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-OCRZ.AIReleased February 3, 2026
GLM-OCR
Compact optical character recognition model combining CogViT with GLM-0.5B for fast, highly accurate document and table extraction.
multimodal-realtimeProprietary API$0.03 / 1M tok (CogViT + GLM-0.5B)Context: 32.768K (32,768 tokens)
Technical Specifications
Architecture Type
CogViT + GLM-0.5B Encoder-Decoder
Total Parameters
0.9B
Context Window
32.768K (32,768 tokens)
Max Output Tokens
8.192K (8,192 tokens)
Knowledge Cutoff
January 2026
Supported Modalities
vision, text
License & Access
Z.AI Terms of Service
Benchmark Evaluations
Table Structure F1
96.2
Ocr Character Accuracy
98.4
Deep Architectural Overview
GLM-OCR is powered by self-developed CogViT visual encoders and a GLM-0.5B decoder. Pre-trained on billions of image-text pairs via CLIP alignment, it parses dense financial statements, multi-column research papers, and complex tables at $0.03/1M tokens.
Strengths & Considerations
Core Strengths
- 98.4% character accuracy on complex printed and scanned documents
- Precise table structure markdown extraction
- Flat $0.03 / 1M token pricing
Known Limitations
- Specialized document extraction model, not designed for conversational dialogue
Token & API Pricing
Input Tokens (1M)$0.03
Output Tokens (1M)$0.03
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)