Side-by-side technical and economic comparison between Cohere's Command R (08-2024) and Cohere's Command A.
• Command R (08-2024): Classified as a Legacy Reference model (Tracked Production / Legacy Family).
| Metric | Command R (08-2024) | Command A | Advantage |
|---|---|---|---|
| Provider Organization | Cohere | Cohere | — |
| Standard Input / 1M | $0.15 | $2.00 | Command R (08-2024) (93% lower) |
| Cached Input / 1M | $0.015 | $0.20 | Command R (08-2024) lower |
| Output / 1M | $0.60 | $8.00 | Command R (08-2024) lower |
| Context Window | 128k | 256k | Command A (256k) |
| Max Generation Tokens | 4.1k | 64k | Command A |
| Tokenizer Family | Cohere BPE (~256k vocabulary) | Cohere Byte-Pair Encoding (256k vocabulary) | — |
Opt for Command R (08-2024) when your engineering requirements prioritize Cohere's ecosystem, specific tokenizer efficiencies (Calibrated Cohere Tokenizer (±3%)), or when your expected prompt-to-completion ratios favor its $0.15/M input rate.
Opt for Command A when looking for Cohere's tooling integration, specific context window depth (256k tokens), or when output generation volume favors its $8/M rate.