Command A is our most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.
| Model | Context | Max out | Pricing |
|---|---|---|---|
| Cohere: command-a-03-2025 | 256K | 8K | $2.5$10 |
| Cohere: command-a | — | — | $2.5$10 |
| OpenRouter: cohere/command-a-03-2025 | — | — | $2.5$10 |
| OpenRouter: cohere/command-a | — | — | $2.5$10 |
/v1/models/cloudflare-ai-gateway/cohere/command-a-03-2025