RETIRING OCT 10 2026VISION VALUE128K CONTEXTTEXT + VISIONQWEN3 VL FLASH REPLACEMENT
Qwen VL Plus API Pricing
Retiring October 10, 2026: Alibaba has announced that qwen-vl-plus goes offline on that date, after which calls fail. Alibaba's notice points to the Qwen3.6 and Qwen3.7 series instead. Qwen VL Plus is the legacy low-cost Qwen vision-language row for visual understanding. Alibaba lists the International/Singapore baseline at $0.21/M input and $0.63/M output; the current snapshot is qwen-vl-plus-2025-08-15. Checked by hand against alibabacloud.com.
Input - per 1M tokens
$0.21/M
Source Alibaba Cloud flat
Output - per 1M tokens
$0.63/M
Context 128K flat
Cache N/A
$0.21/M
Cache no dollar row not listed
Effective - agentic blend
$0.244/M
92/8 split - no cache
§ 01 / TERMINAL
Run the numbers.
Live calculator pre-loaded with current Qwen VL Plus 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
—
§ 02 / SCENARIOS
Real-world presets.
VISION
Invoice extraction
$0.00176/doc
UI QA
Screenshot inspection
$0.00315/screen
VIDEO
Clip frame review
$0.00724/clip
CHARTS
Dashboard explain
$0.00149/image
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 430
Words 64
Tokens (estimated) 82 tokens
Cost as input · uncached $0.00002 USD
Cost as output · uncached $0.00005 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Qwen VL Plus Current | $0.21 | $0.63 | $0.244 agentic 92/8 | 128K | Legacy low-cost vision apps |
| Qwen3 VL Plus | $0.20 | $1.60 | $0.312 +28% | 256K | Current vision and document understanding |
| Qwen3 VL Flash | $0.05 | $0.40 | $0.078 deprecated · −3.1× | 256K | Cheap high-volume vision tasks |
| Qwen VL Max | $0.80 | $3.20 | $0.992 deprecated · +4.1× | 128K | Legacy visual reasoning workloads |
| Qwen 3.5 Plus | $0.40 | $2.40 | $0.56 +2.3× | 256K | Current Qwen production default |
| GPT-5.4 mini | $0.75 cache $0.075 | $4.50 | $0.541 +2.2× | 400K | OpenAI mini coding and CUA |
| Gemini 3.8 Flash | $0.75 cache $0.075 | $3.75 | $0.481 +97% · promo | 1M | Google long-context Flash workloads |
Frequently asked.
Practical pricing questions, separated from calculator assumptions and regional tiers.
Q · 01 When does Qwen VL Plus stop working? +
Alibaba announced on April 13, 2026 that
qwen-vl-plus goes offline on October 10, 2026 (00:00, UTC+8) in the Beijing and Singapore regions; after that, calls fail. Its notice recommends moving to the Qwen3.6 or Qwen3.7 series. Until then the model bills at the rates on this page.Q · 02 What is Qwen VL Plus priced at? +
Qwen VL Plus is listed at
$0.21/M input and $0.63/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 Plus? +
Qwen3.6 Flash is the newer Alibaba row to compare first for new projects (Qwen3 VL Flash, suggested here before, goes offline on the same October 10 date). Qwen VL Plus remains listed for compatibility, but new traffic should usually benchmark the replacement before staying on the legacy SKU.
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
$0.21/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 Plus's effective blended cost is
$0.24/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.