Command A by Cohere is a performant enterprise model for tool use, RAG, agents, multilingual use cases, and 256K context.
Capabilities, design details, and architectural traits
Command A is Cohere’s most performant model for enterprise use cases, positioned around tool use, retrieval-augmented generation, agents, and multilingual workflows. The official docs describe it as a text-only model with a 256K context window and support for structured outputs and reasoning.
Cohere states that Command A has 111 billion parameters and requires two GPUs to run, specifically A100s or H100s. The model is described as significantly more efficient at inference time, with 150% higher throughput than Command R+ 08-2024. The docs also say it is interactive by default and optimized for conversation.
The model is documented as especially strong in real-world enterprise tasks that require breaking questions into subgoals, active information seeking, and financial numerical manipulation. Cohere also notes that it can respond in the user’s language or follow instructions to output a different language. The model supports citations when working from grounded document snippets.
Independent evaluations · Artificial Analysis
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Cohere | Anthropic | Anthropic |
| Release Date | March 13, 2025 | July 24, 2026 | June 9, 2026 |
| Knowledge Cutoff | Aug 2024 | May 2026 | - |
| Context & Limits | |||
| Context Window | 256K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $2.50 Best Input Pricing | $5 | $10 |
| Output Pricing | $10 Best Output Pricing | $25 | $50 |
| Modalities | |||
| Inputs | text | textimage | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 7.5 | 63.1 Best Intelligence Index | 62.1 |
| Coding Index | - | 78.0 Best Coding Index | 76.5 |
| Agentic Index | - | 59.2 Best Agentic Index | 56.6 |
Graduate-level reasoning and expert Q&A evaluation.
Extremely difficult logical reasoning and knowledge.
Logical reasoning over long context windows.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.