LLM Reference

Z-Image

Released
2025-11-26
Last refreshed
2026-07-10
Status
Researched 93d ago
Open weightsCommercial use: unknownMultimodalVision

Z-Image is worth evaluating for vision when its provider route and context window match the workload.

Use it for

  • Teams evaluating vision
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Strict JSON or tool-calling flows
Specifications
Family
Z-Image
Released
2025-11-26
Parameters
6B
Architecture
Diffusion
Specialization
image-generation
Openness
Open weights
Weights
Unknown
Code
Unknown
Created by

Chinese AI research lab developing GLM language models.

Beijing, China
Founded 2019
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · fal API

About

Z-Image by Zhipu AI (Z.ai). A 6B single-stream Diffusion Transformer (S3-DiT) model for efficient few-step text-to-image generation. Supports bilingual Chinese-English text rendering. Z-Image Turbo variant ranked #1 among open-source models on the Artificial Analysis Text-to-Image Leaderboard (December 2025). Available via Fal API (fal-ai/z-image/turbo).

Z-Image is an open-weight model. The structured metadata tracks multimodal input. This page tracks provider routes through fal API. No headline benchmark score is tracked for Z-Image yet.

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
fal API--
ServerlessPartial

Capabilities

Multimodal

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

When was Z-Image released?

Z-Image was released on 2025-11-26.

Which providers offer Z-Image?

Z-Image is available from 1 provider: fal API.