# Qwen3.5 35B-A3B

> Qwen3.5 35B-A3B is an open-weight language model from Alibaba (Qwen), released on 23 Feb 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 $0.14 per million input tokens and $1 per million output tokens (DeepInfra), across 6 providers we track.

Source page: https://www.aimodel.directory/models/qwen3-5-35b-a3b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 23 Feb 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.5-35B-A3B)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.5-35B-A3B)
- **Parameters:** 36B (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.5-35B-A3B)
- **Context window:** 262K (262,144 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Max output:** 66K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Input:** Text, images, video and audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml)
- **Hugging Face:** Qwen/Qwen3.5-35B-A3B (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.5-35B-A3B)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| DeepInfra | $0.14 | $1 | $0.05 | 262K |
| OpenRouter | $0.15 | $1 | $0.05 | 262K |
| SiliconFlow | $0.24 | $1.80 | – | 262K |
| Alibaba Cloud Model Studio | $0.25 | $2 | – | 262K |
| Novita AI | $0.25 | $2 | – | 262K |
| Hugging Face Inference Providers | $0.25 | $2 | – | 262K |

## FAQ

### What is the context window of Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B 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 35B-A3B API cost?

Through Alibaba Cloud Model Studio, Qwen3.5 35B-A3B costs $0.25 per million input tokens and $2 per million output tokens. The lowest listed price is $0.14 input / $1 output through DeepInfra. Prices last verified 4 Oct 2026.

### Is Qwen3.5 35B-A3B open source?

Qwen3.5 35B-A3B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3.5-35B-A3B under the apache-2.0 license. Check the license terms before commercial use.

### When was Qwen3.5 35B-A3B released?

Alibaba (Qwen) released Qwen3.5 35B-A3B on 23 Feb 2026, according to models.dev.

### Which providers offer Qwen3.5 35B-A3B?

We track Qwen3.5 35B-A3B on 6 providers: DeepInfra, OpenRouter, SiliconFlow, Alibaba Cloud Model Studio, Novita AI, Hugging Face Inference Providers.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen3.5 35B-A3B", https://www.aimodel.directory/models/qwen3-5-35b-a3b