GLM 4.6

Model

by Z.ai

Vendor:Z.ai
Model Size:9B
Context Window:204,800 tokens
Max Output:131,072 tokens

Specifications

Model Size

9B

Total Context

204.8K

Max Output

131.1K

Pricing

Input $0.6/M

Output $2.2/M

Cache $0.11/M

Performance Benchmarks

components.product.sweBench

55.4%

components.product.sweBenchDesc

components.product.terminalBench

24.5%

components.product.terminalBenchDesc

components.product.mmmu

68.0%

components.product.mmmuDesc

GLM 4.6 - AI Coding Model | Specs & Pricing 2025 - AI Coding Stack