All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3.5 9B

Qwen instruction model for multilingual chat, reasoning, and tool use

Model facts

Context window
262K tokens
Maximum output
66K tokens
Cheapest paid input
$0.04 per 1M tokens
Cheapest paid output
$0.15 per 1M tokens
Open weights
yes
Providers
21

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, audio, video.

Local hardware estimate

At 4K context: Q4_K_M 6.9 GiB, Q8_0 11.4 GiB, F16 19.8 GiB working memory.

Parameters
9.7 billion
Architecture
qwen3_5
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning21.828.7not measured84.6
Non-reasoning20.623.5not measured94.9

Observed price history

  • 2026-08-24: $0.04 input / $0.15 output per 1M tokens

API providers