Black Forest Labs

FLUX.2 Klein 9B

flux-2-klein-9b/text-to-image

A 9-billion-parameter rectified-flow image model, step-distilled to 4 steps, unifying text-to-image and single/multi-reference image editing in a compact architecture, aimed at low-latency real-time generation scenarios

flux-2-klein-9b/image-to-image flux-2-klein-9b/text-to-image

Try flux-2-klein-9b/text-to-image

Input

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

flux-2-klein-9b/text-to-image per image

Unit Price	$0.00858

Overview

The text-to-image-only pipeline of FLUX.2 klein 9B, released by Black Forest Labs, focuses on balancing quality and latency. It generates images directly from text prompts, supports aspect ratios from 1:1 to 16:9, and offers three output formats: jpeg, png, and webp; inference steps can be set between 4 and 8, and generation can be completed with the default 4 steps. It is well suited for latency-sensitive batch content production, marketing visuals, and visual exploration during the prototyping stage, and developers can integrate it through the unified API on HiAPI.ai.

Key Highlights

Low-step inference for latency-sensitive scenarios — The step-distillation design enables image generation in just 4 steps, with the parameter adjustable between 4 and 8 steps, making it easy to trade off between speed and detail.
Fixed seed support for reproducible generation — A seed parameter is provided; the same prompt and seed combination can reproduce results, which facilitates regression testing and version comparison.
Output parameters aligned with engineering pipelines — Aspect ratios cover the commonly used compositions 1:1, 4:3, 3:4, 16:9, and 9:16, and outputs can be selected directly as jpeg, png, or webp, eliminating the need for additional transcoding.

Capabilities

Text-to-image generation: Pass in a text prompt to obtain the corresponding image, with no required reference image; only prompt is needed, and all other parameters have default values, keeping integration costs low.

Inference step and seed control: num_inference_steps can be adjusted between 4 and 8 to change generation detail, while seed locks randomness, making it suitable for evaluation and debugging that require stable reproduction.

Composition ratios and output formats: aspect_ratio covers five ratios across portrait, landscape, and square formats, and output_format supports jpeg, png, and webp, so generated results can directly match page placements and storage requirements.

Use Cases

Batch image production for content teams — Use product or topic descriptions as input to generate images in batches, specify the ratio and output format, and use them directly for articles, landing pages, and social media assets.
Visual draft exploration for product prototypes — Use short prompts to quickly produce multiple composition options, and reproduce candidate styles with fixed seeds for direction screening before design review.
Integration into real-time or high-frequency image generation applications — For latency-sensitive online features, generate images with the default 4-step inference and adjust the number of steps as needed to control quality and processing time.

Limitations and Selection Advice

This pipeline generates images from plain text only and does not accept reference images. When editing existing images or changing styles is required, choose the image-to-image pipeline in the same series. Inference steps support only 4 to 8 steps, not finer long-sampling adjustments; apart from prompt, there are no parameters such as negative prompts. The model card imposes constraints on out-of-scope use, so check the original license text before commercial use. If a task requires other modalities such as video or audio output, this model is not suitable.

Frequently asked questions

View all FAQs →

How many references does FLUX.2 [klein] 9B Image to Image accept?

It currently accepts one JPEG, PNG, or WebP reference. image_urls must contain exactly one public image URL.
Which editing tasks is it best for?

It is suited to product cleanup, background replacement, in-image text rewriting, color changes, and commercial edits that preserve subject and camera.
How do I set inference steps?

num_inference_steps accepts integers from 4 to 8 and defaults to 4. The current price does not change with the step count.
Which ratios and formats are supported?

Ratios: 1:1, 4:3, 3:4, 16:9, and 9:16. Formats: JPEG, PNG, and WebP.

Create a generation task

POST https://api.hiapi.ai/v1/tasks

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: flux-2-klein-9b/text-to-image

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for flux-2-klein-9b/text-to-image and route default — see the parameter table below.

seedintegerOptional

Random seed used for reproducibility of the generated result; takes an integer.

promptstringRequired

Text prompt used for image generation; takes a string.

aspect_ratiostringOptionalDefault: "4:3"

Aspect ratio of the generated image; takes a string. Default is 4:3.

Options:1:14:33:416:99:16

output_formatstringOptionalDefault: "png"

Output format of the generated image; takes a string. Default is png.

Options:jpegpngwebp

num_inference_stepsintegerOptionalDefault: 4min 4max 8

Number of inference steps; takes an integer between 4 and 8. Default is 4.

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "flux-2-klein-9b/text-to-image",
  "input": {
    "prompt": "…",
    "aspect_ratio": "4:3",
    "output_format": "png",
    "num_inference_steps": 4
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "flux-2-klein-9b/text-to-image",
    input: {
      "prompt": "…",
      "aspect_ratio": "4:3",
      "output_format": "png",
      "num_inference_steps": 4
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "flux-2-klein-9b/text-to-image",
        "input": {
          "prompt": "…",
          "aspect_ratio": "4:3",
          "output_format": "png",
          "num_inference_steps": 4
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}