qwen
Qwen: Qwen3.5-9B
qwen/qwen3.5-9b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
qwen/qwen3.5-9b is the post-trained Qwen3.5 9B model, offered through OpenRouter as a text-output model that accepts text, image, and video input. Its Hugging Face card describes a unified vision-language design, a hybrid Gated DeltaNet and gated-attention architecture, native long-context support with a much larger extension option, and broad multilingual coverage. Qwen reports benchmark results spanning knowledge, instruction following, long context, reasoning, coding, and agent tasks, while OpenRouter lists tool, structured-output, and reasoning-related parameters. These figures and feature claims still warrant workload-specific validation.[1][2]
Strengths
- Accepts text, image, and video input while producing text, according to the OpenRouter modality listing.[1][2]
- The model card reports native long-context support with an option to extend it further, plus compatibility with Transformers, vLLM, SGLang, and KTransformers.[2]
- Vendor-published benchmark tables cover knowledge, instruction following, long context, reasoning, coding, and agentic tasks, and OpenRouter exposes tools, tool choice, structured outputs, and reasoning-related controls.[1][2]
Limitations
- Evidence is limited to a catalog entry and a vendor model card; OpenRouter's aggregated benchmark fields are sparse or partly unpopulated.[1][2]
- OpenRouter leaves knowledge cutoff, reasoning defaults, and supported reasoning efforts unspecified, and lists text as the only output modality.[1]
- Vendor claims of efficiency, parity, and benchmark performance are source-reported rather than independently verified here and may differ across prompts, languages, and deployment stacks.[2]
Where to use it
- A possible fit for assistants that must interpret screenshots, documents with images, or video frames and return text, subject to application-level testing.[1][2]
- Worth evaluating for multilingual chat, retrieval, or document-analysis workloads where long context and tool calling are needed.[1][2]
- Could be prototyped for coding or agent workflows because vendor results and API tool parameters point that way, but agentic support should be verified rather than assumed.[1][2]
Sources
- [1] OpenRouter catalog · Qwen: Qwen3.5-9BSources checked: Nov 13, 2026
- [2] Model documentation · Qwen: Qwen3.5-9BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- qwen/qwen3.5-9b
- Canonical ID
- qwen/qwen3.5-9b-20260310
- Creator
- qwen
- Added to OpenRouter
- 10.03.2026
- Context length
- 262,144
- Modality
- text+image+video->text
- Input modalities
- text, image, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.067 / out $0.099
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 28.7 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 1.2 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| PrimeIntellectbf16 | 262,144 | $0.072 | $0.106 | — | — | 100% |
| Darkbloomfp4 | 262,144 | $0.080 | $0.130 | — | — | 100% |
| SiliconFlowfp8 | 262,144 | $0.100 | $0.150 | — | — | 100% |
| DeepInfrabf16 | 262,144 | $0.100 | $0.150 | — | — | 100% |
| Parasailbf16 | 262,144 | $0.100 | $0.250 | — | — | 6.67% |
| Together | 262,144 | $0.170 | $0.250 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.