FLUX.2 Klein 4B Pricing
This page lists the per-image price for the FLUX.2 Klein 4B distilled job types:
inference.flux-2.klein.4b.txt2img.v1andinference.flux-2.klein.4b.img2img.v1inference.flux-2.klein.txt2img.v1andinference.flux-2.klein.img2img.v1(the default aliases, currently routed to 4B distilled)
Every job is billed as a single product, chosen by the output resolution and the number of input images. Steps, aspect ratio, seed and style preset do not change the price.
Price per image
Section titled “Price per image”| Inputs | Up to 1 MP | Up to 2 MP | Up to 3 MP | Over 3 MP |
|---|---|---|---|---|
| Text-to-image (no inputs) | $0.0005 | $0.0027 | $0.0040 | $0.0059 |
| 1 input image | $0.0010 | $0.0027 | $0.0040 | $0.0059 |
| 2 input images | $0.0017 | $0.0034 | $0.0068 | $0.0084 |
| 3 input images | $0.0025 | $0.0065 | $0.0078 | $0.0084 |
| 4 input images | $0.0033 | $0.0065 | $0.0080 | $0.0109 |
| 5 input images | $0.0045 | $0.0068 | $0.0102 | $0.0109 |
| 6 input images | $0.0054 | $0.0088 | $0.0116 | $0.0132 |
| 7 input images | $0.0068 | $0.0092 | $0.0130 | $0.0145 |
| 8 input images | $0.0100 | $0.0108 | $0.0148 | $0.0170 |
How the buckets work
Section titled “How the buckets work”Output resolution is measured in megapixels (width × height):
| Bucket | Pixel range | Example sizes |
|---|---|---|
| Up to 1 MP | ≤ 1,048,576 | 1024×1024, 1280×768, 1344×768 |
| Up to 2 MP | ≤ 2,096,704 | 1440×1440, 1920×1080 |
| Up to 3 MP | ≤ 3,140,784 | 1728×1728, 2048×1440 |
| Over 3 MP | > 3,140,784 | 2048×2048, 1792×1792 |
Input images are counted from the images array on img2img jobs (1 to 8). The size of the input images does not affect the price; only the count and the output resolution do. txt2img jobs always fall in the no-inputs row.
Rules of thumb
Section titled “Rules of thumb”- A 1024×1024 text-to-image generation is $0.0005.
- Adding one input image at 1 MP doubles the price to $0.0010.
- Each additional input image adds roughly $0.001 at 1 MP.
- Going from 1 MP to over 3 MP output costs about 12× more for text-to-image.
- The most expensive combination, 8 input images at over 3 MP, is $0.0170.
Product codes
Section titled “Product codes”The product field returned by ?price=true follows the pattern inference-flux-2-klein[-N-in]-M-mp, where N is the number of input images (omitted for text-to-image) and M is the megapixel bucket (1 to 4). For example a 2-input job rendered at 1920×1080 bills as inference-flux-2-klein-2-in-2-mp.