Cohere: Command R+ (04-2024)

Text input Text output Unavailable
Author's Description

Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG). It offers multilingual support for ten key languages to facilitate global business operations. See benchmarks and the launch post [here](https://txt.cohere.com/command-r-plus-microsoft-azure/). Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).

Key Specifications
Cost
$$$$$
Context
128K
Parameters
104B
Released
Apr 01, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Structured Outputs Response Format Stop Seed Top P Max Tokens Frequency Penalty Temperature Presence Penalty
Features

This model supports the following features:

Tools Response Format Structured Outputs
Performance Summary

Cohere's Command R+ (04-2024) model, released on April 1, 2024, demonstrates a strong overall performance profile, particularly in reliability and speed. It performs among the fastest models, ranking in the 64th percentile for speed across seven benchmarks. Its pricing is moderate, placing it in the 21st percentile. Notably, Command R+ exhibits exceptional reliability, achieving a 100% success rate across all benchmarks, indicating consistent and usable responses without technical failures. In terms of specific capabilities, the model excels in minimizing hallucinations, achieving 98.0% accuracy in identifying fictional concepts, and performs well in Email Classification (98.0% accuracy). It also shows strong performance in Ethics (97.0% accuracy). However, its performance in General Knowledge (92.5% accuracy) is average, and it struggles with more complex tasks such as Instruction Following (43.0% accuracy) and Reasoning (28.0% accuracy), where it ranks in the lower percentiles. Coding performance is also moderate at 74.0% accuracy. Command R+ is well-suited for applications requiring high reliability and speed, especially in areas like RAG and general consumer use cases, but may require further refinement for highly complex reasoning or multi-step instruction following.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $3
Completion $15

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Cohere
Cohere | cohere/command-r-plus-04-2024 128K $3 / 1M tokens $15 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by cohere