Side-by-side technical and economic comparison between Meta / Together's Llama 4 Scout (17B Active / 109B MoE) — Together AI and Cohere's Command R (08-2024).
• Llama 4 Scout (17B Active / 109B MoE) — Together AI: Classified as a Legacy Reference model (Deprecated on Together AI (Reference)).
• Command R (08-2024): Classified as a Legacy Reference model (Tracked Production / Legacy Family).
| Metric | Llama 4 Scout (17B Active / 109B MoE) — Together AI | Command R (08-2024) | Advantage |
|---|---|---|---|
| Provider Organization | Meta / Together | Cohere | — |
| Standard Input / 1M | $0.18 | $0.15 | Command R (08-2024) (17% lower) |
| Cached Input / 1M | None | $0.015 | Command R (08-2024) lower |
| Output / 1M | $0.59 | $0.60 | Llama 4 Scout (17B Active / 109B MoE) — Together AI lower |
| Context Window | 328k | 128k | Llama 4 Scout (17B Active / 109B MoE) — Together AI (328k) |
| Max Generation Tokens | 16.4k | 4.1k | Llama 4 Scout (17B Active / 109B MoE) — Together AI |
| Tokenizer Family | Meta Llama 3/4 Tiktoken (128k vocabulary) | Cohere BPE (~256k vocabulary) | — |
Opt for Llama 4 Scout (17B Active / 109B MoE) — Together AI when your engineering requirements prioritize Meta / Together's ecosystem, specific tokenizer efficiencies (Calibrated Llama 3 Tokenizer (±3%)), or when your expected prompt-to-completion ratios favor its $0.18/M input rate.
Opt for Command R (08-2024) when looking for Cohere's tooling integration, specific context window depth (128k tokens), or when output generation volume favors its $0.6/M rate.