# GPT Image 2.5 Flare Text To Image ## --- TAB: API Reference --- POST https://api.newportai.com/api/async/gpt_image_2.5/flare/text_to_image

The GPT Image 2.5 Flare Text To Image API generates images from a text prompt using OpenAI's gpt-image-2.5-flare model. Flare is the faster GPT Image 2.5 variant, with image quality comparable to GPT Image 2 and lower latency.

Submit a POST request to the GPT Image 2.5 Flare Text To Image API to obtain a taskId.
Submit a POST request to the Polling API to retrieve the generated images.
Configure a Callback URL to receive results automatically on completion.

## Request Headers

Content-Type string Required

Enum: application/json

Authorization string Required

Bearer authentication token. Example: Bearer {{APIKey}}.

## Request Body

prompt string Required

The text description of the image to generate or edit. Maximum length is 4000 characters.

width integer Optional

The width of the generated image in pixels. Must be a multiple of 16 and no greater than 3840. The aspect ratio of the longer edge to the shorter edge must not exceed 3:1. Total pixels must be between 655,360 and 8,294,400. Outputs above 3,686,400 pixels (2560×1440) are experimental. Default value: 1024.

height integer Optional

The height of the generated image in pixels. Must be a multiple of 16 and no greater than 3840. The aspect ratio of the longer edge to the shorter edge must not exceed 3:1. Total pixels must be between 655,360 and 8,294,400. Default value: 1024.

quality string Optional

The quality level of the generated image. Enum: low, medium, high, xhigh, max. auto is not supported. Lower quality generates faster results with fewer credits. Default value: low.

n integer Optional

The number of images to generate in a single request. Must be between 1 and 10. Default value: 1.

## Response

code integer

Returns 0 for success, or a specific error code.

message string

Returns "success" or a descriptive error message.

data object

taskId string

The unique identifier for the task. Use this ID with the Polling API to retrieve the generated images.

## Errors

10192Illegal param

## Polling

Use the Polling API to retrieve the processing results.

## Callback

Alternatively, you can enable Callback to receive task results automatically upon completion.

### 0 Task Completed ```JSON { "code": 0, "message": "success", "data": { "images": [ { "imageUrl": "https://dreamapi-rs-aigc.newportai.com/dreamapi/o/2026-09-17/3d7e468edd69424086a3e50b44558611.jpg", "imageType": "png" } ], "task": { "taskId": "API-def1b03fdbde4bd4a00397e925d3fffb", "status": 3, "errorCode": 0, "reason": "ok", "taskType": "gpt_image_2.5/flare/text_to_image", "executionTime": 99604, "creditsConsumed": 2, "expire": 1789618658695 } } } ``` ### 0 Task Processing ```JSON { "code": 0, "message": "success", "data": { "task": { "taskId": "API-def1b03fdbde4bd4a00397e925d3fffb", "status": 2, "errorCode": 0, "reason": "ok", "taskType": "gpt_image_2.5/flare/text_to_image", "expire": 1789618658695 } } } ``` ## Code Examples ```curl curl -X POST 'https://api.newportai.com/api/async/gpt_image_2.5/flare/text_to_image' \ -H 'Content-Type: application/json' \ -H 'Authorization: Bearer {{key}}' \ -d '{ "prompt": "A sea otter sitting on a rock in sunlight, photorealistic", "width": 1024, "height": 1024, "quality": "low" }' ``` ```java HttpClient client = HttpClient.newHttpClient(); HttpRequest request = HttpRequest.newBuilder() .uri(URI.create("https://api.newportai.com/api/async/gpt_image_2.5/flare/text_to_image")) .header("Content-Type", "application/json") .header("Authorization", "Bearer {{key}}") .POST(HttpRequest.BodyPublishers.ofString("{\"prompt\":\"A sea otter sitting on a rock in sunlight, photorealistic\",\"width\":1024,\"height\":1024,\"quality\":\"low\"}")) .build(); HttpResponse res = client.send(request, HttpResponse.BodyHandlers.ofString()); ``` ```python import requests response = requests.post( "https://api.newportai.com/api/async/gpt_image_2.5/flare/text_to_image", headers={ "Content-Type": "application/json", "Authorization": "Bearer {{key}}" }, json={ "prompt": "A sea otter sitting on a rock in sunlight, photorealistic", "width": 1024, "height": 1024, "quality": "low" } ) print(response.json()) ``` ## Response Example ### 0 Successful ```JSON { "code": 0, "message": "success", "data": { "taskId": "API-def1b03fdbde4bd4a00397e925d3fffb" } } ``` ### 10192 Illegal param ```JSON { "code": 10192, "message": "Illegal param" } ``` ## --- TAB: Playground --- ## --- TAB: Pricing --- ## GPT Image 2.5 Billing Overview The cost of a request is calculated from output pixel count, quality level, and the number of images generated (`n`). `quality` does not include `auto`. | Factor | Dimension | Credit Multiplier | | ------ | --------- | ----------------- | | Size Tier 1 | pixels ≤ 1,048,576 (≤ 1024²) | Base 2 | | Size Tier 2 | 1,048,576 < pixels ≤ 4,194,304 (≤ 2048²) | Base 4 | | Size Tier 3 | pixels > 4,194,304 | Base 6 | | Quality: low | — | × 1 | | Quality: medium | — | × 2.5 | | Quality: high | — | × 9 | | Quality: xhigh | — | × 16 | | Quality: max | — | × 36 | | Image count (n) | — | × n | **Formula:** `credits = ceil(sizeBase × qualityMult) × n` ## Credit Examples | Model Version | Resolution | Quality | Credits per Image | | ------------- | ---------- | ------- | ----------------- | | GPT Image 2.5 | 1024×1024 | low | 2 | | GPT Image 2.5 | 1024×1024 | medium | 5 | | GPT Image 2.5 | 1024×1024 | high | 18 | | GPT Image 2.5 | 1024×1024 | xhigh | 32 | | GPT Image 2.5 | 1024×1024 | max | 72 | | GPT Image 2.5 | 1536×1024 | high | 36 | | GPT Image 2.5 | 2048×2048 | low | 4 | | GPT Image 2.5 | 2048×2048 | high | 36 | | GPT Image 2.5 | 2880×2880 | low | 6 | | GPT Image 2.5 | 2880×2880 | max | 216 | - [View Full Pricing Page](/pricing) - [Contact us](/contact)

GPT Image 2.5 Flare

Creation History