About
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Related Models
Pricing
Input
$0.95
per 1M tokens
Output
$3.00
per 1M tokens
Blended
$1.46
per 1M tokens
Cheaper than 30% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.46
Monthly
$43.88
vs. Similar Models
OpenAI: GPT-5.4Q:+0.3
$5.63+285%
GPT-5.5 (medium)Q:-0.7
$11.25+669%
Google: Gemini 3.5 FlashQ:-0.9
$3.38+131%
GPT-5.5 (high)Q:+2.0
$11.25+669%
Performance
135
tokens/sec
Faster than 67% of models
0.84
seconds
Faster than 63% of models
15.62
seconds
Faster than 31% of models
Market Median
94 tok/s
43% faster
Median TTFT
1.11s
24% faster
Throughput/Dollar
93
tok/s per $/1M
Speed Comparison
Qwen3 VL 8B (Reasoning)
135 tok/s-0%
Anthropic: Claude 3 Haiku
134 tok/s-1%
OpenAI: GPT-4.1
134 tok/s-1%
Context Window
1.0M
tokens
Larger than 90% of models
Max Output
33K
tokens
3% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
89.5%
HLE
40.1%
LiveCodeBenchNot evaluated
SciCode
50.5%
TerminalBench Hard
50.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
73.3%
Long Context Recall
71.3%
Tau2
99.1%
Market AverageTop Score