z-ai

Z.ai: GLM 5.2 (free)

Z.ai: GLM 5.2 is a text-focused AI model with a substantial context length of up to 128,000 tokens and the ability to handle reasoning tasks effectively. While it does not support tools or structured output, it excels in generating comprehensive responses based on textual input. At this price point, Z.ai: GLM 5.2 is free to use, making it an accessible option for users looking to leverage AI without financial constraints. This model should be shortlisted by those prioritizing affordability and robust reasoning capabilities, though its performance in coding tasks or structured outputs might limit its applicability in specialized domains. With a blended benchmark score of 89.3 across four independent benchmarks, Z.ai: GLM 5.2 offers reliable performance for general text-based applications.

Quality Score
69/100
price + capability + benchmarks
Input Price
Free
per 1M tokens · checked 2026-08-17
Output Price
Free
per 1M tokens · checked 2026-08-17
Context Window
128,000
tokens

Benchmark results

Independent, published benchmarks. Blended score 89.3 across 4 benchmarks, last refreshed 2026-08-17. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 86.9
AI Index Coding software engineering tasks 100.0
AI Index Agentic multi-step tool-using tasks 75.4
EQ-Bench emotional understanding in dialogue 78.7
Model ID
z-ai/glm-5.2:free
Vendor
z-ai
Released
June 2026
Tokenizer
Other
Input Modalities
text
Output Modalities
text
Max Output
128,000 tokens
Tool Calling
not supported
Structured Output
not supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

Similar models

Quick answers

Is Z.ai: GLM 5.2 (free) free to use?
Yes. It is currently listed at no cost per token via OpenRouter, subject to provider rate limits.
What is Z.ai: GLM 5.2 (free)'s context window?
128,000 tokens, roughly 192 pages of text in a single request.
Does Z.ai: GLM 5.2 (free) support tool calling?
It supports a reasoning mode.
Can Z.ai: GLM 5.2 (free) process images?
No, it is text-only on the input side.