← Model list

Qwen3.6 Max Preview

alibaba·alibaba/qwen3.6-max-preview·GA·Closed·qwen series

Flagship Qwen model for complex reasoning, coding, and agentic workflows

At a glance
Official price$1.32 / $7.90 per 1M
Cache read $0.132 · Alibaba (China)
Lowest paid$1.03 / $6.16
OpenRouter Gateway · 2.1× spread
Context245,800
⚠ Providers report 240,000–262,144; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-04
Released / updated2026-04-20 / 2026-04-20

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence41.1
Value18
Coding
Agentic
Output speed62 tok/s
TTFT4.19 s
Value formulaIQ 41.1 ÷ min blended $2.311 = 18

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 13 providers13 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
OpenRouterGateway$1.03
tiered >128K: $1.58
$6.16$1.28262,14465,536
Kilo GatewayGateway$1.03$6.16$1.28262,14465,536
NanoGPTGateway$1.04$6.24$0.52245,76065,536
PioneerGateway$1.04$6.24$0.208$1.30240,00064,000
AIHubMixGateway$1.27
tiered >128K: $2.11
$7.61$0.127$1.58240,00064,000
AlibabaOfficialFirst-party$1.30$7.80$0.13$1.63262,14465,536
Vercel AI Gateway
alibaba/qwen-3.6-max-preview
Cloud$1.30$7.80$0.26$1.63240,00064,000
DevPass (LLM Gateway)Gateway$1.30$7.80$0.13$1.63262,14465,536
Merge GatewayGateway$1.31$7.88256,00065,536
EmpirioLabs AI
qwen3-6-max-preview
Gateway$1.31
tiered >128K: $1.97
$7.88$1.31256,00065,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Pioneer$420.16
2NanoGPT$457.60
3AIHubMix$497.32
4Alibaba · Official$509.60
5DevPass (LLM Gateway)$509.60
6OpenRouter$513.50
Switch to Pioneer to save $89.44/mo (18%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

Toggle (on / off)budget_tokenseffort = noneeffort = higheffort = loweffort = mediumeffort = max

3 / 13 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$7.90$02026-08-052026-08-132026-08-05 · Input list $1.302026-08-06 · Input list $1.302026-08-07 · Input list $1.302026-08-08 · Input list $1.302026-08-09 · Input list $1.302026-08-10 · Input list $1.302026-08-11 · Input list $1.302026-08-12 · Input list $1.302026-08-13 · Input list $1.322026-08-05 · Output list $7.802026-08-06 · Output list $7.802026-08-07 · Output list $7.802026-08-08 · Output list $7.802026-08-09 · Output list $7.802026-08-10 · Output list $7.802026-08-11 · Output list $7.802026-08-12 · Output list $7.802026-08-13 · Output list $7.902026-08-05 · Min blended $2.312026-08-06 · Min blended $2.312026-08-07 · Min blended $2.312026-08-08 · Min blended $2.312026-08-09 · Min blended $2.312026-08-10 · Min blended $2.312026-08-11 · Min blended $2.312026-08-12 · Min blended $2.312026-08-13 · Min blended $2.31