Command A (03-2025)
cohere-command-a-03-2025
Last refreshed 2026-05-16. Next refresh: weekly.
Command A (03-2025) is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.
Decision context: RAG task fit, 1 tracked provider route, and research from 2026-01-01.
Use it for
- Teams evaluating rag, agents, and long context
- Workloads that can use a 256k context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Vision or document-understanding workloads
Cheapest output
$10.00
Microsoft Foundry per 1M tokens
Provider routes
1
Tracked API hosts
Quality / dollar
Unknown
No task benchmark coverage yet
Freshness
2026-01-01
Researched 137d ago
Top use-case fit
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Microsoft Foundry | $2.50 | $10.00 | Serverless |
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
About
Cohere's most performant model to date. Command A excels at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. It has 150% higher throughput compared to Command R+ (08-2024) and requires only two GPUs to run.
Command A (03-2025) has a 256K-token context window.
Command A (03-2025) input tokens at $2.5/1M, output at $10/1M.
