Qwen3.8-2.4T-A95B is Qwen's open-weight, text-only Max-class model: a 2.4-trillion-parameter Mixture-of-Experts LLM with 95B parameters active per token, a 262K-token native context window, and support for extending context up to 1.01M tokens.
Qwen3.8-2.4T-A95B was the first Max-class Qwen model released with open weights. Built on the architectural foundation of Qwen3.5, it is designed for coding, professional work, research, and long-horizon agentic tasks. The model requires thinking mode and supports adjustable reasoning effort (low, medium, and xhigh). Full details are in the official model card.
On a Shared Endpoint, you pay per token. The endpoint is OpenAI-compatible and already live: point your existing SDK at it and start sending requests.