DeepSeek V4 Flash
DeepSeek V4 Flash is DeepSeek's April 23, 2026 efficiency-tier model in the V4 series. It pairs a hybrid attention architecture with a context window of 1.0M tokens and supports reasoning, tool use, and implicit caching.
ReasoningTool UseImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'deepseek/deepseek-v4-flash', prompt: 'Why is the sky blue?'})More models by DeepSeek
| Model |
|---|
| 1M | 0.4s | 106tps | $1.74/M$0.43/M | $3.48/M$0.87/M | Read:$0.0/M Write:— | — | — | +1 |    +3 | 04/23/2026 | |||
| 164K | 0.7s | 101tps | $0.28/M | $0.42/M | Read:$0.03/M Write:— | — | — | +3 |  +2 | 12/01/2025 | |||
| 164K | 0.6s | 124tps | $0.28/M | $0.42/M | Read:$0.03/M Write:— | — | — | +3 | +2 | 12/01/2025 | |||
| 131K | 1.7s | 27tps | $0.27/M | $1.00/M | Read:$0.14/M Write:— | — | — |  | 09/22/2025 | ||||
| 164K | 0.9s | 38tps | $0.21/M | $0.79/M | Read:$0.13/M Write:— | — | — |  +2 | 08/21/2025 | ||||
| 164K | 1.1s | 38tps | $0.27/M | $1.12/M | Read:$0.14/M Write:— | — | — | | 12/26/2024 |