Last refreshed 2026-05-16. Next refresh: weekly.
Why use Command A (03-2025) on Microsoft Foundry?
Microsoft Foundry offers Command A (03-2025) with pay-as-you-go pricing at $2.50/1M input tokens. Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: cohere-command-a-03-2025cohere-command-a-03-2025Request example
cohere-command-a-03-2025.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $2.50 |
| Output tokens | $10.00 |
Capabilities
About Command A (03-2025)
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.
FAQ
What does Command A (03-2025) cost on Microsoft Foundry?
On Microsoft Foundry, Command A (03-2025) costs $2.5 per 1M input tokens and $10 per 1M output tokens.
What is the context window for Command A (03-2025) on Microsoft Foundry?
Command A (03-2025) supports a 256,000 token context window on Microsoft Foundry.
What API model ID do I use for Command A (03-2025) on Microsoft Foundry?
Use the model ID cohere-command-a-03-2025 when calling Microsoft Foundry's API.
Who created Command A (03-2025)?
Command A (03-2025) was created by Cohere as part of the Command model family.
Is Command A (03-2025) open source?
Command A (03-2025) is not open source; the seed data lists it as proprietary.