Qwen3.8-2.4T-A95B
AvailableA Qwen model with a 1M-token context window and tool calling. On the Alibaba Cloud Model Studio API since August 12, 2026.
Access details: Alibaba Cloud Model Studio API
The model ID to use in API requests.
qwen3.8-2.4t-a95bOpen weights on Hugging Face: Qwen/Qwen3.8-2.4T-A95B
Capabilities & limits
- Context window
- 1M
- Maximum output
- 128K
- Image input
- Unsupported
- Tool calling
- Supported
- Structured output
- Supported
Pricing
USD / 1M tokens- Input
- $2.00
- Output
- $6.00
Standard rates per million tokens. Discounts and long-context rates, where offered, are on Qwen's pricing page.
Full rate card 2 rates
All prices in USD.
Input tokens
$2.00 per 1M tokens- input 0 to 1M tokens per request
Output tokens
$6.00 per 1M tokens- input 0 to 1M tokens per request
- non-thinking and thinking modes
USD, International deployment scope (Singapore region) on the international pricing page. Standard prices; the page notes limited-time promotions are excluded. Context-cache and explicit-cache rates are described on a separate page and were not captured; where the page flags a 50% batch discount it is noted here. Rates for other regions (China, Germany, US, Japan, Hong Kong) are not captured. Open-weights model also served on Model Studio.
Price history
Input $2.00 per million tokens
Output $6.00 per million tokens
Technical details
- Parameters
- 2.4T total
- Active parameters
- about 95B
- Architecture
- Sparse mixture of experts (MoE) with hybrid attention
- Input modalities
- Text
- Output modalities
- Text
From Qwen
Official announcement ↗Release & lifecycle
- First available
- Aug 12, 2026
- available
- As of Oct 1, 2026