LLM Reference
Microsoft Foundry

Using Command A (03-2025) on Microsoft Foundry

Implementation guide · Command · Cohere

ServerlessOpen Weights

Microsoft Foundry exposes Command A (03-2025) through model ID cohere-command-a-03-2025. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-05-16. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Microsoft Foundry and generate an API key.
  2. 2
    Use the Microsoft Foundry SDK or REST API to call cohere-command-a-03-2025 — see the documentation for request format.
  3. 3
    You'll be billed $2.50/1M input, $10.00/1M output tokens. See full pricing.
API PortalDocumentationPricing

Code Examples

See Microsoft Foundry documentation for integration details.

Pricing on Microsoft Foundry

TypePrice (per 1M)
Input tokens$2.50
Output tokens$10.00

Capabilities

JSON / Tool use

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.

Full model details →

Model Specs

Released2025-03-01
Context256k
ArchitectureDecoder Only
Knowledge cutoff2024-06

More Models on Microsoft Foundry

Command R+ 08-2024Command R 08-2024
All models on Microsoft Foundry →

Provider

Microsoft Foundry
Microsoft Foundry

Microsoft

Redmond, Washington, United States