Loading...
About
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Related Models
Pricing
Input
$0.39
per 1M tokens
Output
$1.90
per 1M tokens
Blended
$0.77
per 1M tokens
Cheaper than 44% of models. Median price is $0.56/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.77
Monthly
$23.02
vs. Similar Models
Z.ai: GLM 4.7 FlashQ:-0.1
$0.14-81%
Google: Gemma 4 26B A4B Q:+0.1
$0.13-83%
Xiaomi: MiMo-V2-FlashQ:+0.2
$0.15-80%
Qwen3.5 35B A3B (Non-reasoning)Q:+0.5
$0.69-10%
Performance
30
tokens/sec
Faster than 3% of models
1.23
seconds
Faster than 41% of models
1.23
seconds
Faster than 60% of models
Market Median
86 tok/s
65% slower
Median TTFT
1.07s
14% slower
Throughput/Dollar
39
tok/s per $/1M
Speed Comparison
Mistral Large 2 (Nov '24)
30 tok/s-1%
xAI: Grok 3
30 tok/s-1%
GLM-4.6V (Reasoning)
31 tok/s+5%
Context Window
205K
tokens
Larger than 62% of models
Max Output
205K
tokens
100% of context
Benchmarks
MMLU-Pro
78.4%
GPQA Diamond
63.2%
HLE
5.2%
LiveCodeBench
56.1%
SciCode
33.1%
TerminalBench Hard
28.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
44.3%
IFBench
36.7%
Long Context Recall
26.3%
Tau2
76.9%
Market AverageTop Score