Skip to main content
Back to Explore

Qwen3 4B (Non-reasoning)

Alibaba·Released 2025-04-28
Open Source

Pricing

Input

$0.11

per 1M tokens

Output

$0.42

per 1M tokens

Blended

$0.19

per 1M tokens

Cheaper than 71% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.19

Monthly

$5.64

vs. Similar Models

Llama 3.1 Instruct 70BQ:0.0
$0.56+198%
Ministral 3 3BQ:0.0
$0.10-47%
Qwen3 30B A3B (Non-reasoning)Q:0.0
$0.13-29%
IBM: Granite 4.1 8BQ:-0.1
$0.06-67%

Performance

104

tokens/sec

Faster than 56% of models

1.02

seconds

Faster than 55% of models

1.02

seconds

Faster than 69% of models

Market Median

94 tok/s

10% faster

Median TTFT

1.11s

9% faster

Throughput/Dollar

554

tok/s per $/1M

Speed Comparison

Qwen3 4B (Reasoning)
104 tok/s-0%
Z.ai: GLM 4.7 Flash
105 tok/s+0%
Claude 4.5 Haiku (Non-reasoning)
104 tok/s-1%

Benchmarks

MMLU-Pro
58.6%
GPQA Diamond
39.8%
HLE
3.7%
LiveCodeBench
23.3%
SciCode
16.7%
TerminalBench HardNot evaluated
MATH-500
84.3%
AIME
21.3%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models