Side-by-side technical and economic comparison between OpenAI's OpenAI o4-mini and Cohere's Command R+ (08-2024).
• Command R+ (08-2024): Classified as a Legacy Reference model (Tracked Legacy (Predecessor to Command A)).
| Metric | OpenAI o4-mini | Command R+ (08-2024) | Advantage |
|---|---|---|---|
| Provider Organization | OpenAI | Cohere | — |
| Standard Input / 1M | $1.10 | $2.50 | OpenAI o4-mini (56% lower) |
| Cached Input / 1M | $0.275 | $0.25 | Command R+ (08-2024) lower |
| Output / 1M | $4.40 | $10.00 | OpenAI o4-mini lower |
| Context Window | 200k | 128k | OpenAI o4-mini (200k) |
| Max Generation Tokens | 64k | 4.1k | OpenAI o4-mini |
| Tokenizer Family | OpenAI o200k_base (200k vocabulary) | Cohere BPE (~256k vocabulary) | — |
Opt for OpenAI o4-mini when your engineering requirements prioritize OpenAI's ecosystem, specific tokenizer efficiencies (Exact BPE (o200k_base)), or when your expected prompt-to-completion ratios favor its $1.1/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 $10/M rate.