DeepSeek · Text

DeepSeek V4.1 Flash

Text model by DeepSeek, good for writing, editing, summarizing and chat.

Pricing

Charged by actual usage

Unit: points / 1M tokens

Input: 100≈ $0.2
Cache hit: 2≈ $0.004
Output: 400≈ $0.8

Unit: points / 1M tokens
Input	Cache hit	Output
100≈ $0.2	2≈ $0.004	400≈ $0.8

Cache hit: a prefix repeated from earlier requests (such as a system prompt or a long document you keep referring to) is cached, and the cached part is billed at the cache price, about 2% of the input price.
Input and output are billed separately by actual tokens; reasoning tokens count as output.

This model has no member discount; members pay the list price. See plans

About this model

Text model by DeepSeek, good for writing, editing, summarizing and chat. Pick this model in Beav to use it; points are charged at the prices above.

Use in Beav

01Download Beav and sign in
02Choose DeepSeek V4.1 Flash in the model picker
03Use it for writing, editing, summarizing and chat