Skip to main content
Back to Explore

Qwen3.5 0.8B (Non-reasoning)

Alibaba·Released 2026-03-02
Open Source

Pricing

Input

$0.01

per 1M tokens

Output

$0.05

per 1M tokens

Blended

$0.02

per 1M tokens

Cheaper than 92% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.02

Monthly

$0.60

vs. Similar Models

Mistral LargeQ:0.0
$3.00+14900%
Qwen2.5 Coder 7B InstructQ:+0.1
$0.04+125%
Llama 2 Chat 7BQ:-0.1
$0.10+400%
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)Q:+0.2
$0.30+1400%

Performance

29

tokens/sec

Faster than 2% of models

0.48

seconds

Faster than 88% of models

0.48

seconds

Faster than 93% of models

Market Median

94 tok/s

69% slower

Median TTFT

1.10s

56% faster

Throughput/Dollar

1430

tok/s per $/1M

Speed Comparison

Qwen3.5 0.8B
29 tok/s-0%
Nous: Hermes 3 70B Instruct
29 tok/s+2%
Qwen3.5 2B
28 tok/s-3%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
23.6%
HLE
4.9%
LiveCodeBenchNot evaluated
SciCode
2.9%
TerminalBench Hard
0.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
21.6%
Long Context Recall
6.7%
Tau2
65.2%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models