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 | 0.5s | 192tps | $1.74/M$0.43/M | $3.48/M$0.87/M | Read:$0.0/M Write:— | — | — | +1 |    +4 | 04/23/2026 | |||
| 164K | 0.4s | 82tps | $0.28/M | $0.42/M | Read:$0.03/M Write:— | — | — |   +1 | 12/01/2025 | ||||
| 164K | 1.0s | 56tps | $0.26/M | $0.38/M | Read:$0.13/M Write:— | — | — | +1 |  +1 | 12/01/2025 | |||
| 131K | 1.6s | 29tps | $0.27/M | $1.00/M | Read:$0.14/M Write:— | — | — | +1 |  | 09/22/2025 | |||
| 164K | 0.9s | 42tps | $0.21/M | $0.79/M | Read:$0.13/M Write:— | — | — | +1 |  +1 | 08/21/2025 | |||
| 160K | 0.3s | 116tps | $1.35/M | $5.40/M | Read:$0.35/M Write:— | — | — | +1 | | 01/20/2025 |