> ## Documentation Index > Fetch the complete documentation index at: https://docs.ttapi.io/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Send API requests to https://api.ttapi.io with the TT-API-KEY header. Midjourney account hosting uses https://hold.ttapi.io. Claude Code uses https://cc.ttapi.io. > Most generation endpoints are asynchronous. The submit response returns a job id. Poll that product's fetch endpoint, or pass a webhook on the submit request. A fetch call does not start a new generation. > 1 USD = 100 quota. Check the pricing page for that product before estimating cost. > This file lists the English docs. Follow every /_llms/ link recursively for the API reference, Chinese, and Russian. Open a page's .md URL for the endpoint schema. # Generate an image with FLUX 3 Image Klein > Use the FLUX 3 Image Klein API to generate or edit images. It belongs to the same FLUX 3 image family, runs smaller and faster, and accepts exact size, seed, and sampling steps. ## OpenAPI ````yaml openapi/en/flux.json POST /bfl/v1/flux-3-image-klein openapi: 3.1.0 info: title: Flux API DOCS version: 1.0.0 description: >- TTAPI Flux API service, currently integrating the most advanced video large model Sora2. servers: - url: https://api.ttapi.io security: [] paths: /bfl/v1/flux-3-image-klein: post: description: >- Generate or edit images with FLUX 3 Image Klein. It is in the same FLUX 3 image family and supports text-to-image, edits with up to 10 reference images, multi-image composition, and bounding boxes in the prompt. Klein also accepts exact width and height, a seed, an output format, and a step count. The endpoint expands the prompt before generation. Passing `width` and `height` together overrides `aspect_ratio` and `resolution`. Official docs requestBody: required: true content: application/json: schema: type: object properties: prompt: type: string description: >- Free-form prompt describing the image. Without `images`, it generates a new image from the prompt. With reference images, state what to change and refer to them in order as image 1 and image 2. Bounding boxes can be appended to the prompt, using a 0 to 1000 grid as `[top, left, bottom, right]`. images: oneOf: - type: string - type: array items: type: string minItems: 1 maxItems: 10 description: >- Optional reference images. Omit them for text-to-image. When present, the prompt edits, restyles, or combines them. Each item is an http(s) URL or base64, 1 to 10 total. The first image is the picture being edited and sets the default output size. aspect_ratio: type: string description: >- Output aspect ratio. With `auto`, a reference image uses the first image's exact ratio; without references, a ratio is chosen from the prompt, otherwise `16:9`. Ignored when `width` and `height` are both set. default: auto enum: - auto - '21:9' - '2:1' - '16:9' - '3:2' - '7:5' - '4:3' - '5:4' - '1:1' - '4:5' - '3:4' - '5:7' - '2:3' - '9:16' - '1:2' - '9:21' resolution: type: string description: >- Resolution tier: `768sq`, `1k`, `1.5k`, `2k`, or `4k`. Omitted text-to-image requests use `1k`. With a reference image and this field omitted, the first image's own size is used, or the nearest tier when `aspect_ratio` is also set. Ignored when `width` and `height` are both set. enum: - 768sq - 1k - 1.5k - 2k - 4k width: type: integer description: >- Output width in pixels, from 64 to 6256. Must be sent together with `height`, and overrides `aspect_ratio` and `resolution`. Width times height must not exceed 16822272 pixels. minimum: 64 maximum: 6256 height: type: integer description: >- Output height in pixels, from 64 to 6256. Must be sent together with `width`. Width times height must not exceed 16822272 pixels. minimum: 64 maximum: 6256 seed: type: integer description: >- Seed used to reproduce a result. Random when omitted. Range: 0 to 4294967295. minimum: 0 maximum: 4294967295 safety_tolerance: type: integer description: >- Harm moderation tolerance from 0 to 7, with 0 the strictest. Default is 2. The route and organization determine the approved maximum and the ceiling for each category. minimum: 0 maximum: 7 default: 2 output_format: type: string description: Output image format. default: jpeg enum: - jpeg - png steps: type: integer description: 'Denoising steps. Default is 16. Range: 1 to 16.' minimum: 1 maximum: 16 default: 16 webhook_url: type: string description: >- Async callback URL. The initial response returns `jobId`. Use this callback or the [Flux fetch API](/api/en/flux/fetch) to get the final image. required: - prompt responses: '200': $ref: '#/components/responses/SuccessResponse' '400': $ref: '#/components/responses/400Response' '401': $ref: '#/components/responses/401Response' security: - CustomApiKey: [] components: responses: SuccessResponse: description: Request successful content: application/json: schema: type: object properties: status: type: string example: SUCCESS message: type: string example: success data: type: object example: jobId: jobId required: - status - message - data 400Response: description: Parameter error content: application/json: schema: type: object properties: status: type: string example: FAILED message: type: string example: '"prompt" cannot be empty.' data: type: object required: - status - message 401Response: description: Authorization failed content: application/json: schema: type: object properties: status: type: string example: FAILED message: type: string example: Wrong TT-API-KEY or email is not activated. required: - status - message securitySchemes: CustomApiKey: type: apiKey in: header name: TT-API-KEY description: >- You can obtain your API key from the TTAPI Dashboard. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.