> ## Documentation Index > Fetch the complete documentation index at: https://docs.linkmodel.ai/llms.txt > Use this file to discover all available pages before exploring further. # gpt-image-2.6-flare > GPT Image 2.6 Flare generates and edits images from text and image inputs. Use it for interactive image generation and editing workflows. ## OpenAPI ````yaml /openapi/image/gpt-image-2-6-flare.yaml post /images/generations openapi: 3.0.3 info: title: gpt-image-2.6-flare version: 1.0.0 description: >- GPT Image 2.6 Flare generates and edits images from text and image inputs. Use it for interactive image generation and editing workflows. x-linkmodel-sort-weight: 99202611059 servers: - url: https://api.linkmodel.ai/v1 description: Production security: - bearerAuth: [] tags: - name: OpenAI - name: image paths: /images/generations: post: tags: - OpenAI - image summary: gpt-image-2.6-flare description: > GPT Image 2.6 Flare generates and edits images from text and image inputs. Use it for interactive image generation and editing workflows. | | | | --- | --- | | **Provider** | OpenAI | | **Tasks** | text-to-image · image-to-image | | **Starting from** | 0.8125 USD / 1M tokens · Pricing details | ## Task lifecycle This endpoint creates an asynchronous task. Poll `GET /images/generations/{task_id}` with the returned `task_id` until the task reaches a terminal state. If the POST request times out or its result is uncertain, do not blindly retry it. The original request may already have created another task and billing order. Completed asset URLs are dynamically signed. Download or copy assets that must be retained instead of treating the URLs as permanent identifiers. operationId: gpt-image-2-6-flare requestBody: required: true content: application/json: schema: type: object properties: model: type: string enum: - gpt-image-2.6-flare default: gpt-image-2.6-flare description: >- Must be one of: gpt-image-2.6-flare. Defaults to `gpt-image-2.6-flare`. prompt: type: string minLength: 1 maxLength: 32000 description: Length must be between 1 and 32000. images: type: array minItems: 1 maxItems: 14 items: type: string format: url description: >- Temporary platform limit: 1-14 reference images. Full 16-image support awaits Aurora code fix. **Conditional limits:** - svg is text-to-image only; input images are not supported extends.edit.mask: type: string description: >- Optional URL or Base64 edit mask. Requires images, unsupported for gif/svg, and mutually exclusive with markup. **Conditional limits:** - mask requires at least one input image - gif and svg do not support mask extends.edit.markup: type: string description: >- Independent transparent PNG layer for the first input image. HTTPS URL or Base64 PNG selected by markup_is_base64. Requires images; mutually exclusive with mask. Server checks PNG, alpha, corrected dimensions, <=50 MB and <=16777216 pixels. **Conditional limits:** - markup requires at least one input image - svg does not support markup extends.edit.mask_is_base64: type: boolean description: >- Set true for Base64 mask; omit or false for URL. The typed edit DTO validates this flag. This field's allowed values depend on: extends.edit.mask. extends.edit.markup_is_base64: type: boolean description: >- Set true for Base64 PNG markup; omit or false for HTTPS URL. The typed edit DTO validates this flag. This field's allowed values depend on: extends.edit.markup. size: type: string enum: - 1008x1792 - 1024x1024 - 1024x1536 - 1280x960 - 1536x1024 - 1792x1008 - 2048x1152 - 960x1280 - auto default: auto description: >- Choose a preset size. GIF supports only auto. Defaults to `auto`. **Conditional limits:** - GIF currently supports only size=auto when size is provided quality: type: string enum: - auto - high - low - max - medium - xhigh description: >- Optional. Omit to use upstream behavior; no platform quality default. complexity: type: string enum: - high - low - medium description: >- Optional and independent of quality. Omit to use upstream default high; no platform default. max_images: type: integer default: 1 minimum: 1 maximum: 10 description: |- Must be between 1 and 10. Defaults to `1`. **Conditional limits:** - svg requires max_images=1 output_format: type: string enum: - gif - jpeg - png - webp default: png description: >- PNG/JPEG/WebP/GIF only. SVG is temporarily unavailable. Defaults to `png`. frame_count: type: integer minimum: 2 maximum: 16 description: >- GIF only, integer 2-16. Omit to use upstream default 9; explicit zero is invalid. **Conditional limits:** - frame_count is only supported with gif frame_duration_ms: type: integer minimum: 20 description: >- GIF only, integer >=20. Omit to use upstream default 200. Preserve the submitted integer without rounding. **Conditional limits:** - frame_duration_ms is only supported with gif output_compression: type: integer minimum: 0 maximum: 100 description: >- Integer 0-100, including 0. Only set for jpeg or webp; omit for png. **Conditional limits:** - output_compression is only supported with jpeg or webp background: type: string enum: - auto - opaque - transparent description: >- transparent requires png or webp. Omitted output_format uses png. **Conditional limits:** - transparent background requires png or webp moderation: type: string maxLength: 0 description: Length must be at most 0. required: - model - prompt responses: '200': description: >- Business response. `code=0` means the task was accepted; validation failures can return HTTP 200 with `code=400`. content: application/json: schema: oneOf: - type: object required: - code - data - msg properties: code: type: integer enum: - 0 example: 0 data: type: object required: - task_id properties: task_id: type: string description: Use this id to poll task status. example: aurora_abc123 order_id: type: string description: Billing order id. example: 019da9cf-d1db-78e1-ac23-526774d01193 status: type: string example: Processing price: type: number description: Charged amount in the model's pricing currency. example: 0.074 msg: type: string example: success request_id: type: string format: uuid example: 250b66dd-e1fb-4bb6-b5f6-c668efadc35d - type: object required: - code - msg properties: code: type: integer enum: - 400 example: 400 data: type: object example: {} msg: type: string example: model is required request_id: type: string format: uuid example: 96be7a7d-3e81-4916-a6b8-19b32773a693 '400': description: >- Malformed HTTP request rejected by the Gateway. Model and parameter validation may instead use HTTP 200 with business `code=400`. content: application/json: schema: type: object properties: code: type: integer example: 400 msg: type: string example: task_id is required request_id: type: string format: uuid example: 96be7a7d-3e81-4916-a6b8-19b32773a693 '401': description: Unauthorized — missing or invalid API key. content: application/json: schema: type: object properties: code: type: integer example: 401 data: type: object example: {} msg: type: string example: invalid api key request_id: type: string format: uuid example: bff4c295-c7da-4507-9708-4627cb6373ba '500': description: Internal error — task creation failed (e.g. insufficient balance). content: application/json: schema: type: object properties: code: type: integer example: 500 msg: type: string example: >- create task failed: billing: code=100601: insufficient balance request_id: type: string format: uuid example: 3409f6fb-fa9a-4534-b530-195b5f6f4e32 components: securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.