deepseek/deepseek-v4-flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
This model's cache
This model page returns the exact headers below. The page and /api/models/deepseek--deepseek-v4-flash share the model:deepseek--deepseek-v4-flash tag, so invalidation stays scoped to this model.
/models/deepseek--deepseek-v4-flashpublic, max-age=300, stale-while-revalidate=3600catalogmodel:deepseek--deepseek-v4-flashWorkers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.
export const Route = createFileRoute('/models/$modelSlug')({
headers: () => ({
'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
'Cache-Tag': 'catalog,model:deepseek--deepseek-v4-flash',
}),
})Invalidate this cache tag
await ctx.cache.purge({ tags: ['model:deepseek--deepseek-v4-flash'] })Use this when one model changes and you do not want to evict the whole catalog.
- Released
- Apr 24, 2026
- Last updated
- Apr 24, 2026
- Context window
- 1M tokens
- Max output
- 384K tokens
- Open weights
- Yes
- Family
- Deepseek Flash
Starts at
$0.09
per 1M input tokens
Output
$0.18
Sellers
10
No cart or checkout in this MVP — pick a provider below and open their docs when you're ready to use it.
Sorted by lowest input price
| Provider | Input / 1M | Output / 1M | Context | |
|---|---|---|---|---|
OpenRouter deepseek/deepseek-v4-flash | $0.09 | $0.18 | 1.0M | Docs |
Vercel AI Gateway deepseek/deepseek-v4-flash | $0.14 | $0.28 | 1M | Docs |
NovitaAI deepseek/deepseek-v4-flash | $0.14 | $0.28 | 1.0M | Docs |
ZenMux deepseek/deepseek-v4-flash | $0.14 | $0.28 | 1M | Docs |
Merge Gateway deepseek/deepseek-v4-flash | $0.14 | $0.28 | 1M | Docs |
Kilo Gateway deepseek/deepseek-v4-flash | $0.14 | $0.28 | 1.0M | Docs |
NanoGPT deepseek/deepseek-v4-flash | $0.14 | $0.28 | 1.0M | Docs |
DeepSeek deepseek-v4-flash | $0.14 | $0.28 | 1M | Docs |
OrcaRouter deepseek/deepseek-v4-flash | $0.19 | $0.37 | 1M | Docs |
AnyAPI deepseek/deepseek-v4-flash | Quote | Quote | 1M | Docs |
deepseek/deepseek-v4-pro
DeepSeek V4 Pro
Open MoE flagship with million-token context for coding and long agent runs
deepseek/deepseek-chat
DeepSeek Chat
DeepSeek chat model for instruction following, coding, and analysis
deepseek/deepseek-reasoner
DeepSeek Reasoner
DeepSeek reasoning model for multi-step analysis, math, coding, and tools