35-miles de millones parámetro empresarial caballo de batalla optimizado para de contexto largo búsqueda, alto-precisión RAG, y automatizado citas fundamentación.
Technical Specifications
- Provider
- Cohere
- Category
- open-source
- Release Date
- 2024-08
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- command-r
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in Cohere lineup)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($0.15/1M in) across full 128K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.05/1M tokens
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 22 GB VRAM (4-bit Quantized) · 75 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Command R Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $5.00/mo vs $20 flat plan).
Break-even point: ~667 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Command R:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 32%
- GPQA Diamond
- 46%
- MMLU-Pro
- 71%
- HumanEval
- 78.5%
- Terminal-Bench
- 28%
- AIME
- 52%
- Long-Context Reasoning
- 75%
- Chatbot Arena Elo
- 1240pts
Strengths
- estándar de la industria RAG fundamentación con precise source citas generación
- Superb precio-un-rendimiento ratio ($0.15 entrada / $0.60 salida por millones)
- 128K ventana de contexto con de pesos abiertos para privado corporativo alojamiento propio
Limitations & Trade-offs
- menor rendimiento en complejo competitivo codificación que especializado code modelos
- texto-solo sin nativo multimodal visión soporte
Editorial Assessment
el gold estándar en producción-ready recuperación-augmented generación un bajo costo.
Best for: empresarial RAG búsqueda, documento question answering, y cliente soporte con citations
Compare Command R
Frequently Asked Questions about Command R
How much does the Command R API cost per 1M tokens?+
Command R by Cohere is priced at $0.15 per 1M input tokens and $0.6 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.05 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Command R pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Command R's context window?+
Command R features a 128K tokens context window, which equals approximately 96,000 English words or ~256 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 4,096 tokens.
Can I run Command R locally on my own GPU (Open Weights)?+
Yes, Command R (35B) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Cohere train on data sent to the Command R API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Command R perform on coding and reasoning benchmarks?+
Command R achieves a composite Intelligence Index of 43/100, scoring 32% on SWE-bench Verified, 46% on GPQA Diamond, 71% on MMLU-Pro, and 1240 pts on Chatbot Arena Elo.
What is Command R best used for?+
Command R is best suited for: empresarial RAG búsqueda, documento question answering, y cliente soporte con citations. Assessment: el gold estándar en producción-ready recuperación-augmented generación un bajo costo.
Cohere Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Cohere's flagship reasoning tier:
North Mini Code
Command A Plus
Command A Reasoning
Command A Translate
Command A Vision
Command A
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Command R:
La unidad básica de texto que procesa un modelo de lenguaje, que normalmente equivale a 3 o 4 caracteres o aproximadamente 0,75 palabras. Por ejemplo, una frase típica se divide en varios tokens.
Un conjunto estandarizado de pruebas para evaluar y comparar objetivamente las capacidades de distintos modelos de IA en tareas como programación (SWE-bench) o matemáticas avanzadas (AIME).
La cantidad máxima de tokens que un modelo puede considerar a la vez, incluyendo tanto la entrada que lee como la salida que genera. Una ventana de 1.000.000 de tokens puede procesar unas 750.000 palabras en una sola petición.
La capacidad de un modelo de detectar la necesidad de una función externa y emitir argumentos JSON estructurados para ejecutar API, búsquedas web o consultas a bases de datos.
Un protocolo abierto desarrollado por Anthropic que permite a los agentes de IA conectarse de forma estandarizada a sistemas de archivos locales, entornos de desarrollo y servicios externos.
Una optimización donde los proveedores almacenan estados de atención previos para prefijos de prompts frecuentes, reduciendo el coste de entrada hasta en un 90% y acelerando la respuesta.
Las puntuaciones de benchmarks, precios por token y límites de tasa evolucionan rápidamente. Verifique siempre las especificaciones actuales en la documentación oficial del proveedor.