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?'})Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
 DeepSeek | 1M | 1.7s | 112tps | $0.14/M | $0.28/M | Read:$0.0/M Write:— | — | — | +1 | 04/23/2026 | ||
 Novita AI | 1M | 0.9s | 163tps | $0.14/M | $0.28/M | Read:$0.03/M Write:— | — | — | +3 | 04/23/2026 | ||
 DeepInfra | 1M | 1.2s | 25tps | $0.14/M | $0.28/M | Read:$0.03/M Write:— | — | — | +3 | 04/23/2026 | ||
 Blackbox | 1M | $0.14/M | $0.28/M | Read:$0.0/M Write:— | — | — | +1 | 04/23/2026 | ||||
 Fireworks | 1M | 1.7s | 135tps | $0.14/M | $0.28/M | Read:$0.0/M Write:— | — | — | +1 | 04/23/2026 | ||
 Azure | 1M | 1.7s | 110tps | $0.19/M | $0.51/M | — | — | +1 | 04/23/2026 |