Qwen: Qwen3.8-2.4T-A95BActive

qwen/qwen3.8-2.4t-a95b

Qwen3.8-2.4T-A95B is the open-source version of Tongyi Qianwen's latest flagship series, released in August 2026. It adopts a sparse MoE architecture with a total of 2.4 trillion parameters, activating approximately 95 billion per step, and supports 1 million token contexts with a hybrid attention mechanism. Core benchmarks include GPQA Diamond 92.6, PaperBench 93.0, OSWorld 86.1, and BabyVision 82.0. It ranks 4th globally on CodeArena.

By:QwenInput Type:Output Type:Publish time:2026-08-13

Providers

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

ProviderCache Hit RateContext

Alibaba Cloud

alibaba

-$2/ M tokens$6/ M tokensRead:0.17-0.25/ M tokensWrite:2.5/ M tokens1M--

Uptime

24hours

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

No data

Throughput

24hours

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

No data

Latency

24hours

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

No data

Activity

Token volume and request traffic to this model over time.

Token Consumption

Oct 25

Alibaba Cloud1.5K

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

Qwen3.8-2.4T-A95B Qwen

Intelligence Index39.9

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.