Qwen3.5-9B
Qwen· released 10 Mar 2026
qwen/qwen3.5-9b- Input / 1M tokens
- $0.1
- Output / 1M tokens
- $0.15
Longest answer: 33K tokens
About
Qwen3.5-9B is a 9B-parameter multimodal foundation model from Qwen’s Qwen3.5 family. It is designed for reasoning, coding, and visual understanding, using a unified vision-language design. The model accepts text, image, and video inputs and returns text. It supports tools and vision, includes reasoning, has a context window of 262,144 tokens, and allows up to 32,768 output tokens. Its weights are open, and its Hugging Face identifier is Qwen/Qwen3.5-9B. Released on 2026-03-10, it is listed as qwen/qwen3.5-9b. Pricing is USD 0.1 per 1M input tokens and USD 0.15 per 1M output tokens. Teams can assess its multimodal inputs and stated task areas alongside the context and output limits when deciding whether it fits their stack.
Who it is for
It suits teams looking for an open-weight model with text, image, and video inputs for reasoning, coding, or visual understanding. Tool support and the long context may also matter to workflow planning.
What is good
- Open weights
- Accepts text, image, and video inputs
- Tools and vision are supported
- 262,144-token context window
- Maximum output is 32,768 tokens
What to know first
- Output is text only
Verdict
Qwen3.5-9B pairs multimodal inputs with stated reasoning, coding, and visual-understanding aims. Its open weights and 262,144-token context are notable fit details, with text as the only listed output modality.
Details
- Lab
- Qwenopenrouter.ai · 3 Oct 2026
- Context
- 262Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.1 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $0.15 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 32,768 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, image, videoopenrouter.ai · 3 Oct 2026
- Open weights
- Yesopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- Open-Weight Models in 2026178 listed
- Qwen Models: Pricing per 1M Tokens and Context (2026)52 listed
Sources
- openrouter.ai/qwen/qwen3.5-9b· checked 3 Oct 2026