Pass IndexThe State of AISign in

Qwen3 VL 30B A3B Thinking

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

text + image → text · made by Alibaba

$0.15$0.6per Mtok in / out
Fireworks AI · 7 sellers

Sold by 8 ways

SellerLaneRate
Fireworks AI aggregatorstandard$0.15per Mtok in$0.6per Mtok outraw.githubusercontent.com · read 2026-09-16
Nous Research aggregatorstandard$0.2per Mtok in$2.4per Mtok outinference-api.nousresearch.com · read 2026-09-12
Novita AI aggregatorstandard$0.2per Mtok in$1per Mtok outapi.novita.ai · read 2026-08-25
OpenRouter 2 ways$0.2per Mtok in$2.4per Mtok out
OpenRouter aggregatorstandard$0.2per Mtok in$2.4per Mtok outopenrouter.ai · read 2026-08-24
OpenRouter aggregatorsiliconflow/fp8$0.29per Mtok in$1per Mtok outopenrouter.ai · read 2026-08-25
DeepInfra aggregatorstandard$0.29per Mtok in$0.99per Mtok outapi.deepinfra.com · read 2026-08-25
SiliconFlow aggregatorstandard$0.29per Mtok in$1per Mtok outmodels.dev · read 2026-09-16
PPIO aggregatorstandard$0.75per Mtok in$7.5per Mtok outapi.ppinfra.com · read 2026-09-10

About

Qwen3 VL 30B A3B Thinking — a text model from Alibaba, sold by 7 companies from $0.15 in and $0.6 out per million tokens.

It takes text and images and returns text, with a context window of 262,144 tokens. It was published in October 2025, trained on material up to March 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning. Seven companies sell it. The cheapest is $0.15 in and $0.6 out per million tokens at Fireworks AI. Beside the standard rate there is a regional lane.

Every current figure

Maker
Alibaba
Register
model
Takes
text + image
Returns
text
Context
262,144 tokens
Longest answer
262,000 tokens
Published
October 2025
Knowledge to
March 2025
Parameters
31 billion
Licence
not read
Sellers
7
Maker's own price
not read
Price
$0.15 in and $0.6 out per million tokens — Fireworks AI

Known as 1 name

Qwen/Qwen3-VL-30B-A3B-Thinking