← Model list

Qwen3.5 122B-A10B

alibaba·alibaba/qwen3.5-122b-a10b·GA·Open weights·qwen series

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

At a glance
Official price$0.40 / $3.20 per 1M
Cache read · Alibaba
Lowest paid$0.115 / $0.917
OrcaRouter Gateway · 4.3× spread
1 more $0 channels
Context262,144
⚠ Providers report 131,072–262,144; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoAudio
Knowledge cutoff
Released / updated2026-02-23 / 2026-02-23

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

Intelligence32.8
Value104
Coding45.7
Agentic21.3
Output speed130 tok/s
TTFT2.33 s
Cost per task$0.2527
Value formulaIQ 32.8 ÷ min blended $0.316 = 104
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 28.2 · 143 tok/s
ReasoningIQ 32.8 · 130 tok/s

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

Available at 19 providers18 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaFirst-partyFree262,14465,536
OrcaRouterGateway$0.115$0.917262,14465,536
Merge GatewayGateway$0.115$0.917$0.023256,00064,000
EmpirioLabs AI
qwen3-5-122b-a10b
Gateway$0.115
tiered >128K: $0.287
$0.917$0.115256,00064,000
OpenRouterGateway$0.26$2.08262,14465,536
Neon
qwen35-122b-a10b
Cloud$0.22$2.20262,14425,000
SiliconFlow
Qwen/Qwen3.5-122B-A10B
Cloud$0.26$2.08262,144262,144
Kilo GatewayGateway$0.26$2.08262,14465,536
OfoxGateway$0.29$2.29$0.29256,00064,000
Deep Infra
Qwen/Qwen3.5-122B-A10B
Cloud$0.29$2.40262,14465,536
AlibabaOfficialFirst-party$0.40$3.20262,14465,536

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

1Merge Gateway$57.81
2OrcaRouter$68.85
3EmpirioLabs AI$68.85
4Neon$154.00
5OpenRouter$156.00
6SiliconFlow$156.00
17Alibaba · Official$240.00

1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to Merge Gateway to save $182.19/mo (76%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Verified72resolvedSource ↗

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

Reasoning control

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

4 / 19 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$3.20$02026-08-052026-08-132026-08-05 · Input list $0.402026-08-06 · Input list $0.402026-08-07 · Input list $0.402026-08-08 · Input list $0.402026-08-09 · Input list $0.402026-08-10 · Input list $0.402026-08-11 · Input list $0.402026-08-12 · Input list $0.402026-08-13 · Input list $0.402026-08-05 · Output list $3.202026-08-06 · Output list $3.202026-08-07 · Output list $3.202026-08-08 · Output list $3.202026-08-09 · Output list $3.202026-08-10 · Output list $3.202026-08-11 · Output list $3.202026-08-12 · Output list $3.202026-08-13 · Output list $3.202026-08-05 · Min blended $0.3162026-08-06 · Min blended $0.3162026-08-07 · Min blended $0.3162026-08-08 · Min blended $0.3162026-08-09 · Min blended $0.3162026-08-10 · Min blended $0.3162026-08-11 · Min blended $0.3162026-08-12 · Min blended $0.3162026-08-13 · Min blended $0.316