Qwen3.6-35B-A3B

by Qwen

Qwen3.6-35B-A3B is a compact mixture-of-experts model tuned for low latency with multi-token prediction. It accepts text and images and has a 262,144-token context window. It is one of the lower-cost options for visual analysis.

Best for: Affordable image and text tasks with a shorter context.

262K context

Text
Reasoning
Tool use
Image input
Vision

Model weights

Try it in the playground

Pricing

USD per 1M tokens. The 1h and 24h batch windows will be launching in the coming weeks. Batch model ID: qwen3.6.

Provider	Input	Cached input	Output
Boundlessasap	$0.04	$0.02	$0.35
Boundless<1h-25% off`qwen3.6`	$0.03	$0.015	$0.2625
Boundless<24h-50% off`qwen3.6`	$0.02	$0.01	$0.175

What one request costs

Prompt24Ktokens

Cached prefix17Ktokens

Reply2Ktokens

$0.0011

per request to Qwen3.6-35B-A3B

Prompt: 25.1%
Cached: 29.2%
Reply: 45.7%

The same request, across other models