Skip to main content
Black Forest LabsOct 1, 2026

Flux 3

flux-3-imageAnonymized

Flux 3 is Black Forest Labs’ flagship image model, with native 2K and 4K output, precise layout control and strong text rendering. It accepts prompts of up to 32,000 characters and pairs with Flux 3 Edit for local edits and multi-reference composition.

from$0.12
per image
4K
max resolution, 3 sizes
8
aspect ratios, 1:1 default

Same prompt, other models

Every image model renders the same reference prompts, so their results line up side by side.

Photorealistic close-up portrait of a weathered fisherman at golden hour, 85mm lens, shallow depth of field, natural skin texture

Pricing

Billed per image in USD, by resolution. Each resolution is drawn to scale.

1K · default2K4K
Per image$0.12$0.29$0.98
Edit$0.12
2x upscale$0.02
4x upscale$0.08

Estimate a batch

Resolution
$0.12per image
$120for 1,000 images

Against other image models

How it comparesamong 51 image models
Price per imagecheaper than 10%$0.12
Prompt limitlonger than 88%32,000 characters

Further right is better. Hover a dot for its model.

Capabilities

What the family does, and every shape it renders.

Generateflux-3-image
Editflux-3-image-edit · up to 6 images
Upscale2x $0.02 · 4x $0.08
Repeatableseed

Aspect ratios

1:13:216:921:99:162:33:44:5

Specs

Model ID
flux-3-image
Edit model ID
flux-3-image-edit
Endpoint
POST /api/v1/image/generate
Resolutions
1K, 2K, 4K · default 1K
Aspect ratios
8 · default 1:1
Prompt limit
32,000 characters
Steps
default 20, max 50
Privacy
Anonymized
Weights
Closed
Added
Oct 1, 2026

Quickstart

Generate with Venice’s image endpoint, or with the OpenAI-compatible one from any OpenAI SDK.

curl https://api.venice.ai/api/v1/image/generate \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-3-image",
"prompt": "A retro travel poster with the bold headline \"VENICE\" in large condensed serif type, sunset color palette",
"resolution": "1K",
"aspect_ratio": "1:1"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelflux-3-imageRequired
promptUp to 32,000 charactersRequired
resolution1K | 2K | 4KDefault 1K
aspect_ratio8 ratiosDefault 1:1
stepsUp to 50Default 20
seedIntegerRepeats a result
variants1 – 4Images per request
formatwebp | png | jpegDefault webp
safe_modetrue | falseDefault true, which blurs adult content