qwen-bg
max-ico04
128K
In
Out
max-ico02
Chat
max-ico03
disable
Command R+
Explore Cohere's Command R+ API, a high-performance LLM designed for enterprise use with advanced features like multilingual support and tool integration.
Free $1 Tokens for New Members
Text to Speech
                                        const { OpenAI } = require('openai');

const api = new OpenAI({
  baseURL: 'https://api.ai.cc/v1',
  apiKey: '',
});

const main = async () => {
  const result = await api.chat.completions.create({
    model: 'cohere/command-r-plus',
    messages: [
      {
        role: 'system',
        content: 'You are an AI assistant who knows everything.',
      },
      {
        role: 'user',
        content: 'Tell me, why is the sky blue?'
      }
    ],
  });

  const message = result.choices[0].message.content;
  console.log(`Assistant: ${message}`);
};

main();
                                
                                        import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.ai.cc/v1",
    api_key="",    
)

response = client.chat.completions.create(
    model="cohere/command-r-plus",
    messages=[
        {
            "role": "system",
            "content": "You are an AI assistant who knows everything.",
        },
        {
            "role": "user",
            "content": "Tell me, why is the sky blue?"
        },
    ],
)

message = response.choices[0].message.content

print(f"Assistant: {message}")
Docs

One API 300+ AI Models

Save 20% on Costs & $1 Free Tokens
  • ico01-1
    AI Playground

    Test all API models in the sandbox environment before you integrate.

    We provide more than 300 models to integrate into your app.

    copy-img02img01
qwenmax-bg
img
Command R+

Product Detail

🤖 Command R+ Overview: A Powerful LLM for Enterprise AI

Unveiled by Cohere on April 8, 2024, Command R+ represents a significant leap in large language models (LLMs) tailored specifically for enterprise solutions. This cutting-edge model, with its robust architecture, is designed to elevate efficiency and precision across complex business operations, leveraging advanced capabilities like Retrieval-Augmented Generation (RAG) and sophisticated multi-step tool use.

💻 Key Capabilities & Features

  • 🔥 Parameter Count: Built with an impressive 104 billion parameters, enabling high performance and nuanced understanding for complex tasks.
  • 📜 Extensive Context Window: Boasts an exceptional context length of 128,000 tokens, allowing for deeper context retention and more coherent, extended interactions.
  • 🌐 Multilingual Proficiency: Optimized for superior performance in ten key languages (English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Arabic, and Simplified Chinese), with training data spanning thirteen additional languages.
  • 🔍 Grounded Generation: Delivers accurate and verifiable responses by generating content based on external document snippets, complete with integrated citations.
  • 🔧 Advanced Tool Use: Supports both single and multi-step tool use, enabling seamless interaction with external APIs and databases for sophisticated automation.

🏪 Ideal Enterprise Applications

Command R+ is meticulously crafted for challenging enterprise environments. Its capabilities make it exceptionally effective across sectors such as customer support, finance, human resources, and marketing. It particularly shines in scenarios demanding intricate reasoning and extensive automation, streamlining operations and enhancing decision-making.

📈 Technical Specifications & Performance

Architecture & Training:

Utilizing an optimized auto-regressive transformer architecture, Command R+ undergoes supervised fine-tuning (SFT) and preference training. This rigorous process aligns its outputs with human preferences for both helpfulness and safety. It was trained on a diverse, multi-domain dataset, with knowledge current as of August 2024.

Cohere prioritizes bias mitigation through this diverse data strategy, with ongoing evaluation to ensure fairness in real-world deployments.

Performance Benchmarks:

  • ✓ MMLU Accuracy: Achieved an impressive 75% on the MMLU benchmark.
  • ⏱ Processing Speed: Outputs approximately 66.5 tokens per second.
  • ⏰ Average Latency: Responds swiftly with an average latency of around 0.30 seconds (time to first token).
  • 🚀 Throughput Enhancement: Delivers approximately 50% higher throughput compared to its predecessor, maintaining similar hardware demands.

📊 Command R+ vs. Leading LLMs

Command R+ performance comparison with other leading LLMs

Command R+ demonstrates robust competitive performance, striking an excellent balance between capability and cost-effectiveness. In multilingual translation, it achieves a BLEU score of 35.9, nearly matching GPT-4 Turbo (36.6) and significantly outperforming Mistral-Large (31.4). For Retrieval-Augmented Generation (RAG) tasks, Command R+ scores 71.5% accuracy, surpassing Mistral-Large (60.7%) and closely trailing GPT-4 Turbo (76.7%). Furthermore, its tool usage success rate stands at 74.5%, exceeding Mistral-Large’s 63.1% and nearing GPT-4 Turbo’s 73.7%.

🔗 Integration & Ethical AI

API Access & Documentation:

Command R+ is readily available on the AI/ML API platform under the identifier "cohere/command-r-plus."
For developers, comprehensive API Documentation is accessible to facilitate seamless integration and utilization.

Get Command R+ API Access Here

Ethical AI & Licensing:

Cohere places strong emphasis on data privacy and security. Ethical considerations are paramount, with continuous efforts to ensure the model does not propagate biases from its training data. Commercial usage rights are granted via Cohere’s API services.

💬 Frequently Asked Questions (FAQ)

Q: What is Command R+ primarily used for?

A: Command R+ is designed for advanced enterprise applications, particularly effective in areas requiring sophisticated reasoning, Retrieval-Augmented Generation (RAG), and multi-step tool use, such as customer support, finance, and HR.

Q: What is the context length of Command R+?

A: The model supports an impressive context length of 128,000 tokens, allowing it to process and understand very long inputs and generate detailed, context-aware responses.

Q: How many languages does Command R+ support?

A: Command R+ is optimized for performance in ten primary languages (English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Arabic, and Simplified Chinese) and has incorporated training data from thirteen additional languages.

Q: What is "Grounded Generation"?

A: Grounded Generation refers to Command R+'s ability to produce responses based on external document snippets, providing verifiable information with integrated citations to enhance accuracy and trustworthiness.

Q: Is Command R+ suitable for commercial use?

A: Yes, commercial usage rights for Command R+ are available through Cohere’s API services, making it a viable solution for businesses looking to integrate advanced LLM capabilities.

Learn how you can transformyour company with AICC APIs

Discover how to revolutionize your business with AICC API! Unlock powerfultools to automate processes, enhance decision-making, and personalize customer experiences.
Contact sales
api-right-1
model-bg02-1

One API
300+ AI Models

Save 20% on Costs