Z.ai: GLM 4.6V
智谱 GLM · Text
GLM vision model for visual reasoning, documents, and multimodal agents
Model ID z-ai/glm-4.6vUpdated Dec 8, 2025
Pricing & billing
Billing unit: 1M tokens. Vendor reference price; conversion is approximate.
ItemUSD referenceList price (USD)
Input$0.1494$0.1494
Output$0.4482$0.4482
Cache read$0.0299$0.0299
Cache write$0.00$0.00
Context tier pricing: once a single request exceeds the tier's token count, that tier's rate applies (shown in USD1M tokens). 32K $0.2988
Specifications
- Form
- Text model
- Input modalities
- Image、Text、Video
- Output modalities
- Text
- Context length
- 131K
- Max output
- 33K
- Weights
- Open weights
- Family
- glm
- Knowledge cutoff
- 2025-04
- Released
- Dec 8, 2025
Uses and capabilities
Capabilities Text model、Function calling、Structured output、Reasoning、Prompt caching、Open weights
Function calling
Structured output
Reasoning
Prompt caching
Open weights
Sources
Use these links to verify specs and pricing — they may point to the vendor's site or to a third-party catalog.