DeepSeek Reasoner
Updated Sep 11, 2026
deepseek-thinking1.0M context384k max outputreleased Dec 1, 2025Open weightsReasoningTool calling
Official
—
output per 1M tokens
Providers
4
offering this model
Spread
5.8×
max / min output
Offers
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge.
| Provider | 1M input | 1M output | 1M cache read | 1M cache write | Context |
|---|
| OrcaRouteropen | Cheapest$0.147 | Cheapest$0.295 | $0.028 | — | 1.0M |
| NanoGPTopen | $0.4 | $1.7 | $0.2 | — | 64k |
| Helicone | $0.56 | $1.68 | $0.07 | — | 128k |
Other deepseek-thinking models