Qwen 3.6 Flash API Pricing

Qwen 3.6 Flash by Alibaba costs $0.25 per million input tokens and $1.50 per million output tokens.

Price verified from Alibaba's pricing page.

Rates and limits

Input / 1M
$0.25
Output / 1M
$1.50
Cached input / 1M
Not listed
Batch discount
50% off
Context window
1M tokens
Released
March 2026

Pricing note: International (Singapore) deployment. 0-256K input tokens shown; 256K-1M $1 in / $4 out.

What Qwen 3.6 Flash costs per month

Token volume split 3:1 between input and output, with no prompt caching.

Tokens per monthInput / outputStandardBatch API
1M750K / 250K$0.56$0.28
10M7.5M / 2.5M$5.63$2.81
100M75M / 25M$56.25$28.13
Estimate your own workload with Qwen 3.6 Flash

Where to run Qwen 3.6 Flash

Prices above are Alibaba's direct rates. Cloud platforms can charge differently; the cloud platform view compares them.

Qwen 3.6 Flash pricing FAQ

How much does Qwen 3.6 Flash cost per million tokens?

Qwen 3.6 Flash costs $0.25 per million input tokens and $1.50 per million output tokens, as listed on Alibaba's pricing page on September 30, 2026.

How much does Qwen 3.6 Flash cost for 10 million tokens a month?

About $5.63 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $2.81 through the batch API.

What is the context window of Qwen 3.6 Flash?

Qwen 3.6 Flash accepts up to 1,000,000 tokens of context.

Does Qwen 3.6 Flash support prompt caching?

No cached-input price is listed for Qwen 3.6 Flash, so repeated prompt prefixes are billed at the standard input rate.

Is there a batch discount for Qwen 3.6 Flash?

Yes. Requests sent through the batch API cost 50% less: $0.125 per million input tokens and $0.75 per million output tokens.

Where can I use the Qwen 3.6 Flash API?

Qwen 3.6 Flash is available through Alibaba DashScope (Model Studio) and OpenRouter.

Compare with other models

Prices shown as input / output per million tokens. All model prices · Side-by-side comparison