Fireworks RFT now available! Fine-tune open models that outperform frontier models. Try today

Model Library/Black Forest Labs/FLUX.1 Kontext Max
Flux Logo Mark

FLUX.1 Kontext Max

Ready
Try in Playground
fireworks/flux-kontext-max

    FLUX.1 Kontext Max is the most advanced model in the Kontext series, offering maximum quality and context understanding. And handles both text and reference images as inputs. Ideal for enterprise applications requiring the highest level of image generation performance.

    FLUX.1 Kontext Max API Features

    Serverless

    Docs

    Immediately run model on pre-configured GPUs and pay-per-token

    On-demand Deployment

    Docs

    On-demand deployments give you dedicated GPUs for FLUX.1 Kontext Max using Fireworks' reliable, high-performance system with no rate limits.

    Available Serverless

    Run queries immediately, pay only for usage

    $0.08
    Per 1K Tokens

    FLUX.1 Kontext Max FAQs

    What is FLUX.1 Kontext Max and who developed it?

    FLUX.1 Kontext Max is a high-performance text-to-image diffusion model developed by Black Forest Labs. It is the most advanced member of the FLUX.1 Kontext series, built to maximize prompt fidelity, typography control, and image quality for enterprise and creative workflows.

    What applications and use cases does FLUX.1 Kontext Max excel at?

    This model is designed for:

    • High-fidelity image generation from long-form prompts
    • Typography-aware and structured visual outputs
    • Creative editing and inpainting scenarios
    • Image-to-image generation, allowing visual grounding with reference inputs
    Is fine-tuning supported for FLUX.1 Kontext Max?

    No. Fireworks does not support fine-tuning or LoRA for this model.

    What rate limits apply on the shared endpoint?
    • Serverless: Available at $0.08 per 1K tokens
    • On-demand: Supported with no rate limits on dedicated GPUs

    Metadata

    State
    Ready
    Created on
    6/24/2025
    Kind
    Unknown
    Provider
    Black Forest Labs

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    N/A

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Supported
    Serverless LoRA
    Not supported
    Context Length
    N/A
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported