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

FLUX.2 [klein] 4B vs GLM-Image

Preferred for text to image: FLUX.2 [klein] 4B · Newest: FLUX.2 [klein] 4B · Self-hosting: GLM-Image. Quality scores are blind human-preference votes; specs and prices come from each lab’s listings.

  1. Black Forest Labs

    FLUX.2 [klein] 4B

    Released Jan 15, 2026

    • Text to image
    • Image editing
    • Arena1,187
    • From$0.014/image
    • Max size—
    Full specs Remove FLUX.2 [klein] 4B

  2. Z.ai (Zhipu)

    GLM-Image

    Released Jan 14, 2026

    • Text to image
    • Image editing
    • Arena1,012
    • From—
    • Max size—
    Full specs Remove GLM-Image

  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 imageFLUX.2 [klein] 4BFLUX.2 [klein] 4B 1,030 (#70) · GLM-Image 1,012 (#76) — blind human votes
  • NewestFLUX.2 [klein] 4BFLUX.2 [klein] 4B Jan 15, 2026 · GLM-Image Jan 14, 2026
  • Widest inputsSame inputsFLUX.2 [klein] 4B: Text prompts, Reference images · GLM-Image: Text prompts, Reference images
  • Image editingBoth edit imagesTakes a reference image as input: FLUX.2 [klein] 4B yes · GLM-Image yes
  • Self-hostingGLM-ImageDownloadable weights (MIT)
  • Most API hostsSame reachFLUX.2 [klein] 4B: 1 · GLM-Image: 1
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

FLUX.2 [klein] 4B vs GLM-Image specifications side by side
SpecificationFLUX.2 [klein] 4BBlack Forest LabsGLM-ImageZ.ai (Zhipu)
Quality (blind human votes)
Text to image arenaElo-style score · higher is better1,030 ±3#70 of 82 · 152,289 votes (best)1,012 ±9#76 of 82 · 4,854 votes
Image editing arenaElo-style score · higher is better1,187 ±3#51 of 61 · 541,233 votes—
Price
Starting price$0.014/image 1 MP—
How it is billedBilled per megapixel.—
Output
ProducesImagesImages
Images per requestUp to 1—
Inputs
Text promptsYesYes
Reference images (editing)YesYes
Max reference images4—
Access
WeightsProprietaryOpenMIT
API hosts11
ReleasedJan 15, 2026Jan 14, 2026
03 — Questions

Which should you choose?

Which is better, FLUX.2 [klein] 4B or GLM-Image?

For text to image, voters prefer FLUX.2 [klein] 4B (FLUX.2 [klein] 4B 1,030 (#70) · GLM-Image 1,012 (#76)). 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.

Which is cheaper?

FLUX.2 [klein] 4B costs from $0.014/image (1 MP). GLM-Image has no published per-image price. Prices are list rates and change often; check the lab before budgeting.

What is the difference between FLUX.2 [klein] 4B and GLM-Image?

FLUX.2 [klein] 4B is an image model from Black Forest Labs (Jan 15, 2026), taking text prompts and reference images and producing images. GLM-Image is an image model from Z.ai (Zhipu) (Jan 14, 2026), taking text prompts and reference images and producing images.

Which is newer?

FLUX.2 [klein] 4B Jan 15, 2026; GLM-Image Jan 14, 2026.

Which can edit an existing image?

Takes a reference image as input: FLUX.2 [klein] 4B yes; GLM-Image yes.

Can I run any of these on my own hardware?

GLM-Image. Downloadable weights (MIT).

04 — Keep comparing

Related comparisons