# Qwen3.6 35B A3B

Model tracker · checked 2026-10-14 · https://dbggr.dev/models/qwen3-6-35b-a3b/

Qwen3.6 35B A3B is a fast open-weight model from Alibaba, released 16 April 2026. At Alibaba it costs $0.375 per million input tokens and $2.25 per million output tokens, with a 256K-token context window. 3 providers serve it; the cheapest is DeepInfra at $0.10 input and $0.95 output.

- Made by: Alibaba Group (Qwen, Alibaba Cloud)
- Released: 2026-04-16
- Status: Generally available
- Tier: Fast
- Weights: Open
- Context window: 256,000 tokens
- Input: text
- API id: qwen3.6-35b-a3b
- Docs: https://www.alibabacloud.com/help/en/model-studio/models

## Qwen3.6 35B A3B price at 3 providers

US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.

| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| DeepInfra | $0.10 | $0.95 | $0.10 | $0.313 | – | [2026-10-14](https://deepinfra.com/pricing) |
| Novita AI | $0.248 | $1.49 | – | $0.557 | – | [2026-10-14](https://novita.ai/pricing) |
| Alibaba | $0.375 | $2.25 | – | $0.844 | – | [2026-10-14](https://www.alibabacloud.com/help/en/model-studio/model-pricing) |

- Alibaba: International (Singapore) deployment, up to 256K input tokens. Thinking and non-thinking output cost the same. Alibaba's pricing and model pages don't say whether its API takes image input; the open model does.

## Qwen3.6 35B A3B benchmarks

| Benchmark | Score | What it measures | Reported by |
|---|---|---|---|
| SWE-bench Verified | 73.4% | real GitHub issues fixed | [Alibaba](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) |

Scores reported by a model's maker aren't independently checked.

## Models like Qwen3.6 35B A3B

| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| Qwen3.6 35B A3B | $0.375 | $2.25 | 256K | Open |
| [Amazon Nova 2 Lite](https://dbggr.dev/models/amazon-nova-2-lite/) | $0.30 | $2.50 | 1M | Closed |
| [Gemini 3.5 Flash-Lite](https://dbggr.dev/models/gemini-3-5-flash-lite/) | $0.30 | $2.50 | 1M | Closed |
| [Muse Glimmer 30B](https://dbggr.dev/models/muse-glimmer-30b/) | $0.35 | $1.50 | 131K | Open |
| [Qwen3.8 27B](https://dbggr.dev/models/qwen3-8-27b/) | $0.50 | $3.00 | 1M | Open |
| [GLM-5.3 FlashX](https://dbggr.dev/models/glm-5-3-flashx/) | $0.37 | $1.25 | 1M | Open |

## FAQ

### How much does Qwen3.6 35B A3B cost?

Qwen3.6 35B A3B costs $0.375 per million input tokens and $2.25 per million output tokens at Alibaba. Prices are list prices in US dollars, last checked 14 October 2026.

### What is Qwen3.6 35B A3B's context window?

Qwen3.6 35B A3B takes up to 256,000 tokens in one request.

### Is Qwen3.6 35B A3B open weight?

Yes. Alibaba publishes the weights, so you can run Qwen3.6 35B A3B yourself or at any host that serves it.

### Where can I use Qwen3.6 35B A3B?

Qwen3.6 35B A3B is available from DeepInfra, Novita AI and Alibaba. At Alibaba, call it as `qwen3.6-35b-a3b`.