About
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
Related Models
Pricing
Input
$0.10
per 1M tokens
Output
$0.15
per 1M tokens
Blended
$0.11
per 1M tokens
Cheaper than 82% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.11
Monthly
$3.37
vs. Similar Models
Google: Gemini 3.1 Flash Lite PreviewQ:0.0
$0.56+400%
Qwen3 Max Thinking (Preview)Q:0.0
$2.40+2033%
GLM-4.6 (Reasoning)Q:+0.1
$0.96+756%
Gemma 4 31B (Non-reasoning)Q:-0.2
$0.20+82%
Performance
68
tokens/sec
Faster than 34% of models
0.88
seconds
Faster than 61% of models
30.46
seconds
Faster than 16% of models
Market Median
94 tok/s
28% slower
Median TTFT
1.11s
21% faster
Throughput/Dollar
601
tok/s per $/1M
Speed Comparison
DeepSeek: R1 Distill Llama 70B
67 tok/s-1%
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
68 tok/s+1%
GPT-5.2 (Non-reasoning)
67 tok/s-1%
Context Window
262K
tokens
Larger than 62% of models
Max Output
262K
tokens
100% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
80.6%
HLE
13.3%
LiveCodeBenchNot evaluated
SciCode
27.5%
TerminalBench Hard
24.2%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
66.7%
Long Context Recall
59.0%
Tau2
86.8%
Market AverageTop Score
Open Source
apache-2.09BGGUF / GPTQ / AWQ
Downloads
9.2M
Likes
1.6K
VRAM (FP16)
16-24 GB
GPU
RTX 4090 / M2 Max