Side-by-side technical and economic comparison between Cohere's Command R (08-2024) and Meta / Together's Llama 3.1 405B — Together AI.
• Command R (08-2024): Classified as a Legacy Reference model (Tracked Production / Legacy Family).
• Llama 3.1 405B — Together AI: Classified as a Legacy Reference model (Deprecated on Together AI (Reference)).
| Metric | Command R (08-2024) | Llama 3.1 405B — Together AI | Advantage |
|---|---|---|---|
| Provider Organization | Cohere | Meta / Together | — |
| Standard Input / 1M | $0.15 | $3.50 | Command R (08-2024) (96% lower) |
| Cached Input / 1M | $0.015 | None | Command R (08-2024) lower |
| Output / 1M | $0.60 | $3.50 | Command R (08-2024) lower |
| Context Window | 128k | 128k | Llama 3.1 405B — Together AI (128k) |
| Max Generation Tokens | 4.1k | 4.1k | Command R (08-2024) |
| Tokenizer Family | Cohere BPE (~256k vocabulary) | Meta Llama 3 Tiktoken BPE (~128k 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 Llama 3.1 405B — Together AI when looking for Meta / Together's tooling integration, specific context window depth (128k tokens), or when output generation volume favors its $3.5/M rate.