Cohere: Command R+ (04-2024)

Text input Text output
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:

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

This model supports the following features:

Tools Structured Outputs Response Format
Performance Summary

Cohere's Command R+ (04-2024) demonstrates a strong overall performance profile, particularly excelling in reliability and speed. The model consistently performs among the fastest models, ranking in the 73rd percentile for speed across various benchmarks. Its pricing is moderate, placing it in the 22nd percentile, indicating a competitive cost structure. A standout feature is its exceptional reliability, achieving a perfect 100th percentile, meaning it consistently provides usable responses with minimal technical failures. In terms of specific benchmark performance, Command R+ shows a mixed but generally capable profile. It achieves high accuracy in Email Classification (98.0%) and Ethics (97.0%), indicating strong performance in tasks requiring clear categorization and adherence to ethical principles. Its General Knowledge is also robust at 92.5%. However, the model exhibits notable weaknesses in Reasoning (32.3% accuracy) and Instruction Following (43.0% accuracy), suggesting areas for improvement in complex problem-solving and multi-step directive execution. Coding performance is moderate at 74.0%. While its speed is generally high, the duration for General Knowledge and Coding tasks is comparatively longer. Overall, Command R+ is a highly reliable and fast model, well-suited for classification and ethical content generation, though its reasoning and instruction following capabilities could be enhanced.

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 Free Executions Accuracy Cost Duration
Other Models by cohere