DeepSeek-R1-Distill-Llama-70B Performance Analytics - Real-time Metrics, Token Usage & Cost Analysis

Back to Model Details
deepinfra

DeepSeek-R1-Distill-Llama-70B

deepinfra • Performance Analytics

Core Performance Metrics

Total Requests
5
100.0%
Error Rate
0.00%
0.0%
Total Input Tokens
56,143
Total Output Tokens
4,116

Access DeepSeek-R1-Distill-Llama-70B through LangDB AI Gateway

Recommended

Integrate with deepseek's DeepSeek-R1-Distill-Llama-70B and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API
Cost Optimization
Enterprise Security
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests

Performance Percentiles

Response Time
16.04s
100.0%
TTFT
1.22s
TPS (Tokens/Second)
751.2 TPS
100.0%
TPOT (Time/Output Token)
0.020ms

Performance Trends

Sep 22 - Sep 29, 2025

Request Volume
Daily API requests
5
Performance (TPS)
Tokens per second
751.16 tokens/s
Response Time
Average response latency (ms)
16044.20 ms
TTFT
Time to First Token (ms)
1224.80 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution
Input vs Output token usage
Input Tokens:56,143
Output Tokens:4,116
Total Tokens:60,259
Token Usage Timeline
Daily token consumption trends