deepinfra / nvidia/NVIDIA-Nemotron-3.5-Lightning
Pricing Overview
Input Cost Per 1M Tokens
$0.08
per 1M tokensOutput Cost Per 1M Tokens
$0.20
per 1M tokensCache Read Input Token Cost
$0.04
per 1M tokensQuick Cost Calculator
$0.00024
Avg. Cost / Interaction
$0.024
Total Daily Cost
$0.72
Total Monthly Cost
Daily Interactions: 100
System Prompt Tokens: 500
Avg. Input Tokens per Interaction: 500
Avg. Output Tokens per Interaction: 800
Based on 500 system prompt tokens, 500 input tokens, and 800 output tokens per interaction
Limits & Specifications
- max input tokens
262,144 tokens
Use Cases
- Customer Support Chatbot
Automated customer service with context-aware responses
- Content Generation
Blog posts, marketing copy, and creative writing
- Code Assistant
Programming help, code review, and debugging
- Data Analysis
Process and analyze large datasets with insights
Provider Information
Provider: deepinfra
Model: nvidia/NVIDIA-Nemotron-3.5-Lightning
Last Updated: 8/31/2026