Alibaba Qwen · API model

Qwen3.8 Max

Generally availableReleased Aug 3, 2026Proprietary

API id qwen3.8-max prices checked

Input
$2.00/1M
Sources differ
Output
$6.00/1M
Sources differ
Context
1Mtokens
Max output
131Ktokens
Knowledge cutoff
Not disclosed
Typical request
$0.005

Pricing

US dollars per 1 million tokens. A typical request (1,000 input + 500 output tokens) costs $0.005 at standard rates.

RateInputCached inputOutput
Standard$2.00$0.25$6.00
BatchAsynchronous, results within 24 hours$1.00$3.00

Sources list different standard prices. OpenRouter lists cached input at $0.25/M; Alibaba Cloud's own Model Studio page lists $0.20/M for cached reads. Standard input/output match exactly ($2 / $6) across both.

SourceInputOutputNote
independentOpenRouter$2.00$6.00Cached input $0.25/M
vendorAlibaba Cloud Model Studio$2.00$6.00Cached input $0.20/M

Capabilities and limits

Context window1M tokens
Max output131K tokens
InputTextImagesVideo
OutputText
ReasoningAdjustable effort
Tool useYes
Structured output (JSON)Yes
Knowledge cutoffNot disclosed by the vendor

Benchmarks and speed

Not collected yet. Scores will come only from independent leaderboards, each shown with its source and test date.

Planned: GPQA Diamond, SWE-bench Verified, AIME 2025, LMArena Elo, output speed and time to first token.

Where these numbers come from

Every value is an observation with a source and a date. independent is a third-party catalog, vendor is the model maker's own page, derived is our calculation.

FieldValueSourceObserved
Standard price, input / output$2.00 / $6.00independentOpenRouterSep 15, 2026
Standard price, input / output$2.00 / $6.00vendorAlibaba Cloud Model StudioSep 15, 2026
Context window1,000,000independentOpenRouterSep 15, 2026
ReasoningHybrid, toggle per request (enable_thinking)vendorAlibaba Cloud docsSep 15, 2026
Release date2026-08-03vendorAlibaba Cloud Model StudioSep 15, 2026
Typical request$0.005derivedCalculated: 1,000 in + 500 outSep 15, 2026