Command R+ vs Command R

Compare Command R+ and Command R: pricing, performance, context window, latency, and best use cases. Side-by-side comparison on XALEN.

Updated 2026-05-21 · By Abhishek Raj · Our methodology

All Cohere models All Cohere models What is an LLM API? Python Quickstart What is inference?
Feature Command R+ Command R
CategoryEnterpriseOpen Source
Parameters104B35B
Context Window128K128K
Input Price$0.06/1M tokens$0.03/1M tokens
Output Price$0.10/1M tokens$0.06/1M tokens
Latency~400ms~250ms

Choose Command R+ when:

  • ✓ Temple knowledge bases
  • ✓ Scriptural Q&A
  • ✓ Enterprise
Key Strengths:

Built-in RAG, Citation generation, Document grounding

Choose Command R when:

  • ✓ RAG applications
  • ✓ Q&A systems
  • ✓ Content generation
Key Strengths:

Good RAG, Cost-efficient, 128K context

Verdict: Command R+ vs Command R

For cost efficiency, Command R wins at $0.03/1M input tokens. For speed, Command R is faster at ~250ms. Command R+ excels at Temple knowledge bases while Command R is better for RAG applications. Both are available on XALEN through a single API — try them in the Playground to see which fits your workload.

Detailed Analysis

Pricing Comparison

Command R+ costs $0.06/1M input tokens and $0.10/1M output tokens. Command R costs $0.03 input and $0.06 output. Command R is 2.0x cheaper on input tokens. XALEN offers batch processing at 50% discount on both models.

Performance & Context

Command R+ has a 128K context window with ~400ms latency. Command R offers 128K context at ~250ms. Both have identical context windows.

Best For

Command R+ (Enterprise) is optimized for: Temple knowledge bases, Scriptural Q&A, Enterprise. Command R (Open Source) works best for: RAG applications, Q&A systems, Content generation.

Try Both on XALEN

Both models are available through XALEN's OpenAI-compatible API. Switch between them by changing the model parameter:

from xalen import XALEN

client = XALEN(api_key="xln_test_YOUR_KEY")

# Use Command R+
response_a = client.chat.completions.create(
    model="command-r-plus",
    messages=[{"role": "user", "content": "Your question here"}]
)

# Use Command R
response_b = client.chat.completions.create(
    model="command-r",
    messages=[{"role": "user", "content": "Your question here"}]
)

Start Building with XALEN

200+ AI models. One API. Pay-as-you-go.

Get API Key Try in Playground

Frequently Asked Questions

Which is better, Command R+ or Command R?

Command R+ (Enterprise, 104B) offers Built-in RAG. Command R (Open Source, 35B) offers Good RAG. Choose Command R+ for Temple knowledge bases or Command R for RAG applications.

How much does Command R+ cost vs Command R?

Command R+: $0.06/1M input, $0.10/1M output. Command R: $0.03/1M input, $0.06/1M output. Both available on XALEN with batch processing at 50% discount.

Can I use both models on XALEN?

Yes. XALEN provides 200+ models through a single OpenAI-compatible API. Switch between Command R+ and Command R by changing the model parameter. No code changes needed.

Related Comparisons

Command R+ vs Gemma 3 27B Command R+ vs Llama 4 Scout Command R+ vs Llama 4 Maverick Command R+ vs Llama 3.3 70B Command R+ vs Llama 3.1 405B Command R+ vs Llama 3.1 70B Turbo

Last updated: 2026-05-21. Pricing and specifications may change. Check pricing page for latest rates.