About
Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...
Related Models
Pricing
Input
$0.78
per 1M tokens
Output
$3.90
per 1M tokens
Blended
$1.56
per 1M tokens
Cheaper than 28% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.56
Monthly
$46.80
vs. Similar Models
Qwen3.6 35B A3B (Non-reasoning)Q:+0.2
$0.84-46%
OpenAI: gpt-oss-120bQ:-0.2
$0.06-96%
Claude 4.5 Haiku (Non-reasoning)Q:-0.3
$2.00+28%
Arcee AI: Trinity Large ThinkingQ:+0.5
$0.39-75%
Performance
59
tokens/sec
Faster than 27% of models
1.90
seconds
Faster than 23% of models
1.90
seconds
Faster than 51% of models
Market Median
94 tok/s
38% slower
Median TTFT
1.11s
71% slower
Throughput/Dollar
38
tok/s per $/1M
Speed Comparison
Anthropic: Claude Opus 4.8
58 tok/s-0%
Grok Build 0.1 0616
58 tok/s-1%
Qwen3 VL 235B A22B (Reasoning)
58 tok/s-1%
Context Window
262K
tokens
Larger than 62% of models
Max Output
33K
tokens
13% of context
Benchmarks
MMLU-Pro
84.1%
GPQA Diamond
76.4%
HLE
11.1%
LiveCodeBench
76.7%
SciCode
38.3%
TerminalBench Hard
20.5%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
80.7%
IFBench
44.1%
Long Context Recall
46.7%
Tau2
74.3%
Market AverageTop Score