Skip to content
AI Atlas
ModelActivefamily · Command

command-a-03-2025

Coheredocs.cohere.com/docs/models

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.

Updated 33 min ago · first seen 11 Sept 2026

model_01M294H95084G9NE7H0PCZCJZ0

Context
256K tokens
T1 · 33 min ago

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Max output

1 claims · 1 propertiesShow all properties

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
8K tokenscurrentcurrentCohere — docs & blogT1highdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →