Nvidia
Deepseek R1
models.dev synced record
Model ID deepseek-ai/deepseek-r1
Provider Nvidia
Family -
Status -
Knowledge Cutoff -
Release Date 2025-01-20
Input Modalities text
Output Modalities text
Context Window 128000
Input Limit -
Output Limit 4096
Tool Calling No
Reasoning Yes
Structured Output No
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens -
Output Cost / 1M tokens -
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -