Skip to main content
llm.info

Command R+

Cohere

Cohere's enterprise-focused flagship model with 104B parameters and 128K context window. Released April 2024, updated August 2024. Optimized for advanced RAG with industry-leading grounded generation capabilities providing in-line citations to mitigate hallucinations. Trained with specific grounding capabilities - generates responses based on supplied document snippets including citation spans indicating information source. Supports 10 key business languages (trained on 23, evaluated on 10). Powerful Tool Use API for automating complex workflows. Beats GPT-4 Turbo on enterprise benchmarks. Available on Azure, OCI, and Cohere API. Pricing: $3 per 1M input, $15 per 1M output.

Strengths

  • Industry-leading RAG with grounded generation and in-line citations
  • Mitigates hallucinations via document-grounded responses with source citations
  • 128K context window for large document processing
  • Supports 10 key business languages - multilingual enterprise ready
  • Powerful Tool Use API for complex workflow automation
  • Beats GPT-4 Turbo on enterprise-specific benchmarks
  • Available on major platforms - Azure, OCI, Cohere API

Caveats

  • Higher cost than some alternatives ($3 input vs GPT-4o $2.50)
  • Primarily optimized for RAG - may not excel at all general tasks
  • 104B size requires significant resources for self-hosting (not available)
  • 4K max output tokens lower than newer models
  • Less ecosystem maturity than OpenAI/Anthropic
Vendor
Cohere
Context Window
128,000 tokens
Max Output
4,096 tokens
License
Proprietary
Release Date
2024-04-01
Modalities
text

Capabilities

Vision
Audio
Video
Tool Use

Pricing

$3.00 per 1M input tokens, $15.00 per 1M output tokens

Reviews

Comments