Last verified
QWEN3.6 PLUS1M CONTEXTTEXT + CODEINTERNATIONAL PRICEEXPLICIT CACHE

Qwen3.6 Plus API Pricing

Qwen3.6 Plus is an Alibaba Qwen3.6 text/coding model. Alibaba publishes the official Singapore/International row directly in US dollars: $0.5/M input and $3/M output for prompts up to 256K tokens.

Input - per 1M tokens
$0.50/M
Base International row standard
Output - per 1M tokens
$3.00/M
Long row $6/M output standard
Cached input - per 1M tokens
$0.05/M
Explicit cache, creation 125% 90% off
Effective - agentic blend
$0.381/M
92/8 split - 82% cache
§ 01 / TERMINAL

Qwen3.6 Plus API cost calculator.

Live calculator pre-loaded with Qwen3.6 Plus's verified Alibaba International rates. Cache hits use Alibaba's published explicit-cache rule: 10% of standard input on a hit and 125% on creation, for blocks kept 5 minutes after the last hit.

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

Qwen3.6 Plus cost on real workloads.

§ 03 / TOKENIZER

Qwen3.6 Plus 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 380
Words 63
Tokens (estimated) 73 tokens
Cost as input · uncached $0.00004 USD
Cost as output · uncached $0.00022 USD
Cost as cached input $0.000004 USD
§ 04 / SHELF

Qwen3.6 Plus vs similar models.

All models →
Model Input /M Output /M Effective blended Context Best for
Qwen3.6 Plus Current $0.50 cache $0.05 $3.00 $0.381 agentic 92/8 1M Balanced long-context Qwen agents
Qwen3.7 Plus $0.40 $1.60 $0.496 +30% · promo 1M balanced
Qwen3.7 Max $2.50 $7.50 $2.90 +7.6× 1M frontier
DeepSeek V4.1 Flash $0.30 cache $0.006 $1.20 $0.15 −2.5× 1M budget
GPT-6.1 Terra $1.00 cache $0.05 $5.00 $0.645 +69% 1.05M OpenAI's fast, efficient GPT-6 tier
§ 05 / DEEP LINKS

Qwen3.6 Plus cost by scenario.

All calculators →

Audit links

Qwen3.6 Plus API pricing FAQ.

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

Q · 01 What is the Qwen3.6 Plus input price? +
Alibaba lists $0.5/M for input tokens up to 256K in the Singapore/International row. That row is published in US dollars, so nothing is converted.
Q · 02 What is the Qwen3.6 Plus output price? +
The base International output row is $3/M. Output on the 256K-1M row is higher, at $6/M.
Q · 03 Does Alibaba list exact cache pricing? +
Yes, as a rule rather than a table row. Alibaba's Context Cache page lists Qwen3.6 Plus for explicit cache: a hit bills at $0.05/M, 10% of standard input, and creating a cache block bills at $0.625/M, 125% of it. Blocks last 5 minutes and the timer resets on a hit. The model is not on the implicit-cache list, so nothing is discounted until you mark blocks yourself.
Q · 04 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 · 05 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.