Command R+ vs Command R
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Command R+ da Cohere e Command R da Cohere são dois modelos de IA de destaque. O Command R+ oferece uma janela de contexto de 128K tokens a $2.50/$10.00 por milhão de tokens, enquanto o Command R oferece 128K tokens de contexto a $0.15/$0.60 por milhão de tokens. Veja abaixo a comparação completa de benchmarks, latência e custos.
Troque e Compare Qualquer Modelo
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Command R+
Modelo Base de Pesos AbertosO Command R+ da Cohere é um modelo de IA projetado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, oferecendo janela de contexto de 128K, velocidade de 65 tokens/s, índice de inteligência de 48/100 e tarifa
$2.50 / 1M
$10.00 / 1M
128K tokens
41.5%
Command R
Modelo Base de Pesos AbertosO Command R da Cohere é um modelo de IA projetado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, oferecendo janela de contexto de 128K, velocidade de 85 tokens/s, índice de inteligência de 43/100 e tarifa
$0.15 / 1M
$0.60 / 1M
128K tokens
32%
Principais Diferenças em Resumo
- Command R is 16.5x cheaper for API usage (input + output tokens combined).
- Command R is faster at 85 tok/s vs 65 tok/s.
- Command R+ leads on SWE-bench coding (41.5% vs 32.0%).
| Feature | Command R+ | Command R |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 48 | 43 |
Provider | Cohere | Cohere |
Input Price Cost per million input tokens | $2.50 / 1M | $0.15 / 1M |
Output Price Cost per million output tokens | $10.00 / 1M | $0.60 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $2.02 / 1M | $0.13 / 1M |
Context Window Maximum input + output tokens | 128K tokens~192 A4 pages of text | 128K tokens~192 A4 pages of text |
Max Output Tokens Per single request | 8K | 4K |
Throughput Speed Tokens generated per second | 65 tok/s | 85 tok/s |
SWE-bench Verified Real-world software engineering | 41.5% | 32% |
GPQA Diamond Graduate-level reasoning | 56.5% | 46% |
Cached Input Price Prompt caching discount per 1M tokens | $0.75 / 1M | $0.05 / 1M |
Quem vence em cada categoria?
At-a-glance decision frameworkPontuações de Benchmarks Verificadas
Official evaluation metrics verified by independent third-party research labs.
Industry benchmark evaluating real-world GitHub issue resolution and multi-file debugging.
Challenging questions created by domain experts to test complex PhD-level reasoning.
Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.
Crowdsourced human preference evaluation based on blind, head-to-head model battles.
Autonomous multi-step tasks executed inside a real command-line terminal environment.
American Invitational Mathematics Examination — multi-step Olympiad-level reasoning.
Accuracy when reasoning over very large inputs that fill the model context window.
Tokens emitted per second during active generation streaming.
Latência e Tempo de Resposta
Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.
Simulador Interativo de Custo de Tokens
Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.
Command R+ · Strengths & Key Advantages
- Janela de contexto de 128K com limite máximo de saída de 8K tokens (SWE-bench Verified 41.5% · GPQA Diamond 56.5%)
- Taxa de transferência rápida de 65 tokens/segundo com latência inicial (TTFT) de 580 ms
- Pesos abertos (104B) para auto-hospedagem local ou em nuvem privada via vLLM, SGLang ou Ollama
Considerations & Trade-offs
- Requer servidores GPU com memória VRAM adequada para execução local em precisão total
- Para alto volume de requisições, recomenda-se ativar o cache de prompts e a Batch API para reduzir custos
Command R · Strengths & Key Advantages
- Janela de contexto de 128K com limite máximo de saída de 4K tokens (SWE-bench Verified 32% · GPQA Diamond 46%)
- Taxa de transferência rápida de 85 tokens/segundo com latência inicial (TTFT) de 420 ms
- Pesos abertos (35B) para auto-hospedagem local ou em nuvem privada via vLLM, SGLang ou Ollama
Considerations & Trade-offs
- Requer servidores GPU com memória VRAM adequada para execução local em precisão total
- Em derivações científicas extremas, modelos pesados dedicados exclusivamente ao raciocínio oferecem maior profundidade
Token Use & Task Economics
Estimated cost and token consumption to complete one representative agentic task.
| Metric | Command R+ | Command R |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.65 | $0.12 |
Output Tokens / Task Tokens generated per task | 35K | 25K |
Reasoning Tokens / Task Thinking tokens burned per task | 0K | 0K |
Especificações Técnicas
Architecture, release timeline, capabilities, and modalities.
| Feature | Command R+ | Command R |
|---|---|---|
| Official API Model ID (SDK) | command-r-plus | command-r |
| API Protocol | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI |
| Release Date | 2024-08 | 2024-08 |
| Knowledge Cutoff | June 2024 | June 2024 |
| Architecture | Enterprise-Grade Dense Transformer | Retrieval-Augmented Dense Transformer |
| Parameters | 104B | 35B |
| Enterprise Rate Limits (RPM / TPM) | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud |
| Long-Context Tier (>128K/200K) | Flat rate ($2.5/1M in) across full 128K window | Flat rate ($0.15/1M in) across full 128K window |
| Prompt Cache Policy & TTL | Cached input at $0.75/1M tokens | Cached input at $0.05/1M tokens |
| Computer Use / GUI Agent | API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop) | 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 | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema |
| Web Search Grounding & Sandbox | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools |
| Official Fine-Tuning Support | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) |
| Multimodal Token Billing | Text BPE (~4 chars/token) | Text BPE (~4 chars/token) |
| Quantization & Min GPU VRAM | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 64 GB VRAM (4-bit Quantized) · 224 GB VRAM (Native BF16) | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 22 GB VRAM (4-bit Quantized) · 75 GB VRAM (Native BF16) |
| Safety & Frontier Classification | Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma) | Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma) |
| Enterprise Compliance (ZDR/HIPAA/SOC2) | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control |
| Input Modalities | text | text |
| Output Modalities | text | text |
Command R+ vs Command R: Respostas Rápidas (FAQ)
Which is more intelligent, Command R+ or Command R?
Command R+ is more intelligent. It scores 48 compared with 43 on the composite Intelligence Index.
Which model is faster?
Command R is faster, generating 85 tokens per second compared with 65 tokens per second.
Which model is cheaper to run?
Command R is cheaper at $0.13 per 1M tokens blended, compared with $2.02 (7:2:1 cache:input:output ratio).
Which model has lower latency?
Command R has lower latency, with a time to first token of 0.42s compared with 0.58s.
Veredito
Tanto Command R+ (Indicado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, arquiteturas RAG corporativas e integração escalável via API.) quanto Command R (Indicado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, arquiteturas RAG corporativas e integração escalável via API.) entregam excelente desempenho: Command R+ lidera em inteligência geral e programação, Command R oferece geração mais rápida e Command R apresenta o melhor custo-benefício em produção.
Perguntas Frequentes (FAQ)
Qual é melhor para programação e raciocínio, Command R+ ou Command R?+
Nas avaliações de inteligência e código, Command R+ leva vantagem. Confira os gráficos SWE-bench e GPQA acima para detalhes.
Qual modelo tem a API mais barata, Command R+ ou Command R?+
O Command R+ custa $2.50 / $10.00 por 1M de tokens (entrada/saída) e o Command R custa $0.15 / $0.60. No custo combinado, Command R é mais econômico.
Qual modelo possui maior janela de contexto e velocidade?+
O Command R+ suporta 128K tokens de contexto contra 128K tokens do Command R, enquanto Command R entrega maior velocidade de geração.
Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.
Related reading
- Aya Expanse 8B vs. Command R+: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Command R+ vs. Jamba 1.5 Large: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Command R vs. Jamba 1.5 Mini: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aion-3.0 vs. Aion-Mini: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aion-3.0 vs. Gemini 3.6 Flash: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aion-Mini vs. Laguna XS 2.1: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
Fontes oficiais: Documentação oficial de API da Cohere e Cohere e benchmarks independentes (2026).