z-ai

Z.ai: GLM 5

Z.ai: GLM 5 is capable of handling text inputs within a vast context length of 204,800 tokens and supports tools and reasoning processes, making it suitable for complex tasks that require deep analysis. While it does not offer structured output or open weights, this model excels in versatile applications where detailed input modalities are crucial. This model is recommended for users who need robust text processing capabilities at a blended benchmark score of 76.7 across two independent benchmarks; however, its pricing of $0.95 per million input tokens and $2.55 per million output tokens may be a consideration for those on tighter budgets.

Quality Score
98/100
price + capability + benchmarks
Input Price
$0.95
per 1M tokens
Output Price
$2.55
per 1M tokens
Context Window
204,800
tokens

Benchmark results

Independent, published benchmarks. Blended score 76.7 across 2 benchmarks, last refreshed 2026-08-13. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 66.9
EQ-Bench emotional understanding in dialogue 75.0
Model ID
z-ai/glm-5
Vendor
z-ai
Released
February 2026
Tokenizer
Other
Input Modalities
text
Output Modalities
text
Max Output
131,072 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.95/M input and $2.55/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.03
Classify 1,000 customer emails 500k in / 50k out $0.60
A month of a busy support chatbot 5M in / 2M out $9.85

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-07-20 $0.95 $2.55 204,800
2026-07-17 $0.95 $3.15 202,752

Similar models

Quick answers

How much does Z.ai: GLM 5 cost?
$0.95 per million input tokens and $2.55 per million output tokens.
What is Z.ai: GLM 5's context window?
204,800 tokens, roughly 307 pages of text in a single request.
Does Z.ai: GLM 5 support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Z.ai: GLM 5 process images?
No, it is text-only on the input side.