About
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
Related Models
Pricing
Input
$0.60
per 1M tokens
Output
$1.92
per 1M tokens
Blended
$0.93
per 1M tokens
Cheaper than 37% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.93
Monthly
$27.90
vs. Similar Models
Gemini 3 Pro Preview (high)Q:+0.1
$4.50+384%
Qwen: Qwen3.6 PlusQ:+0.1
$0.73-21%
Grok Build 0.1 0616Q:+0.3
$1.25+34%
GPT-5.4 (low)Q:-0.4
$5.91+535%
Performance
70
tokens/sec
Faster than 35% of models
0.70
seconds
Faster than 71% of models
44.98
seconds
Faster than 9% of models
Market Median
94 tok/s
26% slower
Median TTFT
1.11s
37% faster
Throughput/Dollar
75
tok/s per $/1M
Speed Comparison
GPT-5.5 (low)
70 tok/s+0%
GPT-5.5 (medium)
71 tok/s+1%
NVIDIA Nemotron Nano 9B V2 (Reasoning)
71 tok/s+1%
Context Window
203K
tokens
Larger than 55% of models
Max Output
128K
tokens
63% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
82.0%
HLE
27.2%
LiveCodeBenchNot evaluated
SciCode
46.2%
TerminalBench Hard
43.2%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
72.3%
Long Context Recall
63.3%
Tau2
98.2%
Market AverageTop Score