ZeroTwo home

Qwen 3.6 Flash

Default
Qwen 3.6 Flash is Alibaba's fast multimodal model with hybrid reasoning via enable_thinking, a 1M token context window, and support for text, image, and video input. Thinking mode is enabled by default for stronger reasoning on complex tasks.
Qwen 3.6 Flash is Alibaba's fast multimodal model with hybrid reasoning via enable_thinking, a 1M token context window, and support for text, image, and video input. Thinking mode is enabled by default for stronger reasoning on complex tasks.

Qwen 3.6 Flash is an AI model from Qwen, available on ZeroTwo. It costs $0.25 per million input tokens and $1.50 per million output tokens, has a 1,000,000-token context window, can return up to 65,536 output tokens.

Price
$0.25 • $1.50
Input • Output

Qwen 3.6 Flash is Alibaba's fast multimodal model with hybrid reasoning via enable_thinking, a 1M token context window, and support for text, image, and video input. Thinking mode is enabled by default for stronger reasoning on complex tasks.

1,000,000 context window
65,536 max output tokens
Reasoning token support
Pricing
Pricing is based on the number of tokens used. For tool-specific models, like search and computer use, there's a fee per tool call. See details in the pricing page.

Requests above 256,000 input tokens move the whole request to long-context rates: $1.00 input and $4.00 output per million tokens.

Text tokens
Per 1M tokens
∙
Batch API price
Input
$0.25
Cached input
Output
$1.50
Quick comparison
Input
Cached input
Output
Qwen 3.6 Flash
$0.25

Questions

How much does Qwen 3.6 Flash cost?

Qwen 3.6 Flash is priced at $0.25 per million input tokens and $1.50 per million output tokens. On ZeroTwo it is included in your plan's credits rather than billed per token.

What is Qwen 3.6 Flash's context window?

Qwen 3.6 Flash accepts up to 1,000,000 tokens of context and can return up to 65,536 output tokens.

Can I use Qwen 3.6 Flash for free?

You can try Qwen 3.6 Flash on ZeroTwo's free plan, which includes a monthly credit allowance across every model in the catalogue. Heavier use moves to a paid plan rather than a per-token bill.