All Models

GLM-4.6V

Reasoning Tool Calling Attachments Open Weights Structured Output

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

Providers 13
Released Sep 30, 2025
Input Modalities text, image, video, pdf
Output Modalities text
Tarsk Use coding

Benchmarks

17.1
Intelligence Index
11.1
Coding Index
26.3
Math Index

Available Providers (13)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Z.AI Coding Plan glm-4.6v $0.00/MTok $0.00/MTok 128K 32.8K
Zhipu AI Coding Plan glm-4.6v $0.00/MTok $0.00/MTok 128K 32.8K
ZenMux z-ai/glm-4.6v $0.14/MTok $0.42/MTok 200K 64K
AIHubMix glm-4.6v $0.14/MTok $0.41/MTok 128K 32.8K
302.AI glm-4.6v $0.14/MTok $0.43/MTok 128K 32.8K
NovitaAI zai-org/glm-4.6v $0.30/MTok $0.90/MTok 131.1K 32.8K
Chutes zai-org/GLM-4.6V $0.30/MTok $0.90/MTok 131.1K 65.5K
Deep Infra zai-org/GLM-4.6V $0.30/MTok $0.90/MTok 204.8K 131.1K
Z.AI glm-4.6v $0.30/MTok $0.90/MTok 128K 32.8K
Vercel AI Gateway zai/glm-4.6v $0.30/MTok $0.90/MTok 128K 24K
LLM Gateway glm-4.6v $0.30/MTok $0.90/MTok 128K 16K
Zhipu AI glm-4.6v $0.30/MTok $0.90/MTok 128K 32.8K
Poe novita/glm-4.6v —/MTok —/MTok 131K 32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output