Skip to content
OneAtlas

QVQ Max

alibaba/qvq-max
AlibabaTextClosed weightsReasoningTool calldeprecated
Compare 3 providers

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

131K

131,072 tokens

Max output

8K

8,192 tokens

Input

$1.20

per 1M tokens

Output

$4.80

per 1M tokens

Providers

3

3 listings

Intelligence

—

Not yet scored

Pricing

USD per 1M tokens · listed by Alibaba

Token typeStandard
Input$1.20
Output$4.80

Lowest input price across providers: $1.15.

Capabilities

ReasoningYes
Tool callYes
Structured outputNo
TemperatureYes
AttachmentsYes
Interleaved reasoningNo
Open weightsNo
ModeratedUnknown

Input

TextImage

Output

Text

Benchmarks

Published scores and Design Arena Elo

No published benchmark scores for this model yet.

Rankings

Position on each OneAtlas leaderboard

Providers · 3

3 listings

ProviderModel IDContextInput limitOutputInput $Output $Reasoning $Cache readCache writeAudio inAudio outReasoningToolsStructuredTemp.Updated
Alibabaqvq-max131K—8K$1.20$4.80—————YesYesUnknownYesMar 25, 2025
Alibaba (China)qvq-max131K—8K$1.15$4.59—————YesYesUnknownYesMar 25, 2025
NanoGPTqvq-max128K128K8K$1.20$4.80—$0.60———NoNoNoUnknownMar 28, 2025