Command R+ (08-2024) by Cohere is a text-only model for conversational interaction, long-context tasks, grounded RAG, multi-step tool use, and 128K context.
Capabilities, design details, and architectural traits
Command R+ (08-2024) is Cohere’s refreshed text-generation model for conversational work, long-context tasks, grounded retrieval, and multi-step tool use. Cohere positions it for complex RAG workflows and agent-style interactions, with a 128K context window and updated August 2024 release.
| Aspect | Official Characteristic |
|---|---|
| Context | Supports a 128K context window. |
| Retrieval | Trained for grounded generation and RAG workflows with citations from supplied document snippets. |
| Tool use | Supports both single-step tool use and multi-step tool use for agent-like workflows. |
| Release update | August 2024 refresh improved tool-use decisions, instruction following, structured data analysis, and robustness to prompt formatting changes. |
| Deployment profile | Text-only input and text-only output. |
Independent evaluations · Artificial Analysis
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Cohere | Anthropic | Anthropic |
| Release Date | April 4, 2024 | July 24, 2026 | June 9, 2026 |
| Knowledge Cutoff | Mar 2024 | May 2026 | - |
| Context & Limits | |||
| Context Window | 128K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $3 Best Input Pricing | $5 | $10 |
| Output Pricing | $15 Best Output Pricing | $25 | $50 |
| Modalities | |||
| Inputs | text | textimage | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 2.6 | 63.1 Best Intelligence Index | 62.1 |
| Coding Index | - | 78.0 Best Coding Index | 76.5 |
| Agentic Index | - | 59.2 Best Agentic Index | 56.6 |
Graduate-level reasoning and expert Q&A evaluation.
Extremely difficult logical reasoning and knowledge.
Scientific coding and mathematical modeling.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
