FLUX.2 Klein 4B

Model id flux-2-klein-4b · Black Forest Labs · image · 2 modes: text-to-image, image-to-image.

This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls get_model with the mode.

Text To Image

Mode text-to-image. Text to image.

Input

Field	Type	Required	Allowed	Description
`prompt`	string	Yes	up to 5,000 characters	Text prompt describing the image to generate or edit
`aspect_ratio`	string		`1:1`, `16:9`, `9:16`, `4:3`, `3:4`	Aspect ratio: 1:1, 16:9, 9:16, 4:3, or 3:4
`image_size`	string or object		`square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`, or	Image size preset or custom {width, height}. Overrides aspectRatio if both set.
`num_images`	integer		1 to 4	Number of images to generate (1-4). Defaults to 1.
`output_format`	string		`jpeg`, `png`, `webp`	Output image format. Defaults to png.
`seed`	integer			Seed for reproducible generation
`negative_prompt`	string		up to 2,000 characters	Negative prompt — what to avoid in the image
`guidance_scale`	number		0 to 20	Classifier-free guidance scale (0-20). Defaults to 5.
`num_inference_steps`	integer		4 to 50	Inference steps (4-50). Defaults to 28.

Pricing

0.4355 credits per megapixel. Fixed price: charged as estimated. For the exact price of a request, use estimate_generation.

Example

The arguments of generate_media:

{
  "model": "flux-2-klein-4b",
  "mode": "text-to-image",
  "input": {
    "prompt": "Studio photo of a ceramic mug with steam, soft morning light",
    "aspect_ratio": "1:1"
  }
}

Image To Image

Mode image-to-image. Edit up to 4 reference images, as the prompt says.

Input

Field	Type	Required	Allowed	Description
`prompt`	string	Yes	up to 5,000 characters	Text prompt describing the image to generate or edit
`aspect_ratio`	string		`1:1`, `16:9`, `9:16`, `4:3`, `3:4`	Aspect ratio: 1:1, 16:9, 9:16, 4:3, or 3:4
`image_size`	string or object		`square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`, or	Image size preset or custom {width, height}. Overrides aspectRatio if both set.
`num_images`	integer		1 to 4	Number of images to generate (1-4). Defaults to 1.
`output_format`	string		`jpeg`, `png`, `webp`	Output image format. Defaults to png.
`seed`	integer			Seed for reproducible generation
`num_inference_steps`	integer		4 to 8	Inference steps (4-8). Defaults to 4.
`references`	File list	Yes	1 to 4 items	References the output must follow. The kind of each one (image, video, audio) is read from the file; per-kind limits are in the mode’s `capabilities.references`.

References: up to 4: 4 images. Assets, URLs and elements are accepted.

Pricing

0.4839 credits per megapixel. Fixed price: charged as estimated. For the exact price of a request, use estimate_generation.

Example

The arguments of generate_media:

{
  "model": "flux-2-klein-4b",
  "mode": "image-to-image",
  "input": {
    "prompt": "Studio photo of a ceramic mug with steam, soft morning light, keeping the look of the reference",
    "aspect_ratio": "1:1",
    "references": [
      "asset_91a3c7e5b2d84f6a8e0c1b9d7f3a5e24"
    ]
  }
}

Models

Video

Image

Audio

FLUX.2 Klein 4B

Text To Image

Input

Pricing

Example

Image To Image

Input

Pricing

Example

​Text To Image

​Input

​Pricing

​Example

​Image To Image

​Input

​Pricing

​Example

Text To Image

Input

Pricing

Example

Image To Image

Input

Pricing

Example