ModelPickr

Models / Alibaba / Qwen3.5 122B-A10B

Alibaba · qwen

Qwen3.5 122B-A10B

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

$0.40 in · $3.20 out

per 1M tokens · first-party price. Reference price from Alibaba, the lab's own listing.

Provider input prices run from $0.11 to $0.50 per 1M tokens. Output prices run from $0.90 to $3.97.

Context
262,144
Max output
65,536
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
Yes
License
—
Released
Feb 23, 2026
Updated in source
Feb 23, 2026
Knowledge
—
Providers
19

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

Qwen3.5 122B-A10B

$7.20

Cache hit is ignored because this model has no cache-read price.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
AIHubMix$0.11$0.90———
EmpirioLabs AI$0.12$0.92$0.12——
Merge Gateway$0.12$0.92$0.023——
OrcaRouter$0.12$0.92———
Neon$0.22$2.20———
Kilo Gateway$0.26$2.08———
OpenRouter$0.26$2.08———
SiliconFlow$0.26$2.08———
Deep Infra$0.29$2.40——deprecated
Ofox$0.29$2.29$0.29——
Alibabareference$0.40$3.20———
DevPass$0.40$3.20———
Hugging Face$0.40$3.20———
Jalapeno Cloud$0.40$3.20———
LLM Gateway$0.40$3.20———
Novita AI$0.40$3.20———
NanoGPT$0.44$3.50$0.10——
Infomaniak$0.50$3.97———
TensorX$0.50$3.50$0.13$0.63—

Jobs this model qualifies for