# Qwen3.5 397B-A17B

> Qwen3.5 397B-A17B is an open-weight language model from Alibaba (Qwen), released on 15 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 $0.39 per million input tokens and $2.34 per million output tokens (SiliconFlow), across 7 providers we track.

Source page: https://www.aimodel.directory/models/qwen3-5-397b-a17b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 15 Feb 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.5-397B-A17B)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.5-397B-A17B)
- **Parameters:** 403B (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.5-397B-A17B)
- **Context window:** 262K (262,144 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Max output:** 66K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Input:** Text, images, video and audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-397b-a17b.toml)
- **Hugging Face:** Qwen/Qwen3.5-397B-A17B (source: Hugging Face, https://huggingface.co/Qwen/Qwen3.5-397B-A17B)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| SiliconFlow | $0.39 | $2.34 | – | 262K |
| DeepInfra | $0.45 | $3 | $0.22 | 262K |
| OpenRouter | $0.55 | $3.50 | $0.23 | 262K |
| Alibaba Cloud Model Studio | $0.60 | $3.60 | – | 262K |
| Hugging Face Inference Providers | $0.60 | $3.60 | – | 262K |
| Nebius AI Studio | $0.60 | $3.60 | $0.06 | 262K |
| Novita AI | $0.60 | $3.60 | – | 262K |

## FAQ

### What is the context window of Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B 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 397B-A17B API cost?

Through Alibaba Cloud Model Studio, Qwen3.5 397B-A17B costs $0.60 per million input tokens and $3.60 per million output tokens. The lowest listed price is $0.39 input / $2.34 output through SiliconFlow. Prices last verified 4 Oct 2026.

### Is Qwen3.5 397B-A17B open source?

Qwen3.5 397B-A17B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3.5-397B-A17B under the apache-2.0 license. Check the license terms before commercial use.

### When was Qwen3.5 397B-A17B released?

Alibaba (Qwen) released Qwen3.5 397B-A17B on 15 Feb 2026, according to models.dev.

### Which providers offer Qwen3.5 397B-A17B?

We track Qwen3.5 397B-A17B on 7 providers: SiliconFlow, DeepInfra, OpenRouter, Alibaba Cloud Model Studio, Hugging Face Inference Providers, Nebius AI Studio, Novita AI.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen3.5 397B-A17B", https://www.aimodel.directory/models/qwen3-5-397b-a17b