FLUX 3 API
Black Forest Labs' newest image model — grounded, layout-aware, up to 4K
Try FLUX 3
Runs on your balance at the price shown on the button. Results are saved to your account.
Output image shape.
Output size tier: 1K ≈ 1 MP, 1.5K ≈ 2.25 MP, 2K ≈ 4 MP, 4K ≈ 16 MP.
Create a free account with Google or email — pay only for what you generate.
Your image will appear here
Write a prompt, pick your settings and hit Run. You only pay for successful generations.
What is FLUX 3?
FLUX 3 from Black Forest Labs generates and edits images up to 4K with web-grounded knowledge, layout control and up to 10 reference images, at a flat price per resolution tier.
The next FLUX
FLUX 3 is a big step over FLUX.2 in realism, text rendering and prompt understanding. It can look things up before it draws, so real products, places and styles come out right.
Edit, combine, lay out
Edit a single image, combine up to 10 references, or describe where things go — FLUX 3 follows layouts and keeps the parts you didn't mention untouched. Reference images are free.
FLUX 3 pricing
Pay per image. No subscription. Failed generations are refunded automatically.
| Tier | Official price | Cheaper Gen. | You save |
|---|---|---|---|
1K ≈1 MP | $0.042/img | −12% | |
1.5K ≈2.25 MP | $0.062/img | −12% | |
2K ≈4 MP | $0.088/img | −12% | |
4K ≈16 MP | $0.534/img | −12% |
- Official price: BFL API list price for FLUX 3 Image ($0.048 at 1K, $0.07 at 1.5K, $0.10 at 2K, $0.607 at 4K; reference images free). Prices verified 2026-10-16.
- Editing costs the same as generation; reference images are free.
Specifications
- Resolutions
- 1K · 1.5K · 2K · 4K
- Aspect ratios
- 1:1 · 4:5 · 3:4 · 2:3 · 9:16 · 1:2 · 9:21 · 5:4 · 4:3 · 3:2 · 16:9 · 2:1 · 21:9 · 7:5 · 5:7
- Edit inputs
- Up to 10 images (free)
- Released
- Oct 1, 2026
Use FLUX 3 via API
One request to start a job, one to fetch the result. Same shape for every model.
import os, time, requests
API = "https://cheapergen.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['CHEAPERGEN_API_KEY']}"}
# 1. Submit the job
job = requests.post(f"{API}/run/bfl/flux-3/text-to-image", headers=headers, json={
"prompt": "A rain-soaked night market in Taipei, steam rising from food stalls, neon signs in Chinese, 35mm photo",
"aspect_ratio": "1:1",
"resolution": "1K"
}).json()
# 2. Poll until it finishes (or pass "webhook_url" and skip polling)
while job["status"] in ("queued", "running"):
time.sleep(3)
job = requests.get(f"{API}/generations/{job['id']}", headers=headers).json()
print(job["status"], job["output"]["images"][0]["url"] if job["status"] == "succeeded" else job["error"])Example prompts
Hit “Try it” to load a prompt into the playground above.
A field guide page illustrating five North American songbirds with labeled names, watercolor on cream paper
Wide establishing shot of a futuristic Lagos skyline at dusk, maglev train crossing the lagoon
- Image Edit
Make the car in image 1 deep emerald green and move it to the coastal road in image 2
FLUX 3 FAQ
Related models

FLUX.2[pro]
Text → Image
Black Forest Labs' production image model — photoreal, fast, up to 4 MP

Nano BananaPro
Text → Image · Image Edit
Gemini 3 Pro Image — studio-grade generation and editing up to 4K

GPT Image2.5
Text → Image · Image Edit
OpenAI's top image model — precise edits, perfect text, up to 4K

FLUX3 Video
Text · Image → Video
FLUX goes video — 5–20 s clips with synced audio
FLUX 3 is developed by Black Forest Labs. Cheaper Gen. provides API access through official upstream endpoints and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI
