DeepSeek-Reasoner (DeepSeek-V3.1 Thinking Mode) is designed for advanced reasoning, mathematical problem-solving, and complex coding tasks. It uses chain-of-thought reasoning to break down complex problems and achieve superior performance on reasoning benchmarks. Supports 128K context with a default output of 32K tokens (max 64K) for extensive reasoning chains.
Input: Text
Output: Text
Providers
deepseek
Credits
Context128k
Max Output64k
Input$0.560/1M
Output$1.68/1M
Cache Read$0.070/1M
Cache Write—
deepinfra
Credits
Context128k
Max Output64k
Input$0.500/1M
Output$2.15/1M
Cache Read$0.400/1M
Cache Write—
openrouter
Credits
Context128k
Max Output64k
Input (Max)$3.16/1M
Output (Max)$8.44/1M
Cache Read—
Cache Write—
Quick Start
Use DeepSeek Reasoner through Helicone's AI Gateway with automatic logging and monitoring.