FLUX 3 Image Klein is the 5.6B-parameter open-weights model in Black Forest Labs' FLUX 3 Image family. Call the FLUX 3 Image Klein API with model flux-3-image-klein to generate or edit one image per request from text or up to 10 references.
Service Highlights

Image link valid for 72 hours
Transparent pricing with no hidden fees. Pay only for what you use.
* Actual costs are subject to final output.
The FLUX 3 Image Klein API lets you generate images from text, edit a reference or combine up to 10 images. Pick a resolution tier and aspect ratio, and control seed, steps, output format and safety tolerance.
FLUX 3 Image Klein is the smaller, faster open-weights model in the FLUX 3 Image family. Compare with FLUX 3 Image
Generation, editing and output controls available in the FLUX 3 Image Klein API
How creative, product and design teams use the FLUX 3 Image Klein model
Three steps from sign-up to your first FLUX 3 Image Klein API request
Sign up for free. One account gives you the FLUX 3 Image Klein API and every other model on APIMart.
Top up your balance. FLUX 3 Image Klein is billed per image by resolution tier, and the same balance works across all models.
Create an API key in the dashboard and send it as a Bearer token to POST /v1/images/generations with model flux-3-image-klein.
Call flux-3-image-klein with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint for the image URL.
Save your APIMart key in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
POST /v1/images/generations with model flux-3-image-klein, your prompt, resolution and aspect_ratio. Add seed, steps or output_format if needed, and image_urls to edit. The example.com URLs are placeholders: replace them with your own publicly accessible images or Base64 data. The task ID is in data[0].task_id.
Poll GET /v1/tasks/{task_id} until status is completed, then read the image URL from data.result.images[0].url[0]. APIMart keeps results for 72 hours, so download the images you want to keep.
See the FLUX 3 Image Klein API reference for every parameter, layout syntax and response field.
curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-3-image-klein",
"prompt": "Flat vector poster of a mountain sunrise, bold title text SUMMIT 2026, warm orange and teal palette",
"resolution": "1k",
"aspect_ratio": "16:9",
"output_format": "png"
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "flux-3-image-klein",
"prompt": "Flat vector poster of a mountain sunrise, bold title text SUMMIT 2026, warm orange and teal palette",
"resolution": "1k",
"aspect_ratio": "16:9",
"output_format": "png"
}
resp = requests.post(f"{API_BASE}/v1/images/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["images"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(3)
else:
raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-3-image-klein",
"prompt": "Turn the photo into a watercolor illustration and keep the composition and the people'\''s poses",
"resolution": "1k",
"aspect_ratio": "auto",
"image_urls": [
"https://example.com/reference.jpg"
]
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: flux-3-image-klein | Use flux-3-image-klein. |
prompt | string | Required | Default: — | Scene description for text-to-image, or edit instructions. Negative prompts are not supported; describe what you want to see. |
image_urls | string[] | Optional | Default: — | Up to 10 reference images as public HTTP(S) URLs or Base64. Omit for text-to-image; the first image is the one being edited. |
resolution | string | Optional | Default: 1k | 768sq, 1k, 1.5k, 2k or 4k (about 16 MP). Sets the price per image. |
aspect_ratio | string | Optional | Default: auto | One of 15 ratios from 21:9 to 9:21, or auto. Pixel sizes such as 1024x1024 return HTTP 400. |
seed | integer | Optional | Default: — | 0 to 4294967295. Reuse the same seed and settings to reproduce a result; omit for a random seed. |
steps | integer | Optional | Default: 16 | 1 to 16 denoising steps. Fewer steps are faster; the price does not change. |
output_format | string | Optional | Default: jpeg | jpeg or png (jpg equals jpeg). webp returns HTTP 400. |
safety_tolerance | integer | Optional | Default: 2 | 0 (strictest) to 4. |
One APIMart API key calls every FLUX model below. Image models are billed per image and FLUX 3 Video per second of video.
| Model | Best for | Output |
|---|---|---|
| FLUX 3 Image API | The FLUX 3 API for images: generation and editing with up to 10 references, search grounding and output up to 4K | 768sq to 4K (about 16 MP) |
| FLUX 3 Image Klein APIThis page | Lower-cost FLUX 3 images with seed, 1–16 steps and PNG or JPEG output | 768sq to 4K (about 16 MP) |
| FLUX 3 Video API | Text to video, 1–10 keyframes, video continuation and drafts, with synced audio | HD or FHD, 5–20 s |
| FLUX.2 API | Choosing between FLUX.2 Pro, Max and Flex on one page | 1–4 MP |
| FLUX.2 Pro API | Balanced quality and cost for production images, up to 8 references | 1–4 MP |
| FLUX.2 Max API | The highest-quality FLUX.2 output, up to 8 references | 1–4 MP |
| FLUX.2 Flex API | Adjustable steps and guidance for typography and layout-heavy designs | 1–4 MP |
| FLUX.1 Kontext API | Choosing between FLUX.1 Kontext Pro and Max on one page | About 1 MP |
| FLUX.1 Kontext Pro API | Context-aware edits at a fixed price per image, up to 4 references | About 1 MP |
| FLUX.1 Kontext Max API | Higher-quality Kontext edits with stronger prompt adherence | About 1 MP |
Common questions about the FLUX 3 Image Klein API: model, inputs, pricing, API key and task handling
The FLUX 3 Image Klein API gives you access to the 5.6B-parameter open-weights model in Black Forest Labs' FLUX 3 Image family. On APIMart, use model flux-3-image-klein for text-to-image, editing or multi-reference work. Each request returns one image.
Black Forest Labs released FLUX 3 Image Klein on October 15, 2026, as open weights and through its API, two weeks after FLUX 3 Image. On APIMart you call it with model flux-3-image-klein.
Klein is the smaller, faster and lower-cost model in the family. Through the API it also accepts seed, 1–16 steps and PNG or JPEG output. It does not support the grounding search option of FLUX 3 Image, and safety_tolerance uses the same 0–4 range.
image_urls accepts up to 10 HTTP(S) URLs or base64 images. The first image is the one being edited.
Choose a resolution tier — 768sq (768×768), 1k (~1 MP), 1.5k (~2 MP), 2k (~4 MP) or 4k (~16 MP) — with auto or one of 15 aspect ratios. width and height are not accepted at the moment; for a specific frame, combine aspect_ratio with resolution.
seed (0 to 4294967295) makes results reproducible with the same settings; leave it empty for a random seed. steps sets 1 to 16 denoising steps (default 16); fewer steps are faster and don't change the price. output_format returns jpeg (default) or png, and jpg is treated as jpeg.
Black Forest Labs publishes the Klein weights on Hugging Face under the license on its model card. According to Black Forest Labs, running the weights in a commercial product requires a commercial license from them. This page covers API access; for self-hosting terms, see Black Forest Labs' licensing page.
Each image is priced by its resolution tier only. Original prices on APIMart (October 2026): 768sq $0.008, 1k $0.009, 1.5k $0.011, 2k $0.014 and 4k $0.036. Aspect ratio, the number of references, steps, seed and output_format don't change the price, and text-to-image costs the same as editing. Gold members pay 20% less and Platinum and Diamond members save up to 28%; the final charge is the completed task's cost.
Sign up for APIMart, add credits to your balance, then create an API key on the API Keys page of the dashboard. Send it as a Bearer token with each FLUX 3 Image Klein API request; the same key works for every model on APIMart.
POST /v1/images/generations returns a task_id. Query GET /v1/tasks/{task_id} until the task completes or fails, then read the image URL from data.result.images[0].url[0]. APIMart keeps results for 72 hours, so download the images you want to keep.
FLUX 3 Image Klein, FLUX 3 Klein, FLUX.3 Klein and FLUX3 Klein are names for the same model, which you call on APIMart as flux-3-image-klein. FLUX.2 [klein], released by Black Forest Labs in January 2026, is a different, earlier open-weights model and is not served by this API. Klein Base, the 50-step FLUX 3 variant for fine-tuning, is released as open weights only and has no API.
No. APIMart has no free quota for the FLUX 3 Image Klein API; it is pay-as-you-go, starting at $0.008 per 768sq image at the original price, and failed tasks are refunded. If you want to run the model yourself, Black Forest Labs publishes the weights on Hugging Face under its own license.
Explore more models in the same category.

Mai Image 2.6
MAI-Image-2.6 is Microsoft's image model for text-to-image, single-image editing and composition with up to 5 reference images. It is available in high-quality and Flash versions, with 1K and 2K output and sharp text rendering.

Mai Image 2.6 Flash
MAI-Image-2.6 Flash is the Flash version of Microsoft MAI-Image-2.6 for text-to-image and image editing with up to 5 references, 1K/2K PNG output and optional Bing grounding, billed by actual token usage.

Flux 3 Image
FLUX 3 Image by Black Forest Labs handles text-to-image, single-image editing and generation with up to 10 reference images. It supports multiple aspect ratios and resolutions up to 4K, priced by resolution with no extra charge for references.

Nano banana 2.1
Nano Banana 2.1 is Google's Gemini image model for text-to-image generation and reference-image editing. It outputs 1K, 2K or 4K images in 14 aspect ratios and is available through official and Ext routes.
Guides, comparisons and pricing analysis from the APIMart blog.