Skip to main content
Back to Explore

Qwen3.5 2B (Non-reasoning)

Alibaba·Released 2026-03-02
Open Source

Pricing

Input

$0.02

per 1M tokens

Output

$0.10

per 1M tokens

Blended

$0.04

per 1M tokens

Cheaper than 91% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.04

Monthly

$1.20

vs. Similar Models

Gemini 2.0 Flash-Lite (Feb '25)Q:0.0
$0.13+228%
Hermes 4 - Llama-3.1 405B (Non-reasoning)Q:0.0
$1.50+3650%
NVIDIA Nemotron Nano 9B V2 (Reasoning)Q:0.0
$0.07+75%
Gemma 4 E4B (Non-reasoning)Q:+0.1
$0.54+1243%

Performance

27

tokens/sec

Faster than 2% of models

0.42

seconds

Faster than 94% of models

0.42

seconds

Faster than 96% of models

Market Median

94 tok/s

72% slower

Median TTFT

1.10s

62% faster

Throughput/Dollar

664

tok/s per $/1M

Speed Comparison

MoonshotAI: Kimi K2 0711
26 tok/s-1%
Gemma 3 12B Instruct
26 tok/s-2%
MoonshotAI: Kimi K2 0905
26 tok/s-3%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
43.8%
HLE
4.9%
LiveCodeBenchNot evaluated
SciCode
7.2%
TerminalBench Hard
3.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
29.1%
Long Context Recall
13.7%
Tau2
81.6%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models