Skip to main content
Back to Explore

Qwen3.5 4B (Non-reasoning)

Alibaba·Released 2026-03-02
Open Source

Pricing

Input

$0.03

per 1M tokens

Output

$0.15

per 1M tokens

Blended

$0.06

per 1M tokens

Cheaper than 88% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.06

Monthly

$1.80

vs. Similar Models

Mistral Large 3Q:-0.1
$0.75+1150%
Qwen3 30B A3B 2507 (Reasoning)Q:-0.2
$0.67+1022%
OpenAI: GPT-4.1 MiniQ:+0.3
$0.70+1067%
DeepSeek V3 0324Q:-0.3
$1.21+1915%

Performance

40

tokens/sec

Faster than 9% of models

0.56

seconds

Faster than 82% of models

0.56

seconds

Faster than 88% of models

Market Median

94 tok/s

58% slower

Median TTFT

1.10s

50% faster

Throughput/Dollar

660

tok/s per $/1M

Speed Comparison

Hermes 4 - Llama-3.1 405B (Non-reasoning)
40 tok/s+0%
Devstral 2
40 tok/s+1%
Devstral Small (Jul '25)
40 tok/s+1%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
71.2%
HLE
7.5%
LiveCodeBenchNot evaluated
SciCode
18.3%
TerminalBench Hard
11.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
33.3%
Long Context Recall
28.3%
Tau2
87.7%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models