Skip to main content
Back to Explore

GLM-4.6 (Reasoning)

Z AI·Released 2025-09-30
Open Source

Pricing

Input

$0.55

per 1M tokens

Output

$2.20

per 1M tokens

Blended

$0.96

per 1M tokens

Cheaper than 36% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.96

Monthly

$28.89

vs. Similar Models

Qwen: Qwen3.5-9BQ:-0.1
$0.11-88%
Google: Gemini 3.1 Flash Lite PreviewQ:-0.1
$0.56-42%
Qwen3 Max Thinking (Preview)Q:-0.1
$2.40+149%
Inception: Mercury 2Q:+0.2
$0.38-61%

Performance

51

tokens/sec

Faster than 19% of models

1.43

seconds

Faster than 36% of models

40.48

seconds

Faster than 10% of models

Market Median

95 tok/s

46% slower

Median TTFT

1.11s

29% slower

Throughput/Dollar

53

tok/s per $/1M

Speed Comparison

MiniMax: MiniMax M2.7
51 tok/s-0%
Qwen: Qwen3 VL 235B A22B Instruct
52 tok/s+1%
Claude 4.5 Sonnet (Reasoning)
52 tok/s+1%

Benchmarks

MMLU-Pro
82.9%
GPQA Diamond
78.0%
HLE
13.3%
LiveCodeBench
69.5%
SciCode
38.4%
TerminalBench Hard
25.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
86.0%
IFBench
43.4%
Long Context Recall
54.3%
Tau2
70.5%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models