Last verified
RETIRED OCT 10 2026VISION MODEL128K CONTEXTTEXT + VISIONQWEN3 VL REPLACEMENT

Qwen VL Max API Pricing

Retired October 10, 2026: Alibaba took qwen-vl-max offline on that date, and calls to it now fail; the model is gone from Alibaba's pricing page. Alibaba's notice points to the Qwen3.6 and Qwen3.7 series instead. Qwen VL Max is the legacy flagship Qwen vision-language row for complex visual reasoning. Alibaba lists the International/Singapore baseline at $0.8/M input and $3.2/M output; the current snapshot is qwen-vl-max-2025-08-13. Checked by hand against alibabacloud.com.

Input - per 1M tokens
$0.80/M
Source Alibaba Cloud flat
Output - per 1M tokens
$3.20/M
Context 128K flat
Cache N/A
$0.80/M
Cache no dollar row not listed
Effective - agentic blend
$0.992/M
92/8 split - no cache
§ 01 / TERMINAL

Qwen VL Max API cost calculator.

Live calculator pre-loaded with current Qwen VL Max rates. Tweak spend, output mix, or cache assumptions and share the URL to share the calculation.

$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Qwen VL Max cost on real workloads.

VISION

Invoice extraction

$0.00736/doc
6,000 in - 800 out~13,586 units/$100
UI QA

Screenshot inspection

$0.013/screen
12,000 in - 1,000 out~7,812 units/$100
VIDEO

Clip frame review

$0.029/clip
30,000 in - 1,500 out~3,472 units/$100
CHARTS

Dashboard explain

$0.00624/image
5,000 in - 700 out~16,025 units/$100
§ 03 / TOKENIZER

Qwen VL Max token counter and cost.

What's a token →
Calibrated · measured on the vendor's tokenizer · 2026-06-10 Auto-counts as you type

Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (Qwen/Qwen3.5-397B-A17B, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.

Characters 431
Words 65
Tokens (estimated) 82 tokens
Cost as input · uncached $0.00007 USD
Cost as output · uncached $0.00026 USD
§ 04 / SHELF

Qwen VL Max vs similar models.

All models →
Model Input /M Output /M Effective blended Context Best for
Qwen VL Max Current $0.80 $3.20 $0.992 agentic 92/8 128K Legacy visual reasoning workloads
Qwen3 VL Plus $0.20 $1.60 $0.312 −3.2× 256K Current vision and document understanding
Qwen3 VL Flash $0.05 $0.40 $0.078 retired 256K Cheap high-volume vision tasks
Qwen VL Plus $0.21 $0.63 $0.244 retired 128K Legacy low-cost vision apps
Qwen 3.5 Plus $0.40 $2.40 $0.56 −44% 1M Current Qwen production default
GPT-6.1 Terra $1.00 cache $0.05 $5.00 $0.645 −35% 1.05M OpenAI's fast, efficient GPT-6 tier
Gemini 3.8 Flash $0.75 cache $0.075 $3.75 $0.481 −2.1× · promo 1M Google long-context Flash workloads

Qwen VL Max API pricing FAQ.

Practical pricing questions, separated from calculator assumptions and regional tiers.

Q · 01 When did Qwen VL Max stop working? +
Alibaba announced on April 13, 2026 that qwen-vl-max would go offline on October 10, 2026 (00:00, UTC+8) in the Beijing and Singapore regions, and it has: on October 21, 2026 the model is no longer on Alibaba's pricing page, and calls to it fail. Its notice recommends moving to the Qwen3.6 or Qwen3.7 series. The rates on this page are the last Alibaba published.
Q · 02 What is Qwen VL Max priced at? +
Qwen VL Max is listed at $0.8/M input and $3.2/M output in Alibaba Cloud Model Studio's International/Singapore deployment section. The page stores USD per-million-token pricing.
Q · 03 What replaced Qwen VL Max? +
Qwen3 VL Plus is the newer Alibaba row to compare first for new projects. Qwen VL Max was kept listed for compatibility until Alibaba took it offline on October 10, 2026; traffic that used it has to move to the replacement.
Q · 04 Does this page use International or Global pricing? +
This page uses Alibaba Cloud Model Studio International deployment pricing, where endpoint and data storage are in Singapore and inference resources are dynamically scheduled globally excluding Chinese Mainland. Global, US, EU, China (Hong Kong), and Chinese Mainland sections can list different prices.
Q · 05 Is prompt caching priced separately? +
Alibaba marks context-cache support on some Qwen rows, but this row does not publish a concrete cache-read dollar price in the pricing table. The calculator therefore treats cached input as the same $0.8/M baseline instead of inventing a discount.
Q · 06 How is the effective price calculated? +
AI//COST uses the same 92/8 agentic blend everywhere. With no separate cache-read price published for this row, Qwen VL Max's effective blended cost is $0.99/M.
Q · 07 Is there a Batch Invocation discount? +
Alibaba documents Batch Invocation as 50% off real-time input and output tokens for supported Qwen rows. The quote tiles show real-time list pricing; batch economics should be treated as a separate calculator variant.
Q · 08 Does Alibaba include a free quota? +
Many International Model Studio rows include a 1 million token free quota that is valid for 90 days after activating Model Studio. Free-quota eligibility is deployment- and model-specific, so production estimates should use the paid list prices shown here.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against alibabacloud.com · Last verified Oct 21, 2026
Methodology Report a correction More by Y.V.