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. The base-4b and base-9b variants bill at the same prices under their own product codes; the 9b distilled variant has its own table on the Pricing page.
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) | $0.003 | $0.0045 | $0.006 | $0.007 |
| 1 input image | $0.004 | $0.0055 | $0.007 | $0.008 |
| 2 input images | $0.005 | $0.0065 | $0.008 | $0.009 |
| 3 input images | $0.006 | $0.0075 | $0.009 | $0.01 |
| 4 input images | $0.007 | $0.0085 | $0.01 | $0.011 |
| 5 input images | $0.008 | $0.0095 | $0.011 | $0.012 |
| 6 input images | $0.009 | $0.0105 | $0.012 | $0.013 |
| 7 input images | $0.01 | $0.0115 | $0.013 | $0.014 |
| 8 input images | $0.011 | $0.0125 | $0.014 | $0.015 |
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 $0.003.
- Each input image adds $0.001 at any output resolution.
- Going from 1 MP to over 3 MP output adds $0.004 for text-to-image, a little over double the price.
- The most expensive combination, 8 input images at over 3 MP, is $0.015.
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. The base-4b and base-9b variants use inference-flux-2-klein-base-4b[-N-in]-M-mp and inference-flux-2-klein-base-9b[-N-in]-M-mp.