Text to image
Elo · text-to-image arena
Flux.1 Kontext overview
Flux.1 Kontext by Black Forest Labs
FLUX.1 Kontext [pro] is a fast, versatile model for local edits, in-context generation, and text-to-image creation.
Flux.1 Kontext specs
- Model ID
blackforestlabs/flux-kontext-pro- Developer
- Black Forest Labs
- Input
- Text, Image
- Output
- Text, Image
- Endpoint
POST https://api.aimlapi.com/v1/images/generations
Flux.1 Kontext Pro Description
FLUX.1 Kontext Pro is Black Forest Labs’ breakthrough in-context image model. Unlike traditional text-to-image systems that start from scratch every time, Kontext Pro understands both your text prompt and any reference images you feed it. It performs surgical local edits, full-scene transformations, and maintains perfect character, style, and identity across multiple iterations.
Built on a rectified flow transformer architecture with 12 billion parameters, it delivers FLUX-level visual quality while pioneering true iterative workflows. You can edit an image once, then edit the result again, and again without losing facial features, clothing details, lighting mood, or brand style.
It replaces clunky multi-model pipelines with a single, reliable endpoint. No more stitching together separate tools for generation, editing, and consistency checks. Just one fast, powerful call.
- Higher rate limits out of the box: Scale to thousands of images per minute without begging for custom enterprise plans.
- Unified billing across 400+ models: One dashboard, one invoice, one API key. Switch between FLUX variants, LLMs, or voice models instantly without new accounts or separate billing.
- Blazing-fast global inference: Our optimized infrastructure delivers 8-10 second generations with 99.9% uptime. No more waiting 30-40 seconds like on some competitors.
- Enterprise-ready reliability : Commercial licensing included, full prompt and output safety filters, and detailed usage analytics.
Technical Specifications
- Generation speed: 8-10 seconds per image (up to 8× faster than leading competitors)
- Model architecture: 12B parameter rectified flow transformer
- Resolution: Native 1024×1024 with flexible aspect ratios
- Input types: Text-only or text + reference images (single or multiple URLs)
- Benchmark performance: Top ELO ratings exceeding 1100 across image generation and editing leaderboards. Highest scores in character preservation and text editing tasks.
- Safety: Built-in content filters with adjustable tolerance levels
Compared to ByteDance BAGEL (40+ seconds) or OpenAI GPT-4o image generation, FLUX.1 Kontext Pro wins on speed, consistency, and cost every single time.
Performance Metrics
FLUX models (shown in purple) consistently achieve top performance with ELO ratings often exceeding 1100, demonstrating the strong capabilities of the Flux.1 Kontext model family in various image generation and editing benchmarks.
In-Context Generation & Editing
Feed it a reference image (or several) plus a text prompt, and watch magic happen. The model intelligently merges visual context with your instructions, perfect for “change the background to a cyberpunk city but keep the character exactly the same.”
Surgical Local Edits
Want to tweak just the hat on your character while leaving everything else untouched? FLUX.1 Kontext Pro does regional edits with surgical precision. No more “everything changed” disasters.
Unmatched Character & Style Consistency
This is where Kontext Pro destroys the competition. Facial features, body type, clothing details, art style, everything stays locked in across completely different scenes and multiple editing turns. Marketers building avatar libraries or game devs creating consistent characters finally get a model that actually delivers.
Use cases
- Professional designers, advertisers, and editorial teams for creative visual production
- Content creators for precise, consistent, character- and style-focused iterative editing
- Artists, prototypers, and enterprises needing high-speed, localized image transformations
- Cloud platforms and interactive playgrounds for scaled, precision image editing
Flux.1 Kontext benchmarks by 
Artificial Analysis
Human-preference results for Flux.1 Kontext in text to image, next to models available on AI/ML API. Data retrieved Nov 3, 2026.
AI/ML API price
USD per generation
Models on AI/ML API
Arena results for models you can call with the same API key.
Text to image
Blind pairwise human votes on images generated from text prompts. Flux.1 Kontext ranks #71 of 98.
Flux.1 Kontext API pricing
| Usage | Price | Unit |
|---|---|---|
| Image generation | $0.04 | per generation |
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.1 Kontext vs other image models: prices
AI/ML API rates for 5 models, per generation.
| Model | Per generation |
|---|---|
 Flux.1 Kontext | $0.04 |
| FLUX.1 Dev | $0.025 |
| Flux pro 1.1 | $0.04 |
| Flux Kontext Pro | $0.04 |
 Nano Banana Edit | $0.04 |
How to use the Flux.1 Kontext API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
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": "blackforestlabs/flux-kontext-pro",
"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": "blackforestlabs/flux-kontext-pro",
"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": "blackforestlabs/flux-kontext-pro",
"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.1 Kontext
Related articles
.webp)
Flux.1 Kontext FAQ
What inputs and outputs does Flux.1 Kontext [pro] support?
Flux.1 Kontext [pro] takes image, text as input and returns image.
When was Flux.1 Kontext [pro] released?
Flux.1 Kontext [pro] became available on May 29, 2025.
How much does Flux.1 Kontext [pro] cost?
Flux.1 Kontext costs $0.04 per generation on AI/ML API, billed as you go with no subscription.
How is Flux.1 Kontext [pro] billed?
Flux.1 Kontext [pro] is billed per generation, a fixed charge per output rather than by prompt length.
Can Flux.1 Kontext [pro] take an existing image as input?
Yes, Flux.1 Kontext [pro] accepts image input as well as a text prompt.
Who created Flux.1 Kontext [pro]?
Flux.1 Kontext [pro] was built by Black Forest Labs.
How do I call Flux.1 Kontext [pro] on AI/ML API?
Send a request to https://api.aimlapi.com/v1/images/generations with blackforestlabs/flux-kontext-pro as the model id.
Is Flux.1 Kontext [pro] available through a single API key?
Yes. Flux.1 Kontext [pro] is served through AI/ML API, so the same key and endpoint format used for other models applies.
What is the Flux.1 Kontext model ID?
Use blackforestlabs/flux-kontext-pro as the model parameter. Requests go to https://api.aimlapi.com/v1/images/generations with your AI/ML API key.