One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.375 = $0.375
- Output0.1M x $2.25 = $0.225
$0.60per session
Alibaba Cloud (Qwen) - Open weights
Qwen3.6-35B-A3B is an open-weights model from Alibaba Cloud (Qwen) that costs $0.375 per 1M input tokens and $2.25 per 1M output tokens on the first-party API, with a 262K-token context window.
Last verified from alibabacloud.com. All sources
| Item | Price / 1M tokens |
|---|---|
| Input | $0.375 |
| Output | $2.25 |
Note: International (Singapore) list prices. Open-weights MoE vision-language model served on Model Studio. The text generation page does not list it among either its recommended or its legacy models. One tier up to 256K input tokens; thinking output costs the same. No cache or batch price listed. The console states context 256K and max output 64K; recorded as 262,144 and 65,536 (the QwenCloud model card for it states 262K and 65K).
qwen3.6-35b-a3bStructured output is JSON Object mode only (valid JSON, no schema enforcement), in non-thinking mode; not listed in the context cache or batch supported-model lists. Not stated means the provider's docs do not say either way. It is not the same as No. Checked against provider docs on . Compare capabilities across models.
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
1M input tokens and 100K output tokens, no caching.
$0.60per session
10,000 requests a day at 2K input and 500 output tokens each.
$18.75per day
$562.50 per 30-day month
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Qwen3.6-35B-A3B (this page) | $0.375 | $2.25 |
| GLM-4.5Z.ai | $0.60 | $2.20 |
| GLM-4.6Z.ai | $0.60 | $2.20 |
| GLM-4.7Z.ai | $0.60 | $2.20 |
| Qwen3.5-Omni-FlashAlibaba Cloud (Qwen) | $0.40 | $2.20 |
| Qwen3.5-27BAlibaba Cloud (Qwen) | $0.30 | $2.40 |
| Qwen3.5-PlusAlibaba Cloud (Qwen) | $0.40 | $2.40 |
| Qwen3.5-35B-A3BAlibaba Cloud (Qwen) | $0.25 | $2 |
| Qwen3-VL-PlusAlibaba Cloud (Qwen) | $0.20 | $1.60 |
| Qwen3.7-PlusAlibaba Cloud (Qwen) | $0.40 | $1.60 |
Qwen3.6-35B-A3B costs $0.375 per 1M input tokens and $2.25 per 1M output tokens on Alibaba Cloud (Qwen)'s first-party API, per alibabacloud.com on October 26, 2026.
Qwen3.6-35B-A3B has a 262,144-token context window and returns up to 65,536 output tokens per response.
Yes. Qwen3.6-35B-A3B's weights are published at https://huggingface.co/Qwen/Qwen3.6-35B-A3B under the Apache-2.0.
Alibaba Cloud (Qwen) released Qwen3.6-35B-A3B on April 17, 2026.
Last verified from alibabacloud.com.
Newsletter
One email per week. New model releases, price cuts and what they mean for your bill.