Alibaba · all models ›

AQwen3.5-9BOPEN

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.

262KContext window · tokens
$0.1Input price · per M tokens
$0.15Output price · per M tokens
AlibabaProvider

Prices update automatically — checked daily against provider list prices.

See model comparisons → Compare all model prices

Benchmarks & performance

Independent benchmark scores for Qwen3.5-9B, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.

23×
More intelligence per dollar than Claude Opus 5 (Fast).
For the same budget, Qwen3.5-9B delivers 23 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Intelligence index21.8
Coding index28.7
GPQA80.6%
Humanity's Last Exam14.9%
Long Context Reasoning65.3%
SciCode27.5%
IFBench66.7%
τ²-Bench86.8%
τ-Bench Banking7%
Terminal-Bench29.2%
Terminal-Bench Hard24.2%
⚡ Speed84.3 tokens/sec
⏱ Latency1.19s to first token
💰 Blended price$0.151 / 1M tokens
📈 Value144.4 intelligence points per $
vs. models measured heretop 61%
Scores higher than 39% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $0.75 per 1M tokens (median of 14) — this one costs $0.11.
Cheaper and better on this index: DeepSeek V4 Flash 0731 · DeepSeek V4 Flash 0423 · Solar Pro 4 and 3 more
Benchmark data by Artificial Analysis

About this model

Qwen3.5-9B is an open-weight AI model by Alibaba. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.

Frequently asked questions

What is Qwen3.5-9B?

Qwen3.5-9B is an AI language model from Alibaba. It is open-weight: you can download it and run it on your own hardware, for free. It scores 21.8 on the Artificial Analysis intelligence index.

Is Qwen3.5-9B free?

The weights are free and open — you can self-host Qwen3.5-9B and pay nothing per token. If you prefer a hosted API, list prices are $0.1 per million input tokens and $0.15 per million output tokens.

What is Qwen3.5-9B good at?

Independent benchmarks from Artificial Analysis give it GPQA 80.6%, Humanity's Last Exam 14.9%, Long Context Reasoning 65.3%, SciCode 27.5%, IFBench 66.7%, τ²-Bench 86.8%, τ-Bench Banking 7%, Terminal-Bench 29.2%, Terminal-Bench Hard 24.2%. It is particularly used for code generation.

How fast is Qwen3.5-9B?

It generates about 84.3 tokens per second, with a median 1.19s delay before the first token. Measured independently by Artificial Analysis.

Can I self-host Qwen3.5-9B?

Yes. Qwen3.5-9B has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.

Related models

Qwen3.8 MaxAlibabaQwen3.8 27BAlibabaQwen3.7 FlashAlibabaQwen3.6 35B A3BAlibabaQwen3.7 PlusAlibabaQwen3 235B A22B Instruct 2507Alibaba