TokenCalculator.com

LLM Models

Compare pricing and specifications for large language models from all major providers.

Meta Models

Meta Llama 3.3 70B Instruct

2024-12 • 128K context window

Meta's latest 70B parameter model with improved performance and capabilities, offering state-of-the-art results for its size.

Input: $0.6000 / 1K tokens
Output: $0.6000 / 1K tokens

Meta Llama 3.2 90B Vision Instruct

2024-09 • 128K context window

Meta's multimodal model combining text and vision capabilities with strong performance across various tasks.

Input: $1.2000 / 1K tokens
Output: $1.2000 / 1K tokens

Meta Llama 3.2 11B Vision Instruct

2024-09 • 128K context window

A smaller, efficient multimodal model from Meta with vision capabilities, suitable for edge deployment and cost-sensitive applications.

Input: $0.1800 / 1K tokens
Output: $0.1800 / 1K tokens

Meta Llama 3.1 405B Instruct

2024-07 • 128K context window

Meta's largest and most capable Llama 3.1 model, designed for complex reasoning, coding, and nuanced instruction following.

Input: $2.7000 / 1K tokens
Output: $2.7000 / 1K tokens

Meta Llama 3.1 70B Instruct

2024-07 • 128K context window

A large instruction-tuned model from Meta's Llama 3.1 series, offering a strong balance of performance and efficiency for a wide range of tasks.

Input: $0.6000 / 1K tokens
Output: $0.6000 / 1K tokens

Meta Llama 3.1 8B Instruct

2024-07 • 128K context window

A highly efficient instruction-tuned model from Meta's Llama 3.1 series, suitable for fast, on-device, or edge applications.

Input: $0.0600 / 1K tokens
Output: $0.0600 / 1K tokens