> ## Documentation Index > Fetch the complete documentation index at: https://www.krea.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # GPT Image 2.6 Sunburst > GPT Image 2.6, optimized for speed. > [accordion] Deprecated request aliases > > These aliases are accepted for compatibility only and are not shown in the request schema. > > | Deprecated | Use instead | Accepted until | > | - | - | - | > | `imageUrls` | `image_urls` | 2026-06-19 | > | `style_images` | `image_urls` | 2026-09-11 | ## OpenAPI ````yaml https://api.krea.ai/openapi.json post /generate/image/openai/gpt-image-2.6-sunburst openapi: 3.1.0 info: title: Krea API version: v1 servers: - url: https://api.krea.ai description: Krea API security: - bearerAuth: [] tags: - name: General description: Core API operations including job management and billing information - name: Krea description: Krea-owned generation models including Krea 2 - name: Assets description: >- Asset management endpoints for uploading and managing images, videos, audio files, and 3D models - name: Styles description: Style (LoRA) generation and management endpoints - name: Node Apps description: Executing custom node apps built in our nodes tool - name: Image description: Image generation endpoints - name: Image Enhance description: Image enhance endpoints - name: Video description: Video generation endpoints - name: Video Enhance description: Video enhance and upscale endpoints - name: 3D description: 3D model generation endpoints - name: Audio description: Speech and audio generation endpoints - name: Usage description: Workspace usage reporting - name: Agent description: Krea Agent sessions - name: Utilities description: Miscellaneous utility endpoints paths: /generate/image/openai/gpt-image-2.6-sunburst: post: tags: - Image summary: GPT Image 2.6 Sunburst description: GPT Image 2.6, optimized for speed. parameters: - name: X-Webhook-URL in: header required: false schema: type: string format: uri description: >- URL to receive a POST request when the job completes. The webhook will receive the job data including results. Deliveries are signed with Ed25519 (EdDSA); verify them with the keys at https://api.krea.ai/.well-known/jwks.json (see X-Krea-Webhook-* headers). Treat requests without these headers as unauthenticated. requestBody: content: application/json: example: prompt: Hobbiton, just as Tolkien sketched, in hues of emerald. aspect_ratio: '16:9' resolution: 1K schema: type: object properties: prompt: type: string minLength: 1 quality: default: high type: string enum: - low - medium - high - xhigh - max image_urls: description: Image prompts to use for the generation. maxItems: 10 type: array items: type: string maxLength: 1024 format: uri description: >- Can be an external URL, base64 data URI, or uploaded asset URL. aspect_ratio: type: string enum: - '16:9' - '2:1' - '3:2' - '4:3' - '1:1' - '3:4' - '2:3' - '1:2' - '9:16' description: >- Aspect ratio. One of: 16:9, 2:1, 3:2, 4:3, 1:1, 3:4, 2:3, 1:2, 9:16. resolution: type: string enum: - 1K - 2K - 4K description: 'Resolution scale. One of: 1K, 2K, 4K.' output_format: description: >- File format of the result: `png` (default), `svg` for a sanitized vector document, or `gif` for a looping animation. SVG and GIF support text-to-image only, so they cannot be combined with `image_urls`. type: string enum: - png - svg - gif frame_count: description: >- GIF only: number of frames, 2–16 (default 9). The aspect ratio sets each frame's shape; frames are scaled to at most 960 px on the longest edge so the animation fits the model's size limits, and `resolution` does not apply. type: integer minimum: 2 maximum: 16 frame_duration_ms: description: >- GIF only: milliseconds each frame shows, 20–2000, rounded to 10 (default 200). type: integer minimum: 20 maximum: 2000 required: - prompt - aspect_ratio - resolution additionalProperties: false responses: '200': description: >- The resulting job data. This will be returned in a pending state until the job is completed. See [`/jobs/{id}`](#tag/default/get/jobs/{id}) for retrieving the results. content: application/json: schema: type: object properties: job_id: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ status: type: string enum: - backlogged - queued - scheduled - processing - sampling - intermediate-complete - completed - failed - cancelled created_at: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ completed_at: type: 'null' result: type: 'null' error: type: object properties: code: type: string description: >- Why the job failed. `invalid_request` means the request broke a rule, such as a media limit or a file that cannot be read or downloaded. `validation_failed` means a value is outside its parameter's schema. For both codes, change the parameter named in `param` before you resubmit. Other codes are `content_policy`, `model_unavailable`, `insufficient_balance`, `timeout`, `auto_cancelled`, `provider_error`, `internal`, and `node_app_node_failed`. Treat an unknown code as `internal`. message: type: string param: description: >- The request parameter to change, present with `invalid_request` and `validation_failed`. type: string required: - code additionalProperties: false progress: anyOf: - type: number minimum: 0 maximum: 1 - type: 'null' required: - job_id - status - created_at - completed_at - result additionalProperties: false '400': description: The request body is invalid. content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false '401': description: You are not authenticated. content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false '402': description: You have run out of credits. content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false '429': description: You have reached the maximum number of concurrent jobs. content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false components: securitySchemes: bearerAuth: scheme: bearer bearerFormat: Bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.