ModelPickr

Models / Alibaba / Qwen3 VL 235B A22B Instruct

Alibaba · qwen

Qwen3 VL 235B A22B Instruct

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

$0.30 in · $1.50 out

per 1M tokens · provider rate closest to the median. No first-party Alibaba price was listed. The reference price is Hugging Face's rate, the provider closest to the median.

Provider input prices run from $0.20 to $0.53 per 1M tokens. Output prices run from $0.88 to $2.66.

Context
131,072
Max output
32,768
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
Yes
License
—
Released
Sep 23, 2025
Updated in source
Sep 23, 2025
Knowledge
2025-03-31
Providers
12

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.

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
Deep Infra$0.20$0.88$0.11——
Eden AI$0.20$0.88$0.11——
Kilo Gateway$0.21$1.90$0.10——
OpenRouter$0.21$1.90$0.10——
Merge Gateway$0.29$1.15$0.16——
Hugging Facereference$0.30$1.50———
Jalapeno Cloud$0.30$1.50———
LLM Gateway$0.30$1.50———
NanoGPT$0.30$1.90$0.15——
Prime Inference$0.30$1.50———
OrcaRouter$0.40$1.60———
Amazon Bedrock$0.53$2.66———

Jobs this model qualifies for