About
Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.
Related Models
Pricing
Input
$0.05
per 1M tokens
Output
$0.20
per 1M tokens
Blended
$0.09
per 1M tokens
Cheaper than 85% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.09
Monthly
$2.64
vs. Similar Models
Reka Flash (Sep '24)Q:0.0
$0.35+298%
Llama 3.2 Instruct 90B (Vision)Q:-0.1
$1.38+1468%
Solar MiniQ:-0.1
$0.15+70%
AllenAI: Olmo 3 32B ThinkQ:+0.1
$0.24+170%
Performance
109
tokens/sec
Faster than 58% of models
1.06
seconds
Faster than 53% of models
1.06
seconds
Faster than 67% of models
Market Median
95 tok/s
15% faster
Median TTFT
1.11s
4% faster
Throughput/Dollar
1239
tok/s per $/1M
Speed Comparison
KAT-Coder-Pro V1
109 tok/s+0%
Meta: Llama 4 Scout
109 tok/s+0%
Kwaipilot: KAT-Coder-Pro V2
110 tok/s+0%
Context Window
131K
tokens
Larger than 27% of models
Max Output
8K
tokens
6% of context
Benchmarks
MMLU-Pro
63.3%
GPQA Diamond
41.0%
HLE
4.2%
LiveCodeBench
16.3%
SciCode
15.3%
TerminalBench HardNot evaluated
MATH-500
80.5%
AIME
12.0%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score