Kilo Gateway
Launch of fine-tuning for Command R 08-2024 and other new fine-tuning features.
Model details
Command R is a generative large language model built by Cohere and positioned in the scalable category, balancing high performance with accuracy so teams can move past proof-of-concept work into sustained production deployments. The August 2024 update refined both Command R and Command R+ for tool-driven workflows and long-context reasoning, with the release tagged command-r-08-2024 to mark the refresh point. Cohere designed the model to excel across varied tasks such as question answering, summarization, and reasoning, and to carry that capability into demanding enterprise pipelines rather than narrow demonstrations.
The model's practical strengths sit in retrieval augmented generation and tool use, where it is tuned for high precision and paired with a 128,000-token context window and multilingual coverage spanning ten key languages. Through the Cohere chat endpoints, it supports structured outputs and citation-aware responses, which makes it a natural fit for assistants, knowledge agents, and search grounded applications that need reliable grounding over large documents. Cohere also opened fine-tuning for this generation, giving organizations a path to specialize the model on their own data, while the open weights let teams self-host and adapt the system to their infrastructure.
Transparent token rates
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
Kilo Gateway
Launch of fine-tuning for Command R 08-2024 and other new fine-tuning features.
Kilo Gateway
A generative language model optimized for long context tasks and large scale production workloads Command R 08 2024 is an updated highly performant generative large language model. It is designed to excel across a variety of use cases including reasoning, summarization, and question answering, with increased performanc
This exact model name is also listed by 4 other providers.