Back
Qwen: Qwen-Max
Qwen
Input: text
Output: text
Released: Feb 1, 2025•Updated: Mar 28, 2025
Qwen-Max, based on Qwen2.5, provides the best inference performance among Qwen models, 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.
32,768 Token Context
Process and analyze large documents and conversations.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| Alibaba | alibaba | 33K | 8K | $1.60/M | $6.40/M | 40.9 t/s | 1684 ms |
Standard Pricing
Input Tokens
$0.0000016
per 1K tokens
Output Tokens
$0.0000064
per 1K tokens