Cohere: Command R+ (08-2024)
Cohere: Command R+ (08-2024) is a text-in, text-out model from Cohere with a 128,000-token context window and a 4,000-token output ceiling. It supports tool use, which makes it viable for agentic workflows and function-calling pipelines. It does not support reasoning modes, and structured output support is unconfirmed. No multimodal input is available. At $2.50 per million input tokens and $10.00 per million output tokens, it sits in the mid-range tier, neither budget nor premium. The practical problem for buyers is that there is no independent benchmark coverage to validate where it lands against comparable models at this price. Teams already committed to the Cohere ecosystem, or those specifically needing its tool-use capabilities, are the most reasonable candidates to shortlist it; everyone else should treat its quality profile as unproven until third-party evaluation data becomes available.
- Model ID
- cohere/command-r-plus-08-2024
- Vendor
- cohere
- Tokenizer
- Cohere
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 4,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- yes