> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # GPT Image 2.6 Sunburst > GPT Image 2.6 Sunburst: detail-oriented generation and consistent editing. Generate one PNG or edit up to 16 reference images. Defaults: low quality, 1K, opaque background, high complexity. ## Pricing The following prices include one output image and up to 1,024 UTF-8 bytes of prompt text, with no reference images. Prices are in platform tokens (USD shown in parentheses). All aspect ratios use the same tier price. | Quality | 1K | 2K | 4K | |---|---|---|---| | low | 1.92 ($0.0384) | 3.54 ($0.0708) | 5.65 ($0.1130) | | medium | 3.12 ($0.0624) | 5.99 ($0.1198) | 9.73 ($0.1946) | | high | 3.71 ($0.0742) | 7.19 ($0.1438) | 11.72 ($0.2344) | | xhigh | 6.33 ($0.1266) | 12.51 ($0.2502) | 20.58 ($0.4116) | | max | 13.82 ($0.2764) | 27.74 ($0.5548) | 45.88 ($0.9176) | - Each additional started 1,024 bytes of trimmed UTF-8 prompt text adds 0.33 tokens ($0.0066). - Each reference image adds 2.1 tokens ($0.042) per started 1,048,576 pixels. Round each image up separately, then sum. - Example: low / 1K, a short prompt and one 1024×1024 reference costs 4.02 tokens ($0.0804). These are fixed prepaid input and output tariffs, not metered model-token settlement. Use POST /api/v1/pricing/quote with the same prompt and image_list for a quote; image dimensions are checked before charging. Group discounts, if any, apply to the total. Failed jobs refund their charge. Transparency and complexity do not add a charge. This endpoint supports one PNG per request; auto quality, multiple outputs, custom pixel sizes, GIF, SVG, masks and markup are not supported. Returns an img_uuid; poll GET /api/v1/jobs/detail or use custom_callback_url. ## OpenAPI ````yaml api-reference/image-api/openapi-gpt-image-2-6-sunburst.json POST /api/v1/images/generations openapi: 3.1.0 info: title: GoEnhance API - GPT Image 2.6 Sunburst description: GPT Image 2.6 Sunburst version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/images/generations: post: tags: - ImageAPI summary: GPT Image 2.6 Sunburst description: >- GPT Image 2.6 Sunburst: detail-oriented generation and consistent editing. Generate one PNG or edit up to 16 reference images. Defaults: low quality, 1K, opaque background, high complexity. ## Pricing The following prices include one output image and up to 1,024 UTF-8 bytes of prompt text, with no reference images. Prices are in platform tokens (USD shown in parentheses). All aspect ratios use the same tier price. | Quality | 1K | 2K | 4K | |---|---|---|---| | low | 1.92 ($0.0384) | 3.54 ($0.0708) | 5.65 ($0.1130) | | medium | 3.12 ($0.0624) | 5.99 ($0.1198) | 9.73 ($0.1946) | | high | 3.71 ($0.0742) | 7.19 ($0.1438) | 11.72 ($0.2344) | | xhigh | 6.33 ($0.1266) | 12.51 ($0.2502) | 20.58 ($0.4116) | | max | 13.82 ($0.2764) | 27.74 ($0.5548) | 45.88 ($0.9176) | - Each additional started 1,024 bytes of trimmed UTF-8 prompt text adds 0.33 tokens ($0.0066). - Each reference image adds 2.1 tokens ($0.042) per started 1,048,576 pixels. Round each image up separately, then sum. - Example: low / 1K, a short prompt and one 1024×1024 reference costs 4.02 tokens ($0.0804). These are fixed prepaid input and output tariffs, not metered model-token settlement. Use POST /api/v1/pricing/quote with the same prompt and image_list for a quote; image dimensions are checked before charging. Group discounts, if any, apply to the total. Failed jobs refund their charge. Transparency and complexity do not add a charge. This endpoint supports one PNG per request; auto quality, multiple outputs, custom pixel sizes, GIF, SVG, masks and markup are not supported. Returns an img_uuid; poll GET /api/v1/jobs/detail or use custom_callback_url. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - gpt-image-2-6-sunburst description: Model name. Must be `gpt-image-2-6-sunburst`. prompt: type: string minLength: 1 maxLength: 32000 description: >- Generation or editing instructions, up to 32,000 characters. Input billing uses the UTF-8 byte length of the trimmed prompt. ratio: type: string enum: - auto - '1:1' - '1:2' - '2:1' - '1:3' - '3:1' - '2:3' - '3:2' - '3:4' - '4:3' - '4:5' - '5:4' - '9:16' - '16:9' - '9:21' - '21:9' default: auto description: >- Output ratio. With auto, text generation uses 1:1; reference editing follows the first image. image_size: type: string enum: - 1k - 2k - 4k default: 1k description: >- Resolution tier. Together with `quality` it decides the price. quality: type: string enum: - low - medium - high - xhigh - max default: low description: >- Rendering quality. Together with `image_size` it decides the price. background: type: string enum: - opaque - transparent - auto default: opaque description: >- `transparent` keeps the alpha channel. Does not affect pricing. image_list: type: array minItems: 0 maxItems: 16 items: type: object properties: url: type: string format: uri required: - url description: >- Up to 16 direct public image URLs. Each image must be readable, at most 50MB, and return HTTP 200 or 206 without redirects. Reference input is billed separately by its pixel dimensions. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback complexity: type: string enum: - low - medium - high default: high description: >- Planning intensity, independent of rendering quality. No additional charge. required: - model - prompt example: model: gpt-image-2-6-sunburst prompt: a glossy red sneaker, product shot, isolated subject image_size: 1k quality: low background: transparent responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string cost: type: number description: >- Tokens deducted for this request. This is the amount actually charged, so it already reflects any discount active on your account and can be lower than the listed price. Tokens are deducted when the task is accepted, and refunded automatically if the generation ends in failure. example: 5.82 required: - img_uuid - cost required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 cost: 5.82 '2': summary: Insufficient tokens value: code: 100 msg: tokens is not enough quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string required: - code - msg headers: {} deprecated: false security: [] ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.