DeepSeek V4.1 Flash

by DeepSeek

DeepSeek V4.1 Flash is a 552B-parameter mixture-of-experts model. It activates 8B parameters for input tokens and 16B for output tokens. The model handles coding, reasoning, images, and tool use, with a 1,048,576-token context window. Its smaller KV cache can also reduce costs for long-running requests that reuse context.

Best for: Fast coding agents that need image input and a long context.

1M context

Text
Reasoning
Tool use
Image input
Vision

Model weights

Try it in the playground

Pricing

USD per 1M tokens.

Window	Input	Cached input	Output
asap	$0.20	$0.01	$1.00

What one request costs

Prompt94Ktokens

Cached prefix66Ktokens

Reply2Ktokens

$0.0078

per request to DeepSeek V4.1 Flash

Prompt: 72.3%
Cached: 8.4%
Reply: 19.2%

The same request, across other models