deepseek/deepseek-r1
Classic open reasoning model for transparent math, coding, and deliberate problem solving
This model's cache
This model page returns the exact headers below. The page and /api/models/deepseek--deepseek-r1 share the model:deepseek--deepseek-r1 tag, so invalidation stays scoped to this model.
/models/deepseek--deepseek-r1public, max-age=300, stale-while-revalidate=3600catalogmodel:deepseek--deepseek-r1Workers 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-r1',
}),
})Invalidate this cache tag
await ctx.cache.purge({ tags: ['model:deepseek--deepseek-r1'] })Use this when one model changes and you do not want to evict the whole catalog.
- Released
- Jan 20, 2025
- Last updated
- May 29, 2025
- Context window
- 128K tokens
- Max output
- 32.8K tokens
- Open weights
- Yes
- Family
- Deepseek Thinking
Starts at
Free
per 1M input tokens
Output
Free
Sellers
5
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
deepseek/deepseek-v4-flash
DeepSeek V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
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