Qwen3.6 27B
Summary
Qwen3.6 27B is an open-weight language model from Alibaba (Qwen), released on 22 Apr 2026. It accepts text, images, video and audio and generates text, with a 262K-token context window and up to 66K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.30 per million input tokens and $3.20 per million output tokens (SiliconFlow), across 7 providers we track.
Qwen vision-language model for visual reasoning, documents, and agent tasks
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 22 Apr 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 27.8B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 66K tokens [models.dev] |
| Input | Text, images, video and audio [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | Qwen/Qwen3.6-27B [Hugging Face] |
Qwen3.6 27B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| SiliconFlow Qwen/Qwen3.6-27B | $0.30 | $3.20 | – | 262K | models.dev, 4 Oct 2026 |
| DeepInfra Qwen/Qwen3.6-27B | $0.32 | $3.20 | – | 262K | models.dev, 4 Oct 2026 |
| OpenRouter qwen/qwen3.6-27b | $0.32 | $3.20 | – | 262K | OpenRouter, 4 Oct 2026 |
| Hugging Face Inference Providers Qwen/Qwen3.6-27B | $0.47 | $3.19 | – | 262K | models.dev, 4 Oct 2026 |
| Alibaba Cloud Model Studio qwen3.6-27b | $0.60 | $3.60 | – | 262K | models.dev, 4 Oct 2026 |
| Groq qwen/qwen3.6-27b | $0.60 | $3 | $0.30 | 131K | models.dev, 4 Oct 2026 |
| Vercel AI Gateway alibaba/qwen3.6-27b | $0.60 | $3.60 | – | 256K | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of Qwen3.6 27B?
Qwen3.6 27B has a context window of 262,144 tokens (262K) and can generate up to 65,536 tokens in a single response, according to models.dev.
How much does the Qwen3.6 27B API cost?
Through Alibaba Cloud Model Studio, Qwen3.6 27B costs $0.60 per million input tokens and $3.60 per million output tokens. The lowest listed price is $0.30 input / $3.20 output through SiliconFlow. Prices last verified 4 Oct 2026.
Is Qwen3.6 27B open source?
Qwen3.6 27B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3.6-27B under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3.6 27B released?
Alibaba (Qwen) released Qwen3.6 27B on 22 Apr 2026, according to models.dev.
Which providers offer Qwen3.6 27B?
We track Qwen3.6 27B on 7 providers: SiliconFlow, DeepInfra, OpenRouter, Hugging Face Inference Providers, Alibaba Cloud Model Studio, Groq, Vercel AI Gateway.
Change history
No changes detected since we started tracking this model. We re-check every source daily.
Sources
- https://openrouter.ai/qwen/qwen3.6-27b
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.6-27b.toml
- https://huggingface.co/Qwen/Qwen3.6-27B
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/Qwen/Qwen3.6-27B.toml
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.6-27B.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3.6-27B.toml
- https://github.com/sst/models.dev/blob/dev/providers/groq/models/qwen/qwen3.6-27b.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/alibaba/qwen3.6-27b.toml