ZMIME
Image model comparison · 2 models · Updated Nov 2, 2026

FLUX.1 Kontext [dev] vs GPT Image 1

Preferred for text to image: GPT Image 1 · Preferred for image editing: FLUX.1 Kontext [dev] · Newest: FLUX.1 Kontext [dev]. Quality scores are blind human-preference votes; specs and prices come from each lab’s listings.

  1. Black Forest Labs

    FLUX.1 Kontext [dev]

    Released May 29, 2025

    • Text to image
    • Image editing
    • Arena1,151
    • From—
    • Max size—
    Full specs Remove FLUX.1 Kontext [dev]

  2. OpenAI

    GPT Image 1

    Released Apr 24, 2025

    • Text to image
    • Image editing
    • Arena1,139
    • From—
    • Max size—
    Full specs Remove GPT Image 1

  3. Add a model

    Make it a three-way comparison.

01 — At a glance

Where they differ

Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.

  • Preferred for text to imageGPT Image 1FLUX.1 Kontext [dev] 942 (#80) · GPT Image 1 1,115 (#49) — blind human votes
  • Preferred for image editingFLUX.1 Kontext [dev]FLUX.1 Kontext [dev] 1,151 (#55) · GPT Image 1 1,139 (#57) — blind human votes
  • NewestFLUX.1 Kontext [dev]FLUX.1 Kontext [dev] May 29, 2025 · GPT Image 1 Apr 24, 2025
  • Widest inputsSame inputsFLUX.1 Kontext [dev]: Text prompts, Reference images · GPT Image 1: Text prompts, Reference images
  • Image editingBoth edit imagesTakes a reference image as input: FLUX.1 Kontext [dev] yes · GPT Image 1 yes
  • Self-hostingFLUX.1 Kontext [dev]Downloadable weights (FLUX.1 [dev] Non-Commercial License)
  • Most API hostsGPT Image 1FLUX.1 Kontext [dev]: 1 · GPT Image 1: 4
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

FLUX.1 Kontext [dev] vs GPT Image 1 specifications side by side
SpecificationFLUX.1 Kontext [dev]Black Forest LabsGPT Image 1OpenAI
Quality (blind human votes)
Text to image arenaElo-style score · higher is better942 ±4#80 of 82 · 216,222 votes1,115 ±3#49 of 82 · 268,430 votes (best)
Image editing arenaElo-style score · higher is better1,151 ±3#55 of 61 · 3,639,663 votes (best)1,139 ±3#57 of 61 · 2,869,681 votes
Output
ProducesImagesImages
Inputs
Text promptsYesYes
Reference images (editing)YesYes
Access
WeightsOpenFLUX.1 [dev] Non-Commercial LicenseProprietary
API hosts14 (best)
ReleasedMay 29, 2025Apr 24, 2025
03 — Questions

Which should you choose?

Which is better, FLUX.1 Kontext [dev] or GPT Image 1?

For text to image, voters prefer GPT Image 1 (FLUX.1 Kontext [dev] 942 (#80) · GPT Image 1 1,115 (#49)). For image editing, voters prefer FLUX.1 Kontext [dev] (FLUX.1 Kontext [dev] 1,151 (#55) · GPT Image 1 1,139 (#57)). Arena scores come from blind, side-by-side human votes on the same prompts; when the gap is inside both models’ error margins we call it a tie. Test your own prompts before you commit.

What is the difference between FLUX.1 Kontext [dev] and GPT Image 1?

FLUX.1 Kontext [dev] is an image model from Black Forest Labs (May 29, 2025), taking text prompts and reference images and producing images. GPT Image 1 is an image model from OpenAI (Apr 24, 2025), taking text prompts and reference images and producing images.

Which is newer?

FLUX.1 Kontext [dev] May 29, 2025; GPT Image 1 Apr 24, 2025.

Which can edit an existing image?

Takes a reference image as input: FLUX.1 Kontext [dev] yes; GPT Image 1 yes.

Can I run any of these on my own hardware?

FLUX.1 Kontext [dev]. Downloadable weights (FLUX.1 [dev] Non-Commercial License).

04 — Keep comparing

Related comparisons