Z.ai: GLM 4.6
Analysis Summary
Z.ai GLM 4.6 is a text-only model with a 202K context window, tool use, and function calling. Its agentic index of 47.7 and coding index of 29.5 are strong for its intelligence tier, and its math score of 86 and GPQA of 0.780 reflect solid reasoning capability. It competes closely with Qwen3 Max and Kimi K2 0905 on agentic performance.
For businesses, GLM 4.6 suits agentic automation, multi-step tool use, and coding-assisted workflows. Its lack of vision limits use in document-image pipelines, and long-context reasoning is moderate. The model is not widely adopted in mainstream enterprise tooling, which may add integration friction for some teams.
At $0.43 input and $1.74 output per million tokens, pricing is mid-range. Teams comfortable with Z.ai's ecosystem who need strong agentic and coding capability at a reasonable cost will find GLM 4.6 a capable option, though a -4 point regional accessibility adjustment applies given limited enterprise adoption outside its home market.
Assessed June 17, 2026
Editorial notes
Z.ai GLM 4.6 delivers a strong agentic index and competitive coding performance with tool use and function calling, though limited enterprise adoption tempers its practical business reach.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Z.ai: GLM 4.6 compares
Z.ai: GLM 4.6 ranks #101 of 380 AI models we track for overall intelligence, #95 of 317 for coding, #100 of 292 for agentic tasks. Its 203K-token context window is larger than 66% of the models we list. At $0.43 per million input tokens it is cheaper than 36% of comparable models.
About Z.ai: GLM 4.6
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Z.ai: GLM 4.6 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
z-ai/glm-4.6
|
| Provider | z-ai |
| Release Date | September 30, 2025 |
| Context Length | 202,752 tokens |
| Max Completion | 131,072 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.43 | $0.000430 |
| Output | $1.74 | $0.001740 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Z.ai: GLM 4.6
How much does Z.ai: GLM 4.6 cost?
Z.ai: GLM 4.6 costs $0.43 per million input tokens and $1.74 per million output tokens.
What is the context window of Z.ai: GLM 4.6?
Z.ai: GLM 4.6 has a context window of 202,752 tokens (203K).
Is Z.ai: GLM 4.6 good for coding?
On our coding benchmark index, Z.ai: GLM 4.6 ranks #95 of 317 models, placing it in the broader range of the field for code generation and debugging.
What can Z.ai: GLM 4.6 do?
Z.ai: GLM 4.6 supports tool use and function calling.
Who created Z.ai: GLM 4.6?
Z.ai: GLM 4.6 is developed by Z.ai and was released on September 30, 2025.
