Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

GPT Image 2

POST /v1/tasks

All models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name gpt-image-2
Type Image generation (text-to-image)
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

HiAPI text-to-image model for accurate text rendering, complex prompts, and layout-heavy compositions.

Production guidance

Production guidance
  • For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
  • GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
  • Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Accurate text rendering

Useful for menus, signs, UI screenshots, infographics, and any image where text must stay readable.

promptresolution
Poster and layout work

Use one detailed prompt to describe headlines, supporting copy, subject placement, and whitespace.

promptaspect_ratioresolution
Product and commerce images

Generate clean product visuals with consistent composition for product pages and social covers.

promptaspect_ratio
Long-prompt creative drafts

Control subject, style, material, camera, composition, and text content in one complex prompt.

prompt
Multi-format delivery

Adapt one creative direction into square, landscape, portrait, or ultrawide placements.

aspect_ratioresolution

Request parameters

model string required

Fixed value gpt-image-2.

example gpt-image-2
input object required

Business parameters. GPT Image 2 model-specific configuration lives here.

prompt string required

Text prompt, up to 20000 characters.

aspect_ratio enum optional

Aspect ratio of the generated image.

default auto enum: auto1:13:22:34:33:45:44:516:99:162:11:23:11:321:99:21
resolution enum optional

Image resolution.

default 1K enum: 1K2K4K
callback object optional

Optional callback configuration. HiAPI sends a terminal notification to your service when the task finishes.

url string required

Required when callback is provided. HTTPS URL that receives the terminal task notification.

example https://your-domain.com/hiapi/callback
when enum optional

Callback trigger timing. Use final for terminal-state notifications.

default final enum: final

Example requests

Basic text-to-image

Minimum usable request with prompt, aspect ratio, and resolution.

Request body
{
  "model": "gpt-image-2",
  "input": {
    "prompt": "A clean product photo of a red apple on a white table",
    "aspect_ratio": "1:1",
    "resolution": "1K"
  }
}
Square product creative

For product pages, social avatars, and square cover placements.

Request body
{
  "model": "gpt-image-2",
  "input": {
    "prompt": "A premium skincare bottle on a white acrylic surface, soft studio lighting, clean commercial product photography",
    "aspect_ratio": "1:1",
    "resolution": "1K"
  }
}
Portrait poster with text

Put the required words, hierarchy, and layout constraints directly into the prompt.

Request body
{
  "model": "gpt-image-2",
  "input": {
    "prompt": "A vertical launch poster with the exact headline \"SUMMER DROP\", small subtitle \"New arrivals\", bright product photography, clean grid layout, generous whitespace",
    "aspect_ratio": "9:16",
    "resolution": "1K"
  }
}
Production request with callback

Recommended production shape: create the task, then wait for callback.url to receive the terminal notification.

Request body
{
  "model": "gpt-image-2",
  "input": {
    "prompt": "A clean product photo of a red apple on a white table",
    "aspect_ratio": "1:1",
    "resolution": "1K"
  },
  "callback": {
    "url": "https://your-domain.com/hiapi/callback",
    "when": "final"
  }
}

Getting the result

  1. The response returns a taskId immediately without waiting for generation to finish.
  2. In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
  3. When status=success, download the generated image from output[].url.
  4. When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

Next steps