Last verified
RETIRING OCT 10 2026QWEN3.6 MAX256K CONTEXTTEXT + CODEINTERNATIONAL PRICENO CACHE ROW

Qwen3.6 Max Preview API Pricing

Retiring October 10, 2026: Alibaba has announced that qwen3.6-max-preview goes offline on that date, after which calls fail. Alibaba recommends Qwen3.7 Max instead. Qwen3.6 Max Preview is an Alibaba Qwen3.6 text/coding model. Alibaba publishes the official Singapore/International row directly in US dollars: $1.3/M input and $7.8/M output for prompts up to 128K tokens.

Input - per 1M tokens
$1.30/M
Base International row standard
Output - per 1M tokens
$7.80/M
Long row $12/M output standard
Cached input - not itemized
$1.30/M
Cache no exact token price not listed
Effective - agentic blend
$1.82/M
92/8 split - no cache discount
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with the verified Qwen3.6 Max Preview International base row. The 128K-256K long-context row is $2/M input and $12/M output.

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

Real-world presets.

CODING

Agent implementation

$0.083/task
28,000 in - 6,000 out~1,201 units/$100
RAG

Long-doc answer

$0.156/answer
90,000 in - 5,000 out~641 units/$100
CHATBOT

Product assistant

$0.014/turn
5,000 in - 1,000 out~6,993 units/$100
BATCH

Knowledge summary

$0.056/doc
32,000 in - 1,800 out~1,797 units/$100
§ 03 / TOKENIZER

Paste text. See tokens. See 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 392
Words 64
Tokens (estimated) 75 tokens
Cost as input · uncached $0.0001 USD
Cost as output · uncached $0.00059 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Qwen3.6 Max Preview Current $1.30 $7.80 $1.82 agentic 92/8 256K Preview Qwen Max workloads
Qwen3.7 Plus $0.40 $1.60 $0.496 −3.7× · promo 1M balanced
Qwen3.7 Max $2.50 $7.50 $2.90 +59% · promo 1M frontier
Qwen3 Next 80B A3B Instruct $0.15 $1.20 $0.234 deprecated · −7.8× 262K text
Qwen3 Next 80B A3B Thinking $0.15 $1.20 $0.234 deprecated · −7.8× 262K reasoning
Qwen3 30B A3B Instruct 2507 $0.20 $0.80 $0.248 deprecated · −7.3× 262K text
DeepSeek V4.1 Flash $0.30 cache $0.006 $1.20 $0.15 −12× 1M budget
GPT-5.4 mini $0.75 cache $0.075 $4.50 $0.541 −3.4× 400K light
§ 05 / DEEP LINKS

Specific scenarios.

All calculators →

Audit links

Provider hub →

Frequently asked.

Short answers for teams evaluating Qwen3.6 Max Preview against other Qwen tiers.

Q · 01 When does Qwen3.6 Max Preview stop working? +
Alibaba announced on June 8, 2026 that qwen3.6-max-preview goes offline on October 10, 2026 (00:00, UTC+8) in the Beijing and Singapore regions; after that, calls fail. Its notice recommends Qwen3.7 Max. Until then the model bills at the rates on this page.
Q · 02 What is the Qwen3.6 Max Preview input price? +
Alibaba lists $1.3/M for input tokens up to 128K in the Singapore/International row. That row is published in US dollars, so nothing is converted.
Q · 03 What is the Qwen3.6 Max Preview output price? +
The base International output row is $7.8/M. Output on the 128K-256K row is higher, at $12/M.
Q · 04 Does Alibaba list exact cache pricing? +
No exact prompt-cache token price is itemized for this row, so the calculator keeps cache disabled instead of inventing a discount.
Q · 05 Why use International pricing? +
AI//COST uses Alibaba's Singapore/International row for non-mainland deployment. Mainland and other regional rows can differ, so the source URL is preserved for invoice audits.
Q · 06 Is this a text LLM page? +
Yes. This page covers the text/code API model. Media, audio, image, and video models are intentionally handled separately.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against alibabacloud.com · Last verified Jul 27, 2026
Methodology Report a correction More by Y.V.