Cohere AI Models - Token Counter & Cost Calculator
Calculate token usage and API costs for Cohere's enterprise-grade language models. Get accurate pricing estimates for Command R+, Command R, and more.
Available Cohere Models
Command A
Context: 256,000 tokens
Input: $2.5/1MOutput: $10/1M
Largest, most performant model, ideal for building enterprise agents with a low compute footprint. 8K maximum output tokens.
Command R
Context: 128,000 tokens
Input: $0.15/1MOutput: $0.6/1M
Midsized model providing the best combination of efficiency and performance. 4K maximum output tokens.
Command R7B
Context: 128,000 tokens
Input: $0.0375/1MOutput: $0.15/1M
Smallest model, made for building powerful applications on commodity GPUs and edge devices. 4K maximum output tokens.