Model comparison
Command R+ (04-2024) vs Claude 2.1
- Input
- $3.00
- Output
- $15.00
- Context
- 128K
- Released
- 2024-04-04
- Input
- $8.00
- Output
- $24.00
- Context
- 200K tokens
- Released
- 2023-11-21
Claude 2.1 scores higher on 3 of the 3 benchmarks both models report; Command R+ (04-2024) is cheaper on input tokens ($3 vs $8 per 1M, 2.7×); Claude 2.1 has the larger context window (200K vs 128K); Command R+ (04-2024) ships open weights while Claude 2.1 is API-only.
Specs and pricing side by side
| Spec | Command R+ (04-2024) | Claude 2.1 |
|---|---|---|
| Maker | Cohere | Anthropic |
| Released | 2024-04-04 | 2023-11-21 |
| Context window | 128K | 200K tokens |
| Max output | 4K tokens | ~4,000 tokens (Claude 2 was trained to… |
| Input price | $3.00 | $8.00 |
| Output price | $15.00 | $24.00 |
| Parameters | 104B (dense) | Undisclosed |
| License | Proprietary (API); open weights under CC-BY-NC on Hugging Face | Proprietary |
| Weights | Open weights | API only |
| Modalities | Text | Textsame |
| Knowledge cutoff | February 2023 | Early 2023 (training data cuts off in early… |
Benchmarks both models report
| Benchmark | Command R+ (04-2024) | Claude 2.1 |
|---|---|---|
| MMLU | 75.7% | 78.5% |
| ARC Challenge | 70.99% | 91% |
| GSM8K | 70.7% | 88% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Command R+ (04-2024) if…
- Cost matters: input tokens cost 2.7× less ($3 vs $8 per 1M).
- You want to self-host or fine-tune (open weights, Proprietary (API); open weights under CC-BY-NC on Hugging Face).
- Your use case is: enterprise retrieval-augmented generation with citations.
Pick Claude 2.1 if…
- You care about MMLU, ARC Challenge, GSM8K (it scores higher on 3 shared benchmarks).
- You need the longer context (200K vs 128K).
- Your use case is: long-document analysis: summarizing and querying lengthy manuals, contracts, and financial filings.
FAQ
Which is better, Command R+ (04-2024) or Claude 2.1?
Claude 2.1 scores higher on 3 of the 3 benchmarks both models report; Command R+ (04-2024) is cheaper on input tokens ($3 vs $8 per 1M, 2.7×); Claude 2.1 has the larger context window (200K vs 128K); Command R+ (04-2024) ships open weights while Claude 2.1 is API-only. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Command R+ (04-2024)?
Command R+ (04-2024): $3.00 input, $15.00 output. Claude 2.1: $8.00 input, $24.00 output (list API prices as published by each maker).
What are the context windows of Command R+ (04-2024) and Claude 2.1?
Command R+ (04-2024) offers 128K with up to 4K tokens output; Claude 2.1 offers 200K tokens with up to ~4,000 tokens (Claude 2 was trained to generate coherent documents up to 4,000 tokens) output.
Is Command R+ (04-2024) newer than Claude 2.1?
Command R+ (04-2024) was released 2024-04-04; Claude 2.1 was released 2023-11-21.