whichllm — Browse and compare AI model specs and pricing

FastRouter

DeepSeek R1 Distill Llama 70B

deepseek-thinking

Model ID deepseek-ai/deepseek-r1-distill-llama-70b
Provider FastRouter
Family deepseek-thinking
Status -
Knowledge Cutoff 2024-10
Release Date 2025-01-23
Input Modalities text
Output Modalities text
Context Window 131072
Input Limit -
Output Limit 131072
Tool Calling No
Reasoning Yes
Structured Output -
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.03
Output Cost / 1M tokens $0.14
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -