Alibaba: qwen-max-0919 API
A core snapshot of the Qwen2.5-Max architecture released by Alibaba Cloud on September 19, 2024. As the pinnacle of the Qwen2.5 series, it marks the full transition of the Qwen family toward high-performance Mixture-of-Experts (MoE) architectures. This version delivers a quantum leap in coding, long-context retrieval stability, and deep Chinese cultural nuance compared to its predecessors. Renowned for its exceptional instruction-following precision, it remains a premier choice for enterprise-grade applications and served as the stable benchmark prior to the release of the trillion-parameter Qwen3 series in 2025.
- Context window: 32,768 tokens
- Max output: 8,192 tokens
- Input: text
- Output: text
- Tool calling: Supported
- File input: Supported
- Released: 2024-09-18
- Knowledge cutoff: 2024-07-31
Frequently Asked Questions
What is the context window of qwen-max-0919?
qwen-max-0919 supports a context window of up to 32,768 tokens.
Does qwen-max-0919 support function calling?
Yes. qwen-max-0919 supports tool / function calling.
What is the knowledge cutoff of qwen-max-0919?
The knowledge cutoff of qwen-max-0919 is 2024-07-31.