Side-by-side technical and economic comparison between Mistral AI's Mistral Large 3 and Mistral AI's Codestral (Current Generation).
| Metric | Mistral Large 3 | Codestral (Current Generation) | Advantage |
|---|---|---|---|
| Provider Organization | Mistral AI | Mistral AI | — |
| Standard Input / 1M | $0.50 | $0.30 | Codestral (Current Generation) (40% lower) |
| Cached Input / 1M | $0.05 | $0.03 | Codestral (Current Generation) lower |
| Output / 1M | $1.50 | $0.90 | Codestral (Current Generation) lower |
| Context Window | 256k | 256k | Mistral Large 3 (256k) |
| Max Generation Tokens | 16.4k | 8.2k | Mistral Large 3 |
| Tokenizer Family | Mistral Tekken Tokenizer (131k vocabulary) | Mistral Tekken BPE (~131k vocabulary) | — |
Opt for Mistral Large 3 when your engineering requirements prioritize Mistral AI's ecosystem, specific tokenizer efficiencies (Calibrated Mistral Tokenizer (±3%)), or when your expected prompt-to-completion ratios favor its $0.5/M input rate.
Opt for Codestral (Current Generation) when looking for Mistral AI's tooling integration, specific context window depth (256k tokens), or when output generation volume favors its $0.9/M rate.