Qwen: Qwen3 Max Thinking PreviewSunset

qwen/qwen3-max-preview

Please note: This is a toggle thinking model. To enable "thinking" mode, you need to set "enable_thinking=True".

This is a preview version of the Max model in the Tongyi Qianwen 3 series, achieving an effective integration of thinking and non-thinking modes. In thinking mode, there is a significant enhancement in capabilities such as intelligent agent programming, common-sense reasoning, and reasoning across mathematics, science, and general domains.

By:QwenInput Type:Output Type:Publish time:2025-11-03

Providers

Route requests across multiple providers. Copy a provider slug to set your preference.

ProviderCache Hit RateContext

Alibaba CloudSunset

alibaba

34.4%$1.2-3/ M tokens$6-15/ M tokensRead:0.24-0.6/ M tokensWrite:1.5-3.75/ M tokens262.14K5.02s14.0tps

Uptime

24hours

Direct request success rate on AI Gateway and per-provider.

Apr 21, 01:29

Alibaba Cloud100.00%

Throughput

24hours

P50 throughput on live AI Gateway traffic, in tokens per second (TPS).

Apr 21, 01:00

Alibaba Cloud14.0 tps

Latency

24hours

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.

Apr 21, 01:00

Alibaba Cloud5.02s

Activity

Token volume and request traffic to this model over time.

Token Consumption

Apr 20

Alibaba Cloud46.1K

Token volume broken down by the provider that served each request. Larger segments indicate providers handling more of this model's traffic.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis

No benchmark data is available for this model.

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 Ranking

No app usage is available for this period.

Related Models

More models from Qwen

Qwen: Qwen-Audio-3.1-ASR-Flash

1.25Mtokens

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

1.26Btokens

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

24.82Btokens

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.