Qwen-Max
Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion tokens and further post-trained with curated Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) methodologies. The parameter count is unknown.
Specifications
Modalities
Supported Parameters
Max Output Tokens
8,192Data policy
- Prompt retention
- Unknown — we could not confirm
- Training
- Unknown — not declared
"Unknown" does not mean "safe". It means we could not confirm it.
Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.
Frequently asked questions
- Is Qwen-Max available on FastMetal?
- Not at the moment. Qwen3 VL 235B A22B Instruct, from the same lab, is available on the FastMetal API today.
- What is the context window of Qwen-Max ?
- 32,768 tokens, shared between the prompt and the response.
- How does Qwen-Max rank?
- #208 on the public arena's Japanese board (ELO 1,242). Ranks move as the leaderboard is updated.
Leaderboard
Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-22; category names mapped and ratings rounded by FastMetal.