Z.AI
Ultra-low latency version of GLM-5.3-Flash engineered for high-concurrency real-time IDE code completion and interactive agents.
200K ctx$0.37 / 1M tok (Ultra-Low Latency MoE)
Introducing GLM-4.6VZ.AIReleased December 8, 2025
GLM-4.6V
Multimodal vision model with native function calling and controllable thinking mode switch over 128k tokens.
multimodal-realtimeProprietary API$0.30 / 1M tok (Native Tool Calling Vision)Context: 128K (128,000 tokens)Arena ELO: 1335
Technical Specifications
Architecture Type
Multimodal Vision-Language Transformer
Total Parameters
Frontier Vision Scale
Context Window
128K (128,000 tokens)
Max Output Tokens
32.768K (32,768 tokens)
Knowledge Cutoff
November 2025
Supported Modalities
text, code, vision, reasoning
License & Access
Z.AI Terms of Service
Benchmark Evaluations
Docvqa
91.8
Chartqa
84.1
Mmbench
87.2
Chatbot Arena ELO
1335
Deep Architectural Overview
GLM-4.6V excels at parsing dense technical charts, architectural diagrams, financial reports, and UI screenshots. It supports seamless function calling directly from image inputs at an economical $0.30/$0.90 price point.
Strengths & Considerations
Core Strengths
- Native function calling from images and documents
- Controllable thinking mode switch
- Affordable $0.30 input / $0.05 cache hit pricing
Known Limitations
- Replaced by GLM-5.3-Flash for native visual web coding
Token & API Pricing
Input Tokens (1M)$0.30
Output Tokens (1M)$0.90
Cached Input (1M)$0.0500
Pricing is verified directly against Z.AI's developer documentation and API rate sheets.
Similar & Alternative Models
Explore other frontier models from Z.AI and comparable reasoning engines.
Z.AI
The first native multimodal model in the GLM-5 series: 320B parameters (18B active) combining linear and sparse attention for low-cost visual coding.
200K ctx$0.15 / 1M tok (320B MoE Visual Coding)
Z.AI
Z.AI’s premier flagship model, delivering a 50% performance gain on Code Bench and matching Claude Mythos 5 in cybersecurity and vulnerability discovery.
1M ctx$1.40 / 1M tok (Flagship Coding & Cyber)
Z.AI
Flagship model built for project-scale context, supporting truly usable 1M-token context with 128k output.
1M ctx$1.40 / 1M tok (1M Lossless Context)