Skip to main content
Back to Explore

Qwen2.5 Turbo

Alibaba·Released 2024-11-18
131K ctx

About

Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.

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

113

tokens/sec

Faster than 60% of models

1.07

seconds

Faster than 52% of models

1.07

seconds

Faster than 67% of models

Market Median

94 tok/s

20% faster

Median TTFT

1.11s

4% faster

Throughput/Dollar

1286

tok/s per $/1M

Speed Comparison

Qwen3 30B A3B (Reasoning)
113 tok/s+0%
MiniMax: MiniMax M2
113 tok/s-1%
Qwen3 30B A3B (Non-reasoning)
111 tok/s-2%

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

Quick Compare

Similar Models

Compare all 7 models