Command A
Release Date: 3/13/2025
Benchmarked by 
Command A is Cohere's most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. It supports a context length of 256K tokens with high throughput.
Avg. Accuracy
44.57%
Latency
44.19s
Cost (In/Out)
2.5 / 10
Context Window
256k
Max Output Tokens
8k
Input Modality
Benchmarks
Accuracy
Rankings
Academic Benchmarks
Proprietary Benchmarks (contact us to get access)