CohereProprietaryReasoning
Command R+
Cohere’s Command R+ model optimized for retrieval-augmented generation, enterprise search, and multilingual business assistants.
Tool calling · Coding
Last reviewed: 24 July 2026
Overview
Cohere’s Command R+ model optimized for retrieval-augmented generation, enterprise search, and multilingual business assistants.
Capabilities
- Vision: No
- Audio: No
- Tool calling: Yes
- Thinking: No
- MCP: No
- Coding: Yes
- Structured output: Yes
Technical specifications
- Provider
- Cohere
- License
- Proprietary (API); Command R weights may differ
- Context window
- 128K
- Release
- 2024
- Modalities
- Text
- Vision
- No
- Audio
- No
- Tool calling
- Yes
- Thinking
- No
- MCP
- No
- Open weights
- No
- API
- Yes
- Pricing (input)
- Cohere API tiered
- Pricing (output)
- Cohere API tiered
Supported modalities
Text
Context window
128K (128,000 tokens)
Pricing
Input: Cohere API tiered
Output: Cohere API tiered
Availability
API: Yes
Chat UI: Yes
Open weights: No
Strong enterprise/RAG positioning; cloud marketplace availability.
Use cases
- Enterprise RAG assistants
- Multilingual business chat
- Tool-using workflow agents
- Search + generation pipelines
Strengths
- RAG-oriented training and tooling
- Enterprise deployment options
- Solid multilingual performance
Limitations
- Less of a general “frontier chat” brand vs GPT/Claude
- Weaker native vision than multimodal peers
Related guides
Related benchmarks
Related research
Related GitHub
Related tools
Related rankings
Related comparisons
Companies
Explore more models
- Mistral LargeMistralMistral’s flagship large model for enterprise reasoning, multilingual chat, and function calling via La Plateforme and cloud partners.
- Claude OpusAnthropicAnthropic’s highest-capability Claude tier for deep reasoning, long-context analysis, coding, and careful instruction following.
- Claude SonnetAnthropicAnthropic’s balanced Claude tier — strong quality at lower latency and cost than Opus, widely used for production agents and coding.
- Gemini 2.5 ProGoogleGoogle’s Pro-class Gemini model for advanced reasoning and native multimodal workloads across text, images, audio, and long context.
- GPT-5OpenAIOpenAI’s flagship general-purpose model for complex reasoning, coding, multimodal understanding, and agentic tool use.
- GrokxAIxAI’s Grok model family — real-time oriented assistants with strong coding and reasoning, available via xAI API and consumer surfaces.