z-ai

Z.ai: GLM 4.5

Z.ai: GLM 4.5 is designed to process text inputs up to a context length of 131,072 tokens and can generate up to 98,304 completion tokens. It supports reasoning capabilities and tools integration but does not provide structured output. While it covers two benchmark categories-AI Index and Eqbench-it does not offer open-source weights or structured data outputs. Given its blended benchmark score of 53.1 across these benchmarks, Z.ai: GLM 4.5 is particularly suitable for projects requiring robust text-based reasoning and tool integration within a budget. Its pricing at $0.6 per million input tokens and $2.2 per million output tokens makes it cost-effective for applications where text processing and basic reasoning are key needs.

Quality Score
90/100
price + capability + benchmarks
Input Price
$0.60
per 1M tokens
Output Price
$2.20
per 1M tokens
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 53.1 across 2 benchmarks, last refreshed 2026-07-21. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 32.2
EQ-Bench emotional understanding in dialogue 67.4
Model ID
z-ai/glm-4.5
Vendor
z-ai
Released
July 2025
Tokenizer
Other
Input Modalities
text
Output Modalities
text
Max Output
98,304 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 $0.60/M input and $2.20/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.02
Classify 1,000 customer emails 500k in / 50k out $0.41
A month of a busy support chatbot 5M in / 2M out $7.40

Similar models

Quick answers

How much does Z.ai: GLM 4.5 cost?
$0.60 per million input tokens and $2.20 per million output tokens.
What is Z.ai: GLM 4.5's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does Z.ai: GLM 4.5 support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Z.ai: GLM 4.5 process images?
No, it is text-only on the input side.