Qwen3.6 35B A3B
Provider: Alibaba (Qwen) CN
Overview
Alibaba's Qwen3.6 35B A3B is a mid-tier multimodal sparse mixture-of-experts model targeting vision, tool use, and complex reasoning workloads.
Strengths
- 35 billion total parameters with 3 billion active
- 262144 token context window
- Supports native vision and function calling
- Includes structured JSON mode and thinking capabilities
Best use cases
- Multimodal document analysis and extraction
- Automated tool use and function pipelines
- Structured data generation tasks
Pricing position
Input is priced at $0.1/1M tokens with output at $0.95/1M tokens, making output significantly pricier than Qwen3 Next 80B A3B Instruct ($1.1/1M) and peer models like Llama 4 Scout ($0.3/1M).
Caveats
No free tier is available across third-party hosts, and output cost exceeds many similarly priced input peers.
Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.
Key facts
- Price basis
- Median third-party host price (no first-party API)
- Max output
- 236K tokens
- Listed on OpenRouter
- 2026-04-27
- Tracked since
- 2026-05-08
- Last updated
- 2026-11-10
Features
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.06 |
| 1M (small app) | 1 | 0.5 | $0.57 |
| 10M (mid scale) | 10 | 5 | $5.75 |
| 100M (large) | 100 | 50 | $57.50 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from Alibaba (Qwen)
Similar-priced models
Source: OpenRouter API (qwen/qwen3.6-35b-a3b)