Side-by-side technical and economic comparison between Google's Gemini 3.1 Pro Preview and Cohere's Command A.
| Metric | Gemini 3.1 Pro Preview | Command A | Advantage |
|---|---|---|---|
| Provider Organization | Cohere | — | |
| Standard Input / 1M | $2.00 | $2.00 | Identical |
| Cached Input / 1M | $0.20 | $0.20 | Command A lower |
| Output / 1M | $12.00 | $8.00 | Command A lower |
| Context Window | 1.05M | 256k | Gemini 3.1 Pro Preview (1.05M) |
| Max Generation Tokens | 16.4k | 64k | Command A |
| Tokenizer Family | Google Gemini SentencePiece (256k vocabulary) | Cohere Byte-Pair Encoding (256k vocabulary) | — |
Opt for Gemini 3.1 Pro Preview when your engineering requirements prioritize Google's ecosystem, specific tokenizer efficiencies (Calibrated Gemini Tokenizer (±4%)), or when your expected prompt-to-completion ratios favor its $2/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.