Qwen3.5 27B
Summary
Qwen3.5 27B is an open-weight language model from Alibaba (Qwen), released on 23 Feb 2026. It accepts text, images and video and generates text, with a 262K-token context window and up to 66K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.25 per million input tokens and $2 per million output tokens (SiliconFlow), across 6 providers we track.
Qwen vision-language model for visual reasoning, documents, and agent tasks
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 23 Feb 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] |
| Knowledge cutoff | Apr 2025 [models.dev] |
| Input | Text, images and video [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | Qwen/Qwen3.5-27B [Hugging Face] |
Qwen3.5 27B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| SiliconFlow Qwen/Qwen3.5-27B | $0.25 | $2 | – | 262K | models.dev, 18 Nov 2026 |
| DeepInfra Qwen/Qwen3.5-27B | $0.26 | $2.60 | – | 262K | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3.5-27b | $0.26 | $2.60 | – | 262K | OpenRouter, 18 Nov 2026 |
| Alibaba Cloud Model Studio qwen3.5-27b | $0.30 | $2.40 | – | 262K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers Qwen/Qwen3.5-27B | $0.30 | $2.40 | – | 262K | models.dev, 18 Nov 2026 |
| Novita AI qwen/qwen3.5-27b | $0.30 | $2.40 | – | 262K | models.dev, 18 Nov 2026 |
Running Qwen3.5 27B locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 17 GB | 18 GB | 20 GB |
| Q8_0 (8-bit) | 30 GB | 31 GB | 32 GB |
| FP16 / BF16 (16-bit) | 56 GB | 57 GB | 59 GB |
At 4-bit with an 8K conversation, Qwen3.5 27B needs about 18 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.
Frequently asked questions
What is the context window of Qwen3.5 27B?
Qwen3.5 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 Qwen3.5 27B API cost?
Through Alibaba Cloud Model Studio, Qwen3.5 27B costs $0.30 per million input tokens and $2.40 per million output tokens. The lowest listed price is $0.25 input / $2 output through SiliconFlow. Prices last verified 18 Nov 2026.
Is Qwen3.5 27B open source?
Qwen3.5 27B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3.5-27B under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3.5 27B released?
Alibaba (Qwen) released Qwen3.5 27B on 23 Feb 2026, according to models.dev.
Which providers offer Qwen3.5 27B?
We track Qwen3.5 27B on 6 providers: SiliconFlow, DeepInfra, OpenRouter, Alibaba Cloud Model Studio, Hugging Face Inference Providers, Novita AI.
How much VRAM does Qwen3.5 27B need?
About 18 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 31 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Kimi K2.5 | Moonshot AI | 27 Jan 2026 | 262K | $0.45 | $2.25 | Open |
| GLM-4.7 | Zhipu AI (Z.ai) | 22 Dec 2025 | 205K | $0.40 | $1.75 | Open |
| GLM-5 | Zhipu AI (Z.ai) | 12 Feb 2026 | 205K | $0.95 | $2.55 | Open |
| Kimi K2.6 | Moonshot AI | 20 Apr 2026 | 262K | $0.65 | $3.40 | Open |
| Step 3.7 Flash | StepFun | 29 May 2026 | 256K | $0.20 | $1.15 | Open |
| Macaron V1 Tall | Mindlab | 21 Jul 2026 | 262K | $0.25 | $1.43 | Open |
Change history
- OpenRouter price changed: input $0.27 → $0.26, output $2.16 → $2.60 per 1M tokens
- Input modalities changed from text, image, video, audio to text, image, video
- OpenRouter price changed: input $0.26 → $0.27, output $2.60 → $2.16 per 1M tokens
- OpenRouter price changed: input $0.20 → $0.26, output $1.56 → $2.60 per 1M tokens
Sources
- https://openrouter.ai/qwen/qwen3.5-27b
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-27b.toml
- https://huggingface.co/Qwen/Qwen3.5-27B
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/Qwen/Qwen3.5-27B.toml
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.5-27B.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3.5-27B.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3.5-27b.toml