Command R
LLM Provider / Model ยท Cost-effective enterprise RAG, multilingual understanding at budget pricing
At a glance
| Input price | $1.00 |
| Output price | $2.00 |
| Price tier | Budget |
| Context window | 128K |
| Max output | 4K |
| Context tier | 32K-128K |
| Speed tier | Fast |
| Latency | fast |
| Knowledge cutoff | Mar 2024 |
| Modality | Text-only |
| Model ID | command-r |
| Provider | Cohere |
| HumanEval | 76% |
| MMLU | 72% |
| SWE-Bench | 22% |
| Benchmark | RAG-focused: budget |
| Released | Mar 2024 |
| Hosting | Closed/API |
| Capabilities | Tool use, Streaming, Structured output, RAG-optimized, Multilingual |
What Command R does
Tool use, Streaming, Structured output, RAG-optimized, Multilingual
Best for
Cost-effective enterprise RAG, multilingual understanding at budget pricing
Works well with
Agent / Orchestration
Conflicts & caveats
- Trae's built-in model menu may not include Command R โ Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
- Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Command R is not in the supported model list.
- Kiro's spec mode is tuned for Claude models โ Command R may work but spec-driven flows are best with Claude.
- Cursor's built-in model menu may not include Command R โ verify it's available in your Cursor model picker.
- OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family โ Command R is not selectable inside this integration.
- Gemini CLI is locked to Google Gemini models โ your LLM is Command R.
- Claude Code only works with Claude models โ your LLM is Command R.
- Devin uses Cognition's proprietary model internally โ your selected Command R will be ignored.
- OpenAI Codex (Cloud) runs GPT-5.1 Codex internally โ your selected Command R will be ignored.
- Jules runs Gemini models internally โ your selected Command R will be ignored.
- The Claude Code SDK is tuned for Claude models โ Command R may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
- Lovable uses a fixed internal model โ your selected Command R will be ignored.
- Replit Agent 3 uses its own model selection internally โ your selected Command R will be ignored.
Build a full stack around Command R โ Flowpicker shows compatibility warnings before you commit.
Open the stack planner โ