← Model list

Qwen3.6 35B-A3B

alibaba·alibaba/qwen3.6-35b-a3b·BETA·Open weights·qwen series

Open multimodal Qwen MoE for local agents that need vision, audio, and code

At a glance
Official price$0.248 / $1.49 per 1M
Cache read · Alibaba
Lowest paid$0.07 / $0.42
EmpirioLabs AI Gateway · 71.4× spread
2 more $0 channels
Context262,144
⚠ Providers report 16,384–262,144; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoAudio
Knowledge cutoff2025-04
Released / updated2026-04-17 / 2026-04-17

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning

Intelligence32.1
Value204
Coding41.9
Agentic21.6
Output speed118 tok/s
TTFT2.07 s
Cost per task$0.2944
Value formulaIQ 32.1 ÷ min blended $0.158 = 204
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 24.6 · 138 tok/s
ReasoningIQ 32.1 · 118 tok/s

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

Available at 25 providers23 with public prices · 1 free · 1 subscription-covered

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Umans AI Coding Plan
umans-qwen3.6-35b-a3b
GatewaySubscription$0$0262,144262,144
QVACGatewayFree262,14465,536
EmpirioLabs AI
qwen3-6-35b-a3b
Gateway$0.07$0.42$0.035131,07216,384
SaladCloud AI GatewayGateway$0.09$0.60262,144262,144
AKI.IO
qwen3.6-35b
Gateway$0.15$0.50256,00032,768
ZenifraGateway$0.19$0.48262,14465,536
CortecsGateway$0.167$0.557262,000262,000
NanoGPT
qwen/Qwen3.6-35B-A3B
Gateway$0.112$0.80$0.056262,14416,384
Deep Infra
Qwen/Qwen3.6-35B-A3B
Cloud$0.10$0.95262,14481,920
Venice AI
qwen3-6-35b-a3b
Gateway$0.10$1.00256,00065,536
AlibabaOfficialFirst-party$0.248$1.49262,14465,536

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

1EmpirioLabs AI$30.80
2SaladCloud AI Gateway$48.00
3AKI.IO$55.00
4NanoGPT$55.68
5Cortecs$61.25
6Zenifra$62.00
18Alibaba · Official$123.85

2 more channels offer $0 (Umans AI Coding Plan, QVAC); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to EmpirioLabs AI to save $93.05/mo (75%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Verified73.4resolvedSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Reasoning control

Toggle (on / off)effort = loweffort = mediumeffort = higheffort = noneeffort = maxbudget_tokenseffort = minimaleffort = xhigh

7 / 25 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.49$02026-08-052026-08-132026-08-05 · Input list $0.2482026-08-06 · Input list $0.2482026-08-07 · Input list $0.2482026-08-08 · Input list $0.2482026-08-09 · Input list $0.2482026-08-10 · Input list $0.2482026-08-11 · Input list $0.2482026-08-12 · Input list $0.2482026-08-13 · Input list $0.2482026-08-05 · Output list $1.492026-08-06 · Output list $1.492026-08-07 · Output list $1.492026-08-08 · Output list $1.492026-08-09 · Output list $1.492026-08-10 · Output list $1.492026-08-11 · Output list $1.492026-08-12 · Output list $1.492026-08-13 · Output list $1.492026-08-05 · Min blended $0.1582026-08-06 · Min blended $0.1582026-08-07 · Min blended $0.1582026-08-08 · Min blended $0.1582026-08-09 · Min blended $0.1582026-08-10 · Min blended $0.1582026-08-11 · Min blended $0.1582026-08-12 · Min blended $0.1582026-08-13 · Min blended $0.158