GPT Image 2 is OpenAI's text-to-image model. This page covers HiAPI's stable gpt-image-2/text-to-image model through the unified asynchronous task API for posters, knowledge cards, product visuals, and images with explicit text and layout requirements.

Is GPT Image 2 the same as GPT Image 2.0?

On HiAPI, the official product name is GPT Image 2 and its API model IDs do not contain “2.0.” GPT Image 2.0 is a common search shorthand rather than a separate HiAPI model. Use the exact model ID shown on the model page and in the API docs when integrating.

Which endpoint and model ID does the GPT Image 2 API use?

Send POST requests to /v1/tasks, set model to gpt-image-2/text-to-image, and pass prompt, aspect_ratio, and resolution in input. The create response returns a taskId; retrieve the final image through task polling or a callback.

How do I use GPT Image 2?

Start in the Playground by describing the subject, scene, layout, and any exact text, then choose an aspect ratio and resolution. After validating the result, create an asynchronous API task with the same model ID. Use the GPT Image 2 API docs for all parameters, callbacks, task retrieval, and errors.

Which resolutions and aspect ratios does GPT Image 2 support?

The standard route supports 1K, 2K, and 4K plus 16 aspect ratios including auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, and 9:16. Some combinations are restricted: auto is 1K only and 1:1 does not support 4K, so check the parameter docs before submitting.

How is the GPT Image 2 API priced?

HiAPI's stable route uses resolution-based per-image pricing. This model page shows the starting price; use the dedicated GPT Image 2 API pricing and cost per image guide for resolution details, batch budgets, and cost explanations, and confirm production budgets against live pricing.

Back to Models

GPT Image 2

New

by OpenAIImage

Use the GPT Image 2 text-to-image model on HiAPI for posters, knowledge cards, product visuals, and other generated images. Try it online or integrate the async API.

Pricing

Standard Usage

60 Credits/ image

Use GPT Image 2 in your AI Agent

Install the HiAPI GPT Image 2 Skill to call the model from OpenClaw, Codex, Claude Code, OpenCode, and similar agents.

View Skill docs View GitHub

Input

Prompt *0 / 20000

Aspect Ratio

Resolution

Quality

Estimated cost60 Credits / image1K

Output

Ready for generation

Configure your parameters and click "Run" to see the output here.

--GPU-T4

Image generation examples

From knowledge cards to commercial posters

These existing prompt-library examples cover structured information, technical visuals, poster layouts, and character design. Open any image for a larger view, copy the original prompt when available, or continue to the full prompt recipe.

Choose an adjacent model by generation task, reference-image editing, or visual style.

Image editing

GPT Image 2 Image-to-Image

Use reference images for edits, restyling, and controlled visual changes.

Generation and editing

Nano Banana 2

A neighboring multimodal image model for fast iterative creative workflows.

About GPT Image 2

GPT Image 2 is OpenAI's text-to-image model for text-heavy posters, structured knowledge cards, product visuals, character design, and complex prompts with explicit layout and object relationships.

The Playground, specifications, and quickstart on this page all use the stable text-to-image model ID gpt-image-2/text-to-image. The aspect ratios, resolutions, pricing, and API examples shown here apply to that model ID.

For resolution prices, batch budgets, and failed-task billing details, see GPT Image 2 API pricing and cost per image.

Provider: OpenAI
Default task: Text-to-image
Output resolutions: 1K / 2K / 4K
Endpoint: POST /v1/tasks

Model specifications

These specifications describe the current stable HiAPI text-to-image route. Other routes can use different parameter combinations.

Model ID: gpt-image-2/text-to-image
Output resolution: 1K2K4K
Aspect ratios: auto1:13:22:34:33:45:44:516:99:162:11:23:11:321:99:21
Prompt length: Up to 20,000 characters
Task protocol: POST /v1/tasksAsync
Pricing by resolution: 1K60 Credits / image2K80 Credits / image4K120 Credits / image

Combination limits: auto supports 1K only; 1:1 does not support 4K; and 5:4, 4:5, 3:1, 1:3, and 9:21 are limited to 1K.

How to use GPT Image 2

This page keeps the path from prompt validation to the first API call short. The API docs own full parameters, route differences, callbacks, and task retrieval.

Create: subject, scene, style

Constrain: copy, position, hierarchy

Define the image and exact text

Describe the subject, setting, composition, and style. Put exact copy in quotation marks and specify its hierarchy and placement.

GPT Image 2 API quickstart

This is the minimum asynchronous request for the stable text-to-image route. Use the API docs for callbacks, task retrieval, route parameters, and error handling.

Endpoint: POST /v1/tasks
Model ID: gpt-image-2/text-to-image

cURL

curl --request POST 'https://api.hiapi.ai/v1/tasks' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-image-2/text-to-image",
    "input": {
      "prompt": "A clean product photo of a red apple on a white table",
      "aspect_ratio": "1:1",
      "resolution": "1K"
    }
  }'

The create request returns a taskId immediately while the image is generated asynchronously.

View full GPT Image 2 API documentation Get an API key