Well-known prior open-weight model, still documented and available (200K context). docs.z.ai/guides/llm/glm-4.6 model id verbatim: "model": "glm-4.6"; overview: 'GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, sear
profile normalized against the 70-model field
Context window· 200K of 10M2%
Max output· 131K of 384K34%
Output speed—
Affordability· $2.20 / Mtok out99%
Capability breadth· 2 of 1118%
Capability switches · 2 of 11
Reasoning mode
Tool / function use
Streaming
JSON mode
Structured outputs
Prompt caching
Fine-tuning
Web search
Code execution
Vision input
Audio input
Specifications
Every value carries a primary source and a verification date.
Capacity
Context window
200K
Parameters
355B-A32B
Max output
131K
Pricing
Input $/Mtok
$0.60 / 1M input tokens USD per 1M tokens
Cached input $/Mtok
$0.11 / Mtok USD/Mtok
Output $/Mtok
$2.20 / 1M output tokens USD per 1M tokens
Capabilities
Reasoning mode
Yes
Tool / function use
Yes
Vision input
No
API
API model ID
glm-4.6
General
Release date
September 29, 2025
License
mit
Benchmarks
Sourced evaluation scores, each verified against its primary source.
CC-Bench (real-world coding, win rate vs Claude Sonnet 4)