modelbenchmark.io

Qwen3-VL 235B-A22B

Alibaba · qwen3-vl-235b-a22b

Compare

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

Specification

alibaba listing

Context
131K
Max output
33K
Released
2025-04
Knowledge cutoff
2025-04
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · alibaba list price

Input
$0.70
Output
$2.80
Cache read
$0.052

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputbedrock_converse$0.26
Batch outputbedrock_converse$1.33
Priority inputbedrock_converse$0.93
Priority outputbedrock_converse$4.66

Batch input is 51% below the interactive input price at the same listing.

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
alibabavendor$0.70$2.80——131K33K—
venice$0.21$1.90$0.10—128K16K—
alibaba-cn$0.2867$1.1468——131K33K—
amazon-bedrock$0.53$2.66——262K262K—
bedrock_converse$0.53$2.66——256K8K—
cortecs$0.617$3.119$0.052—256K256K—

Price history

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

DateHostField$/M
2026-09-02amazon-bedrockInput$0.30
2026-09-12amazon-bedrockInput$0.53
2026-09-02amazon-bedrockOutput$1.50
2026-09-12amazon-bedrockOutput$2.66

More from Alibaba

most-hosted first