FLUX.3AI image generator
Black Forest Labs' newest image model, released on 2026-10-01, at 1K. On Leap, it sits beside 174 other models in one studio.
- Text to image
- 14 aspect ratios
- No subscription
- Every top model, one account
- Pay per run, priced before it starts

AI image generator
FLUX.3 at a glance
FLUX.3 is an image model from Black Forest Labs. It makes images from words.
- Made by
- Black Forest Labs
- Makes
- Images
- Starts from
- Words
- Shapes
- 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2
- Prompt
- Up to 4,000 characters
- Price per run
- $0.065
- Updated
- October 5, 2026
How it's made
From a still to a film, in one place.
"Passo Giau", replayed step by step: FLUX.3 makes the still, Gemini Omni Flash 1.1 brings it to life. Two models, one studio.


- 01FLUX.3Makes the stillDone
Car commercial frame, aerial drone shot, early morning. The switchback road of the Passo Giau in the Italian Dolomites: grey limestone walls, larch tr...
- 02Gemini Omni Flash 1.1Brings it to lifeDone
The yellow coupe accelerates out of the hairpin and climbs the switchback toward the camera; the drone tracks backward and rises, revealing the valley...
"Passo Giau", made on Leap: two models, one studio, one library.
Pick the right one
FLUX.3 and its siblings
| Model | Best for | Price per run |
|---|---|---|
| FLUX.3 (this page) | Black Forest Labs' newest image model, released on 2026-10-01, at 1K. | $0.065 |
| FLUX.1 [schnell] | Fast, low-cost text to image. Good for drafts and volume. | $0.006 |
| FLUX.2 [pro] | Black Forest Labs' second generation: sharper detail and text than FLUX1.1, at a lower price. | $0.041 |
| FLUX.2 [flex] | FLUX.2 tuned for typography and fine detail, such as posters and layouts. | $0.068 |
Side by side
More image models on Leap
No prompt needed
Or start from a recipe
Recipes write the prompt for you: add a photo, pick a look, and get a finished result.
Questions
FLUX.3, answered
- What is FLUX.3?
- FLUX.3 is an image model from Black Forest Labs. Black Forest Labs' newest image model, released on 2026-10-01, at 1K. On Leap it runs in one studio beside every other top model, with one account.
- What resolution and sizes does it make?
- 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16 or 1:2.
- How is it different from FLUX.1 [schnell], FLUX.2 [pro] and FLUX.2 [flex]?
- FLUX.3: Black Forest Labs' newest image model, released on 2026-10-01, at 1K. FLUX.1 [schnell]: Fast, low-cost text to image. Good for drafts and volume. FLUX.2 [pro]: Black Forest Labs' second generation: sharper detail and text than FLUX1.1, at a lower price. FLUX.2 [flex]: FLUX.2 tuned for typography and fine detail, such as posters and layouts. They all run in the same studio, so you can try one prompt on each.
- How much does a run cost?
- An image costs $0.065. You see the exact price before you press go, and a run that fails costs nothing.
- Is FLUX.3 free to try?
- No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.065 (an image), so $5 covers 76 of those. You pay per run, in dollars, with no subscription.
- Can I use what I make commercially?
- Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
- Is there an API?
- Yes. Leap's REST API runs it as black-forest-labs/flux-3, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
- Do I need a Black Forest Labs account?
- No. Leap sends your request to Black Forest Labs' model and gives you what it makes. One Leap account runs FLUX.3 and every other model, in the studio, through the API and from your agents.
Your idea, FLUX.3.
Every run shows its price before it starts, and one that fails costs nothing.
Make it with FLUX.3For developers
Run FLUX.3 from code
- Model ID
- black-forest-labs/flux-3
- Makes
- Image
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "black-forest-labs/flux-3", "input": { "prompt": "Theatrical key-art poster for an invented Nordic thriller titled SALT LINE. A lone woman in her fifties, Faroese, weathered face with windburned cheeks and pale eyes, grey-blond hair whipped by the wind, in a bright yellow oilskin fishing jacket, stands on a black basalt sea wall in the Faroe Islands as a storm wave explodes white behind her; she is small against the sea, and the turf-roofed houses of a cliff village sit high behind her. Desaturated slate blue and black, with the yellow jacket as the only colour. Typography: the title SALT LINE huge in a tall, condensed, bold sans serif in white across the upper third, tightly set; at the bottom the tagline \"The sea keeps what it takes.\" and below it, small, \"IN CINEMAS THIS NOVEMBER\". Film grain, offset print texture, a real one-sheet composition with generous negative space. No other text." } }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"






