Skip to content

Zhipu AI · Image

GLM-Image

Zhipu AI 🇨🇳ImageGLM familyOpen weights. One of its sources says the weights are publicly available.
From Llmgateway's listing:
Z.AI's GLM-Image text-to-image generation model with hybrid auto-regressive architecture, excellent for text-rendering and knowledge-intensive generation.
llminfo IQ
83.6
Market median price
$0.05 /image
Max context
10K
Listings
9

Evidence and sources

🤗 zai-org/GLM-Imagellminfo IQ 83.6, ranked among image generation models. From 152 benchmarks. A fair amount of data behind it.How llminfo IQ is computedReleased 14 Jan 2026Maker HQ: CN (source)
Sources: LMArena data, Models.dev data, LLMGateway data, llminfo researchPrimary data from LMArena from Models.dev: weights availability from LLMGateway: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 image generation models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 2 of the 9 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Text
Images

Capabilities

Supported operations and provider-stated features

VisionFunction calling

Listings

 Zhipu AI (Open Platform)glm-imageSource: Zhipu BigModel Open Platform PricingNot published by the provider—
 Fastrouterz-ai/glm-imageSource: FastRouter data4K$0.01—
 Llmgatewayglm-imageSource: LLMGateway data2K—$0.015
 LlmgatewayInference by Z.aiglm-imageSource: LLMGateway dataNot published by the provider—$0.015
 NanoGPTglm-imageSource: NanoGPTNot published by the provider$0.12—
 fal.aifal_ai/fal-ai/glm-imageSource: LiteLLM dataNot published by the provider$0.05—
 fal.aifal_ai/fal-ai/glm-image/image-to-image · image-to-imageSource: LiteLLM dataNot published by the provider$0.05—

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Image generation

Arena ELO Text to ImageSource: LMArena data · Nov 2026
GEditBench v2Source: GEditBench v2
UniGenBench++136 related benchmarks · 136 results
Source: UniGenBench++ data
BenchmarkScore
(Chinese) - 2D
(Chinese Long) - 2D
(Chinese Long) - 3D
(Chinese Long) - Action-Overall
Show 132 more benchmarksHide 132 benchmarks
BenchmarkScore
(Chinese Long) - Animal
(Chinese Long) - Attribute-Overall
(Chinese Long) - Color
(Chinese Long) - Comparison
(Chinese Long) - Composition
(Chinese Long) - Compound-Overall
(Chinese Long) - Consistency
(Chinese Long) - Contact
(Chinese Long) - Expression
(Chinese Long) - Feature matching
(Chinese Long) - Full body
(Chinese Long) - Grammar-Overall
(Chinese Long) - Hand
(Chinese Long) - Imagination
(Chinese Long) - Inclusion
(Chinese Long) - Layout-Overall
(Chinese Long) - Logical Reasoning
(Chinese Long) - Material
(Chinese Long) - Negation
(Chinese Long) - Non Contact
(Chinese Long) - Overall
(Chinese Long) - Pronoun Reference
(Chinese Long) - Quantity
(Chinese Long) - Relationship-Overall
(Chinese Long) - Shape
(Chinese Long) - Similarity
(Chinese Long) - Size
(Chinese Long) - State
(Chinese Long) - Style
(Chinese Long) - Text
(Chinese Long) - World Knowledge
(Chinese) - 3D
(Chinese) - Action-Overall
(Chinese) - Animal
(Chinese) - Attribute-Overall
(Chinese) - Color
(Chinese) - Comparison
(Chinese) - Composition
(Chinese) - Compound-Overall
(Chinese) - Consistency
(Chinese) - Contact
(Chinese) - Expression
(Chinese) - Feature matching
(Chinese) - Full body
(Chinese) - Grammar-Overall
(Chinese) - Hand
(Chinese) - Imagination
(Chinese) - Inclusion
(Chinese) - Layout-Overall
(Chinese) - Logical Reasoning
(Chinese) - Material
(Chinese) - Negation
(Chinese) - Non Contact
(Chinese) - Overall
(Chinese) - Pronoun Reference
(Chinese) - Quantity
(Chinese) - Relationship-Overall
(Chinese) - Shape
(Chinese) - Similarity
(Chinese) - Size
(Chinese) - State
(Chinese) - Style
(Chinese) - Text
(Chinese) - World Knowledge
(English Long) - 2D
(English Long) - 3D
(English Long) - Action-Overall
(English Long) - Animal
(English Long) - Attribute-Overall
(English Long) - Color
(English Long) - Comparison
(English Long) - Composition
(English Long) - Compound-Overall
(English Long) - Consistency
(English Long) - Contact
(English Long) - Expression
(English Long) - Feature matching
(English Long) - Full body
(English Long) - Grammar-Overall
(English Long) - Hand
(English Long) - Imagination
(English Long) - Inclusion
(English Long) - Layout-Overall
(English Long) - Logical Reasoning
(English Long) - Material
(English Long) - Negation
(English Long) - Non Contact
(English Long) - Overall
(English Long) - Pronoun Reference
(English Long) - Quantity
(English Long) - Relationship-Overall
(English Long) - Shape
(English Long) - Similarity
(English Long) - Size
(English Long) - State
(English Long) - Style
(English Long) - Text
(English Long) - World Knowledge
(English) - 2D
(English) - 3D
(English) - Action-Overall
(English) - Animal
(English) - Attribute-Overall
(English) - Color
(English) - Comparison
(English) - Composition
(English) - Compound-Overall
(English) - Consistency
(English) - Contact
(English) - Expression
(English) - Feature matching
(English) - Full body
(English) - Grammar-Overall
(English) - Hand
(English) - Imagination
(English) - Inclusion
(English) - Layout-Overall
(English) - Logical Reasoning
(English) - Material
(English) - Negation
(English) - Non Contact
(English) - Overall
(English) - Pronoun Reference
(English) - Quantity
(English) - Relationship-Overall
(English) - Shape
(English) - Similarity
(English) - Size
(English) - State
(English) - Style
(English) - Text
(English) - World Knowledge

Human preference

Vision

CVTG-2KSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Other

Data credits: LMArena, CC BY 4.0 (licence) · Data by LLM Stats · UniGenBench++ (CodeGoat24), MIT (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark

Around the web

  • Z.ai unveils GLM-5, advances AI agents and China chip compatibility

    Joanna Gao Joanna Gao , Taipei Feb 12, 2026, 14:54 0 [](https://twitter.com/intent/tweet?url=https://www.digitimes.com/news/a20260212PD225/china-zhipuai-ai-startup-performance-2025.html&text=Z.ai unv…

    digitimes.com

  • GitHub - MetaGLM/zhipuai-sdk-nodejs-v4: NodeJs SDK for ZhiPu AI · GitHub
    role": "user", "content": "What is the relationship between ZhipuAI and ChatGLM?"} ], stream: false }); …role": "user", "content": "What is the relationship between ZhipuAI and ChatGLM?"} ], stream: false }); console.log(result); }; dialogue(); Streaming Invocation (SSE) Basic Chat import { ZhipuAI } fr…

    github.com

  • GLM-4.7 · Models
    Magic Cube login / register ZhipuAI / GLM-4.7 202 Collections Text Generation 358.34B Transformers Safetensors …Magic Cube login / register ZhipuAI / GLM-4.7 202 Collections Text Generation 358.34B Transformers Safetensors PyTorch License: mit glm4_moe English Chinese ModelScope Inference Demo @ZhipuAI 421,918…

    modelscope.cn

  • ModelScope模型库-GLM-4.5
    login / register ZhipuAI / GLM-4.5 402 Collections Text Generation 358.34B Safetensors PyTorch License: mit …login / register ZhipuAI / GLM-4.5 402 Collections Text Generation 358.34B Safetensors PyTorch License: mit glm4_moe English Chinese ModelScope Inference Demo @ZhipuAI 30,103 downloads 716.71GB updat…

    modelscope.cn

  • GLM-4.5 · Models - ollama.modelscope.cn
    ZhipuAI / GLM-4.5 403 Collections Text Generation 358.34B Safetensors PyTorch License: mit glm4_moe English Chinese …ZhipuAI / GLM-4.5 403 Collections Text Generation 358.34B Safetensors PyTorch License: mit glm4_moe English Chinese ModelScope Inference Demo @ZhipuAI 30,132 downloads 716.71GB updated Jan 20,2026 Mo…

    ollama.modelscope.cn

  • GLM-4 - Hugging Face
    Team, THUDM & ZhipuAI. The abstract from the paper is the following: We introduce ChatGLM, …Team, THUDM & ZhipuAI. The abstract from the paper is the following: We introduce ChatGLM, an evolving family of large language models that we have been developing over time. This report primarily fo…

    huggingface.co

  • GLM-5 · Models
    Home Models Datasets Studios Docs Community MCP Civision Top Searches copaw qwen3.5 Qwen3 qwen api …Home Models Datasets Studios Docs Community MCP Civision Top Searches copaw qwen3.5 Qwen3 qwen api deepseek indextts2 Z-Image qwen3-vl glm login / register ZhipuAI / GLM-5 157 Collections Text Genera…

    modelscope.cn

  • GLM 5.2 API by ZHIPUAI - 高性价比- 统一API 接入
    GLM 5.2 — Atlas Cloud API Agent-oriented model built for complex reasoning, tool use, and …GLM 5.2 — Atlas Cloud API Agent-oriented model built for complex reasoning, tool use, and autonomous task execution. This is the machine-readable API reference for GLM 5.2 on Atlas Cloud, a unified A…

    atlascloud.ai

  • Zhipu AI GLM (GLM-4.7 / GLM-4-Flash) API Guide - How to Apply & Use | 6G-AI
    apply for fine-tuning to get 5M additional training tokens. Tip 4 API is compatible with …apply for fine-tuning to get 5M additional training tokens. Tip 4 API is compatible with OpenAI format for easy integration. Tip 5 CogView-3-Flash offers free AI image generation. Tip 6 GLM-4.7 at $0…

    6g-ai.com

  • Zhipu AI | Models | Mastra Docs
    0.60 · $2 zhipuai/glm-4.6 · 205K · $0.60 · $2 zhipuai/glm-4.6v · 128K · $0.30 …0.60 · $2 zhipuai/glm-4.6 · 205K · $0.60 · $2 zhipuai/glm-4.6v · 128K · $0.30 · $0.90 zhipuai/glm-4.7 · 205K · $0.60 · $2 zhipuai/glm-4.7-flash · 200K · — · — …

    mastra.ai

Also known as: fal-ai/glm-image, fal-ai/glm-image/image-to-image, z-ai/glm-image

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works