whichllm — Browse and compare AI model specs and pricing

Helicone

DeepSeek R1 Distill Llama 70B

deepseek-thinking

Model ID deepseek-r1-distill-llama-70b
Provider Helicone
Family deepseek-thinking
Status -
Knowledge Cutoff 2025-01
Release Date 2025-01-20
Input Modalities text
Output Modalities text
Context Window 128000
Input Limit -
Output Limit 4096
Tool Calling Yes
Reasoning Yes
Structured Output -
Temperature Control Yes
Open Weights No
Input Cost / 1M tokens $0.03
Output Cost / 1M tokens $0.13
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -