Cracked AI Engineering

Llama 3.3 70B

Venice AIOpen Weights

The Venice AI Llama 3.3 70B AI model offers a massive context window of 65,536 tokens and an output limit of 8,192 tokens, making it ideal for complex text input and function calling tasks. With open weights and a training data cutoff in 2023, developers can trust in the model's reliability and up-to-date capabilities. Priced at $0.7/M input and $2.8/M output tokens, this model is a cost-effective solution for advanced AI projects.

Key Specifications

Context Window

66K tokens

Max Output Tokens

8K tokens

Input Pricing

$0.70

per million tokens

Output Pricing

$2.80

per million tokens

Capabilities

  • Text Generation
  • Function Calling

Additional Details

Provider
Venice AI
Release Date
June 9, 2025
Supported Input Types
text

Compare with Similar Models