qwen
Qwen: Qwen3.5-27B
qwen/qwen3.5-27b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
qwen/qwen3.5-27b is a post-trained vision-language model that OpenRouter lists as accepting text, image, and video inputs and producing text. Its catalog description calls it dense, while the model documentation details Gated DeltaNet linear-attention blocks alongside gated attention and a long native context that can be extended further. Vendor-published results cover knowledge, instruction following, long-context reasoning, STEM, and coding, but they are self-reported rather than independent verification.[1][2]
Strengths
- Accepts text, image, and video inputs and returns text, according to the OpenRouter catalog; the model documentation identifies it as a post-trained vision-language model.[1][2]
- Its hybrid design pairs Gated DeltaNet linear-attention blocks with gated attention, and its documented long context can be extended beyond the native window.[2]
- The documentation lists compatibility with Hugging Face Transformers, vLLM, SGLang, and KTransformers, while the catalog exposes tools, structured outputs, and common sampling controls.[1][2]
Limitations
- The only performance evidence supplied is vendor-published; OpenRouter catalog benchmark fields are empty, so workload-specific validation remains necessary.[1][2]
- Video input appears in the OpenRouter modality listing, but the supplied model card uses an image-text-to-text pipeline tag; confirm video support on the intended serving path.[1][2]
- The sources do not specify a knowledge cutoff, hardware requirements, or the setup needed for extended context; absence of these fields is an evidence gap, not proof of a limitation.[1][2]
Where to use it
- Multimodal assistants that turn images or catalog-supported video into text, after confirming the provider's video pipeline.[1][2]
- Long-document summarization, retrieval, or review where the extended context may reduce chunking, with validation at the target lengths.[2]
- Tool-using or structured-output workflows, because the API listing exposes those controls; agent reliability still needs task-level testing.[1]
Sources
- [1] OpenRouter catalog · Qwen: Qwen3.5-27BSources checked: Nov 13, 2026
- [2] Model documentation · Qwen: Qwen3.5-27BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...
Specifications
- Model ID
- qwen/qwen3.5-27b
- Canonical ID
- qwen/qwen3.5-27b-20260224
- Creator
- qwen
- Added to OpenRouter
- 25.02.2026
- Context length
- 262,144
- Modality
- text+image+video->text
- Input modalities
- text, image, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.260 / out $2.6
- 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 | No measurement | — |
| Agents | No measurement | 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
No evaluations are supplied for this model.
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) |
|---|---|---|---|---|---|---|
| Alibaba | 262,144 | $0.195 | $1.56 | — | — | 100% |
| Chutesfp8 | 262,144 | $0.200 | $1.75 | — | — | 88.89% |
| SiliconFlowfp8 | 262,144 | $0.250 | $2 | — | — | 100% |
| DeepInfrafp8 | 262,144 | $0.260 | $2.6 | — | — | 100% |
| AtlasCloudfp8 | 262,144 | $0.270 | $2.16 | — | — | 100% |
| Novitabf16 | 262,144 | $0.300 | $2.4 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.