← LLM API prices

Qwen3 VL 235B A22B Instruct

Alibaba

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

In
$0.21
Out
$1.90
Blended
$0.63
Where to buy this model
5 access routes
RouteInOutBlendedvs
DeepInfra cheapestfp8$0.20$0.88$0.37-
Alibaba $0.26$1.04$0.46+24%
Novita bf16$0.30$1.50$0.60+62%
Venice fp8$0.21$1.90$0.63+70%
Parasail fp8$0.21$1.90$0.63+70%

official API · cloud platform · inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.

Ctx
262K
max output
33K
cache read /1M
$0.10
Family
qwen
Modalities
text · image
Features
json · tools

Live pricing, updated 2026-09-15.

Concepts on this page