whichllm — Browse and compare AI model specs and pricing

NovitaAI

DeepSeek R1 Distill Qwen 32B

deepseek-thinking

Model ID deepseek/deepseek-r1-distill-qwen-32b
Provider NovitaAI
Family deepseek-thinking
Status -
Knowledge Cutoff -
Release Date 2025-01-20
Input Modalities text
Output Modalities text
Context Window 64000
Input Limit -
Output Limit 32000
Tool Calling No
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.30
Output Cost / 1M tokens $0.30
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -