About
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...
Related Models
Pricing
Input
$0.40
per 1M tokens
Output
$1.75
per 1M tokens
Blended
$0.74
per 1M tokens
Cheaper than 45% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.74
Monthly
$22.13
vs. Similar Models
Qwen3.5 27BQ:0.0
$0.54-27%
MiniMax: MiniMax M2.5Q:-0.1
$0.21-72%
Qwen: Qwen3.5 397B A17BQ:-0.1
$0.90+22%
Claude 4.1 Opus (Reasoning)Q:-0.1
$30.00+3968%
Performance
119
tokens/sec
Faster than 61% of models
0.61
seconds
Faster than 76% of models
17.46
seconds
Faster than 28% of models
Market Median
94 tok/s
26% faster
Median TTFT
1.11s
45% faster
Throughput/Dollar
161
tok/s per $/1M
Speed Comparison
GLM-4.7 (Non-reasoning)
119 tok/s-0%
Grok 4.3 (Non-reasoning)
119 tok/s+0%
Qwen3 VL 30B A3B Instruct
120 tok/s+1%
Context Window
203K
tokens
Larger than 55% of models
Max Output
131K
tokens
65% of context
Benchmarks
MMLU-Pro
85.6%
GPQA Diamond
85.9%
HLE
25.1%
LiveCodeBench
89.4%
SciCode
45.1%
TerminalBench Hard
31.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
95.0%
IFBench
67.9%
Long Context Recall
64.0%
Tau2
95.9%
Market AverageTop Score