FLUX.2 overview
FLUX.2 by Black Forest Labs
FLUX.2 is an advanced text-to-image generative model developed by Black Forest Labs.
FLUX.2 specs
- Model ID
flux-2- Developer
- Black Forest Labs
- Input
- Text
- Output
- Image
- Endpoint
POST https://api.aimlapi.com/v1/images/generations
What Is Flux 2?
Flux 2 is a professional visual foundation model from Black Forest Labs that combines a powerful vision‑language backbone with a rectified flow transformer to understand both world knowledge and fine‑grained spatial relationships. It is designed to handle text‑to‑image, image‑to‑image, and complex editing inside one architecture, simplifying pipelines for teams that previously juggled multiple models.
Core Capabilities
- Generates photorealistic images and detailed illustrations at resolutions up to roughly 4 megapixels, suitable for print, product pages, and high‑impact advertising.
- Natively supports infographics, UI mockups, and complex typography, delivering clean, readable on‑image text and multi‑language layouts.
- Handles both new image creation from prompts and transformation of existing assets with the same underlying model, streamlining integration and QA
Architecture Highlights
- Built on a latent flow‑matching approach that improves learnability and image quality while maintaining strong compression for practical deployment.
- Couples a large vision‑language model (Mistral‑3 24B class) with a rectified flow transformer to capture semantics, materials, lighting, and composition more reliably than earlier diffusion systems.
- Retrained latent space from scratch to push past the typical “quality vs. compression vs. learnability” trade‑off, resulting in sharper details and more faithful prompt adherence.
Performance Benchmarks
- Outperforms all other open-weight alternatives in text-to-image generation and image editing tasks.
- Achieves photorealistic detail, stable lighting, and texture sharpness on par with professional closed-source models.
Flux 2 API For Image Generation
By interpreting narrative intent, motion cues, and stylistic direction directly from text, the model generates videos that feel purposeful rather than procedural. Scenes evolve naturally, transitions remain consistent, and visual identity is preserved from the first frame to the last.
Prompt Adherence & Visual Quality
- Interprets complex prompts that specify camera angle, lens, materials, mood, and composition, keeping scenes coherent even at high detail.
- Produces realistic lighting and physics that avoid the typical “AI look,” with accurate perspective, spatial reasoning, and object placement.
- Supports exact color targeting (including HEX codes) so brand palettes and UI themes are reproduced consistently across large batches.
Use cases
- Product mockups requiring precise text and visual detail
- Marketing and branding materials with strict adherence to typography and style
- UI/UX design and infographic generation with high fidelity text rendering
- Creative workflows needing flexible output control with cost efficiency
- Research and development via open-weight models for experimentation in image generation and editing
FLUX.2 API pricing
| Usage | Price | Unit |
|---|---|---|
| Image generation | $0.012 | per Megapixel |
The final price depends on request parameters such as resolution or duration.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
FLUX.2 vs other image models: prices
AI/ML API rates for 5 models, per Megapixel.
| Model | Per Megapixel |
|---|---|
 FLUX.2 | $0.012 |
| FLUX.2 Klein 4B | $0.014 |
| FLUX.2 Klein 9B | $0.015 |
| FLUX.2 Klein 9B Preview | $0.015 |
| FLUX.2 Flex | $0.05 |
How to use the FLUX.2 API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/images/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "flux-2",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "flux-2",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}
response = requests.post("https://api.aimlapi.com/v1/images/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/images/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "flux-2",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to FLUX.2
Related articles
.webp)
FLUX.2 FAQ
What inputs and outputs does FLUX.2 support?
FLUX.2 takes image, text as input and returns image.
How much does FLUX.2 cost?
FLUX.2 costs $0.012 per Megapixel on AI/ML API, billed as you go with no subscription.
How is FLUX.2 billed?
FLUX.2 is billed per generation, a fixed charge per output rather than by prompt length.
Can FLUX.2 take an existing image as input?
Yes, FLUX.2 accepts image input as well as a text prompt.
Who created FLUX.2?
FLUX.2 was built by Black Forest Labs.
How do I call FLUX.2 on AI/ML API?
Send a request to https://api.aimlapi.com/v1/images/generations with flux-2 as the model id.
Is FLUX.2 available through a single API key?
Yes. FLUX.2 is served through AI/ML API, so the same key and endpoint format used for other models applies.
What is FLUX.2's API endpoint?
FLUX.2 is accessed via https://api.aimlapi.com/v1/images/generations.
What is the FLUX.2 model ID?
Use flux-2 as the model parameter. Requests go to https://api.aimlapi.com/v1/images/generations with your AI/ML API key.