Cohere Labs develops Command A Reasoning, a 111 billion parameter chat model optimized for tool use, agentic, and multilingual use cases with reasoning capabilities. It is genuinely best at tasks that require reasoning, such as chain of thought and function calling, thanks to its supervised fine-tuning and preference training.
Input
Output
Context
289K
Max Output
-
Parameters
111.1B
Input Modalities
Output Modalities
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Automatically route workloads to the right model for every task, every time.