modelbenchmark.io

Qwen3 VL 235B A22B Instruct

Alibaba · qwen3-vl-235b-a22b-instruct

Compare

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

Specification

dashscope listing

Context
131K
Max output
33K
Released
2025-09-23
Knowledge cutoff
2025-03-31
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · dashscope list price

Input
$0.40
Output
$1.60
Cache read
$0.11
Cache write
$0.2625

Available from 22 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepinfra$0.20$0.88$0.11262K33K
llmgateway$0.20$0.88$0.11262K8K
openrouter$0.21$1.90$0.10262K33K
tensorx$0.21$1.90$0.0525$0.2625131K131K
fireworks_ai$0.22$0.88262K262K
kilo$0.26$1.04131K33K
merge-gateway$0.287$1.147$0.1578131K33K
helicone$0.30$1.50256K16K
huggingface$0.30$1.50131K33K
jalapeno$0.30$1.50129K33K
llmgateway-providers
$0.30
$0.20
$1.50
$0.88
$0.11
131K
262K
33K
nano-gpt$0.30$1.20$0.15131K33K
novita$0.30$1.50131K33K
novita-ai$0.30$1.50131K33K
siliconflow$0.30$1.50262K262K
siliconflow-cn$0.30$1.50262K262K
dashscope · dashscope$0.40$1.60131K33K
edenai$0.40$1.60131K33K
orcarouter$0.40$1.60131K33K
qwen_ai_platform · qwen-ai-platform$0.40$1.60131K33K
qwencloud · qwencloud$0.40$1.60131K33K
vercel$0.40$1.60131K129K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterCache read$0.10
2026-09-06openrouterCache read$0.10
2026-09-02llmgateway-providersInput$0.20
2026-09-04llmgateway-providersInput$0.30
2026-09-02openrouterInput$0.21
2026-09-06openrouterInput$0.21
2026-09-02llmgateway-providersOutput$0.88
2026-09-04llmgateway-providersOutput$1.50
2026-09-02openrouterOutput$1.90
2026-09-06openrouterOutput$1.90

More from Alibaba

most-hosted first