Feature change Imagen 4 model IDs are now imagen-4.0… Oct 21, 2026
New model Added Google Imagen 4 image-generation docs Oct 14, 2026

Frequently asked questions

View all FAQs →

What is Imagen 4 good for?

Everyday product, lifestyle and content images. Describe the subject, scene, material and light to get an image ready for review, for product heroes, campaign drafts and editorial illustrations.
Which aspect ratios does Imagen 4 support?

Six: 1:1, 16:9, 9:16, 3:4, 4:3 and auto. aspect_ratio is required; the Playground on this page defaults to 16:9.
How long can the prompt be?

Up to 5,000 characters. prompt is required; order it as subject, scene, material, light and text.
Can I exclude things I don't want?

Yes, with negative_prompt. It is optional, up to 5,000 characters, and works for extra text, watermarks or a cluttered background.

Create a generation task

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

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: imagen-4.0

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for imagen-4.0 and route default — see the parameter table below.

seedstringOptionalmaxLength 500

Optional random seed for reproducibility of the generated result; passed in as a string.

promptstringRequiredminLength 1maxLength 5000

Text description of the image to generate, which is the primary input for image generation.

aspect_ratiostringRequired

Controls the aspect ratio of the output image, specified as a string.

Options:1:116:99:163:44:3auto

negative_promptstringOptionalmaxLength 5000

Describes elements to exclude from the generated image, passed in as text.

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "imagen-4.0",
  "input": {
    "prompt": "…",
    "aspect_ratio": "…"
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "imagen-4.0",
    input: {
      "prompt": "…",
      "aspect_ratio": "…"
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "imagen-4.0",
        "input": {
          "prompt": "…",
          "aspect_ratio": "…"
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}