Venice AI (Reseller)
Llama 3.3 70B Pricing
API pricing for Llama 3.3 70B via Venice AI. Input tokens cost $0.7/1M, output tokens cost $2.8/1M with 131K context window.
Last updated:
Tools
Input Cost
$0.7
per 1M tokens
Output Cost
$2.8
per 1M tokens
Context Window
131K
tokens
Cost Calculator
Estimated Cost:
$0.00
Model Details
Reseller
Venice AI
Model ID
llama-3.3-70b
Context Window
131K tokens
Max Output
32768 tokens
Sources