NVIDIA Nemotron 3 Super - blazing-fast agentic AI, ready to deploy today!
Flux Model Family
Developed by Black Forest Labs (the original creators behind Stable Diffusion), Flux is a family of state-of-the-art image generation and editing models that deliver exceptional visual quality with breakthrough prompt accuracy and photorealism. Built on advanced 12 billion parameter architecture, Flux models excel at understanding exactly what you want to create or modify.
FLUX 2 represents the next generation of the Flux family, introducing significantly improved image quality, faster generation, and more precise prompt following. The lineup includes Max for ultimate quality, Pro for production workflows, and Klein variants (9B and 4B) optimized for speed and efficiency — making high-quality image generation accessible at every scale.
Flux offers specialized variants for every need: from open-source to commercial licensing, Flux is perfect for developers building creative applications, product visualization tools, and next-generation image editing experiences.
Featured Model: black-forest-labs/FLUX-2-klein-9b
The best quality-to-latency ratio, production apps model of the Flux 2 family. Frontier visual intelligence — state-of-the-art image generation and editing from Black Forest Labs
Featured Model: black-forest-labs/FLUX-2-klein-4b
The fastest model of the Flux 2 family. Frontier visual intelligence — state-of-the-art image generation and editing from Black Forest Labs
Featured Model: black-forest-labs/FLUX-2-max
The new top-tier image model from Black Forest Labs, significantly pushing image quality and editing consistency
Featured Model: black-forest-labs/FLUX-2-pro
Multi-reference visual intelligence with unprecedented detail, color precision, and spatial reasoning. The most advanced image generation and editing model. Generate photorealistic images with precise control.
Available Flux Models
DeepInfra provides access to Black Forest Labs' complete Flux ecosystem, offering everything from lightning-fast generation to sophisticated in-context editing capabilities with industry-leading prompt adherence and visual quality.
| Model | $ per image | Actions |
|---|---|---|
| FLUX-2-dev | $0.01 x (w / 1024) x (h / 1024) x (iters / 28) | |
| FLUX.1-Kontext-dev | $0.01 x (w / 1024) x (h / 1024) x (iters / 25) | |
| FLUX-2-klein-9b | $0.015 x (w / 1024) x (h / 1024) | |
| FLUX-2-klein-4b | $0.014 x (w / 1024) x (h / 1024) | |
| FLUX-2-max | $0.07 | |
| FLUX-2-pro | $0.015 | |
| FLUX-1-Redux-dev | $0.012 x (w / 1024) x (h / 1024) x (iters / 25) | |
| FLUX-1-dev | $0.009 x (w / 1024) x (h / 1024) x (iters / 25) | |
| FLUX-1-schnell | $0.0005 x (w / 1024) x (h / 1024) x iters | |
| FLUX-pro | $0.05 | |
| FLUX-1.1-pro | $0.04 |
FAQ
What is Flux AI?
Flux is a family of state-of-the-art image generation and editing models developed by Black Forest Labs, the original team behind Stable Diffusion. Built on 12 billion parameter rectified flow transformers, Flux models excel at text-to-image generation, in-context image editing, character consistency preservation, and photorealistic visual synthesis. Available in multiple variants including Pro for maximum quality, Dev for open-weight research, Schnell for ultra-fast generation, and Kontext for revolutionary image editing capabilities, Flux models are designed for comprehensive visual AI applications with exceptional prompt following and creative control.
What tasks are Flux models best suited for?
- In-context image editing with FLUX.1 Kontext for precise modifications using natural language instructions
- Text-to-image generation with industry-leading prompt adherence and photorealistic output quality
- Character consistency preservation across multiple scenes and editing iterations
- Typography and text rendering within images with accurate font reproduction and layout
- Product visualization and marketing content creation with professional-grade results
- Iterative design workflows enabling step-by-step refinement through multiple editing turns
- High-resolution synthesis up to 4K with Ultra variants for detailed, crisp visual output
- Creative content generation for advertising, entertainment, and artistic applications
- Rapid prototyping with Schnell variant delivering quality results in 1-4 inference steps
Are the Flux models on Deepinfra optimized for low latency?
Yes. DeepInfra's autoscaling infrastructure delivers optimized performance for Flux models across all variants. The platform supports both OpenAI-compatible APIs for simple integration and dedicated inference endpoints for maximum performance control, making Flux models ideal for both development and production environments.
What are the pricing details for using Flux models on Deepinfra?
DeepInfra uses a transparent pay-per-use pricing model with no upfront costs or long-term commitments.
Image Generation: Charged per image generation or editing operation. Amount varies by model complexity and resolution requirements.
Pricing scales with model capability—Schnell offers the most cost-effective option for rapid generation, while Pro variants provide premium quality at competitive rates. FLUX.1 Kontext editing operations are priced per modification, enabling cost-effective iterative workflows.
There are no setup fees, and you only pay for what you use.
How do I integrate Flux models into my application?
How do I get started using Flux on DeepInfra?
- Get your API key
- Test models directly from the browser, cURL, or SDKs
- Review pricing on your usage dashboard
© 2026 Deep Infra. All rights reserved.