Qwen: Qwen3-Max-Thinking下线

qwen/qwen3-max

Qwen3-Max-Thinking is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.

由:Qwen输入类型:输出类型:发布时间:2026-01-23

供应商

在多个供应商之间路由请求。复制供应商标识以设置偏好供应商。

供应商缓存命中率上下文

Alibaba Cloud下线

alibaba

14.6%$1.2-3/ 百万 token$6-15/ 百万 token读取：0.12-0.6/ 百万 token写入：1.5-3.75/ 百万 token252K--

可用率

24 小时

AI Gateway 直连请求及各供应商的成功率。

Oct 9, 19:39

Alibaba Cloud100.00%

吞吐量

24 小时

AI Gateway 实时流量的 P50 吞吐量，单位为每秒 token 数（TPS）。

No data

延迟

24 小时

AI Gateway 实时流量的 P50 首 token 延迟（TTFT），单位为毫秒。

该时段暂无延迟样本。

活动

该模型随时间变化的 token 用量和请求流量。

Token 消耗

Oct 9

Alibaba Cloud14.8K

按实际处理请求的供应商拆分 token 用量。区块越大，表示该供应商处理的模型流量越多。

基准测试

标准化评测得分。百分比越高越好，并展示排名百分位。

指标来源：Artificial Analysis

该模型暂无基准测试数据。

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

Token 排行

No app usage is available for this period.

相关模型

更多模型来自 Qwen

Qwen: Qwen-Audio-3.1-ASR-Flash

1.25Mtoken

Qwen-Audio-3.1-ASR-Flash is a large-scale model supporting efficient short speech recognition, designed for high-quality, multilingual, and cultural content transcription scenarios. The model supports multilingual and multi-regional Chinese dialect recognition, and is optimized for the rhythm, cadence, and classical Chinese expression of ancient Chinese poetry. It features context enhancement, punctuation prediction, and text normalization capabilities. This version also supports controllable ASR/AST output for multiple dialects. It includes native transcription and polishing capabilities, as well as industrial-grade multi-person dialogue role-based transcription capabilities.

Qwen: Qwen3.8-Omni-Flash

1.26Btoken

Designed for audio and video understanding and content analysis, it supports text, image, audio, and video inputs with text output.

Qwen: Qwen3.8-Max-0902

24.82Btoken

Qwen3.8-Max-0902 is a snapshot release of Qwen3.8-Max with stronger coding performance for complex engineering tasks and long-horizon autonomous development. It also improves agentic tool use and visual understanding for chart reasoning, document parsing, and multimodal perception, while retaining a 1M-token context window, reasoning mode, and a full tool ecosystem.