Skip to main content
Back to Explore

Qwen3 8B (Non-reasoning)

Alibaba·Released 2025-04-28
Open Source

Pricing

Input

$0.18

per 1M tokens

Output

$0.20

per 1M tokens

Blended

$0.18

per 1M tokens

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

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.18

Monthly

$5.55

vs. Similar Models

Jamba 1.5 LargeQ:0.0
$3.50+1792%
Nous: Hermes 3 70B InstructQ:0.0
$0.70+278%
Qwen3 Omni 30B A3B InstructQ:0.0
$0.43+132%
Qwen3.5 0.8BQ:-0.1
$0.02-89%

Performance

62

tokens/sec

Faster than 30% of models

1.57

seconds

Faster than 33% of models

1.57

seconds

Faster than 57% of models

Market Median

94 tok/s

34% slower

Median TTFT

1.10s

42% slower

Throughput/Dollar

333

tok/s per $/1M

Speed Comparison

Claude Opus 4.5 (Reasoning)
62 tok/s+0%
Qwen3 235B A22B (Non-reasoning)
61 tok/s-0%
GLM-5.1 (Non-reasoning)
62 tok/s+1%

Benchmarks

MMLU-Pro
64.3%
GPQA Diamond
45.2%
HLE
2.8%
LiveCodeBench
20.2%
SciCode
16.8%
TerminalBench Hard
2.3%
MATH-500
82.8%
AIME
24.3%
AIME 2025
24.3%
IFBench
28.6%
Long Context Recall
0.0%
Tau2
24.9%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models