Skip to content
OneAtlas

Qwen3.8 2.4T A95B

alibaba/qwen3.8-2.4t-a95b
AlibabaTextOpen weightsReasoningTool callStructured output
Compare 23 providers

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

Context

262K

262,144 tokens

Max output

131K

131,072 tokens

Input

$2.50

per 1M tokens

Output

$6.25

per 1M tokens

Providers

23

25 listings

Intelligence

39.9

Intelligence Index

Pricing

USD per 1M tokens · listed by Hugging Face

Token typeStandard
Input$2.50
Output$6.25

Lowest input price across providers: $1.95.

Capabilities

ReasoningYes

Effort: low, medium, xhigh

Tool callYes
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningYes

Field: reasoning_content

Open weightsYes
ModeratedNo

Input

Text

Output

Text

Benchmarks

Published scores and Design Arena Elo

Rankings

Position on each OneAtlas leaderboard

Providers · 23

25 listings

ProviderModel IDContextInput limitOutputInput $Output $Reasoning $Cache readCache writeAudio inAudio outReasoningToolsStructuredTemp.Updated
AI/ML APIalibaba/qwen3.8-2.4t-a95b262K—52K$2.65$6.61—$0.53———YesYesYesYesAug 12, 2026
AIHubMixqwen3.8-2.4t-a95b262K—131K$2.00$6.00—$0.50———YesYesYesYesAug 12, 2026
Charm Hyperqwen3.8-2.4t-a95b1M—128K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026
ChutesQwen/Qwen3.8-2.4T-A95B——————————NoNoUnknownYesOct 26, 2026
Cortecsqwen3.8-2.4t-a95b262K—262K$2.50$6.00—$0.63———YesYesYesYesAug 12, 2026
Deep InfraQwen/Qwen3.8-2.4T-A95B262K—131K$2.00$6.00—$0.20———YesYesYesYesAug 12, 2026
DevPass (LLM Gateway)qwen3.8-2.4t-a95b1.01M—131K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026
Eden AIqwen/qwen3.8-2.4t-a95b1M—131K$2.00$6.00—$0.25$2.50——YesYesYesYesAug 12, 2026
Fireworks AIaccounts/fireworks/models/qwen3p8-2p4t-a95b262K—131K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026
Hugging FaceQwen/Qwen3.8-2.4T-A95B262K—131K$2.50$6.25—————YesYesYesYesAug 12, 2026
IteraComputeqwen/qwen3.8-2.4t-a95b1.05M—131K$1.95$5.70—$0.25———YesYesYesYesAug 12, 2026
Kilo Gatewayqwen/qwen3.8-2.4t-a95b1.01M—909K$2.00$6.00—$0.25$2.50——YesYesYesYesAug 12, 2026
LLM Gatewaytogether-ai/qwen3.8-2.4t-a95b1.01M—909K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026
LLM Gatewaynovita/qwen3.8-2.4t-a95b1M—131K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026
Merge Gatewayqwen/qwen3.8-2.4t-a95b262K—1.01M$2.50$6.25—$0.50———YesNoNoYesAug 12, 2026
ModalQwen/Qwen3.8-2.4T-A95B1.01M—131K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026
Novita AIqwen/qwen3.8-2.4t-a95b1M—131K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026
Opperqwen3.8-2.4t-a95b262K—131K$2.50$6.00—$0.63———YesYesYesYesAug 12, 2026
Requestyqwen3.8-2.4T-A95B@eu1M—262K$2.50$6.00—$0.63———YesYesYesYesAug 12, 2026
Requestyqwen3.8-2.4T-A95B262K—262K$2.00$6.00—$0.20———YesYesYesYesAug 12, 2026
RunInfraInferact/Qwen3.8-2.4T-A95B-NVFP4262K—33K$2.00$6.00—$0.20———YesYesYesYesAug 12, 2026
SiliconFlowQwen/Qwen3.8-2.4T-A95B1.05M—131K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026
TensorXqwen/qwen3.8-2.4t-a95b262K—64K$2.50$6.00—$0.63———YesYesYesYesAug 12, 2026
Venice AIqwen-3-8-2-4t-a95b262K—66K$2.50$7.50—$0.31———YesYesYesYesAug 12, 2026
Vercel AI Gatewayalibaba/qwen3.8-2.4t-a95b262K—128K$2.00$6.00—$0.25———YesYesYesYesAug 12, 2026