Side-by-side technical and economic comparison between Mistral AI's Codestral (Current Generation) and Google's Gemini 2.5 Flash.
| Metric | Codestral (Current Generation) | Gemini 2.5 Flash | Advantage |
|---|---|---|---|
| Provider Organization | Mistral AI | — | |
| Standard Input / 1M | $0.30 | $0.30 | Identical |
| Cached Input / 1M | $0.03 | $0.03 | Gemini 2.5 Flash lower |
| Output / 1M | $0.90 | $2.50 | Codestral (Current Generation) lower |
| Context Window | 256k | 1.05M | Gemini 2.5 Flash (1.05M) |
| Max Generation Tokens | 8.2k | 8.2k | Codestral (Current Generation) |
| Tokenizer Family | Mistral Tekken BPE (~131k vocabulary) | Google Gemma SentencePiece (~256k vocabulary) | — |
Opt for Codestral (Current Generation) when your engineering requirements prioritize Mistral AI's ecosystem, specific tokenizer efficiencies (Exact Tekken Tokenizer (±2%)), or when your expected prompt-to-completion ratios favor its $0.3/M input rate.
Opt for Gemini 2.5 Flash when looking for Google's tooling integration, specific context window depth (1.05M tokens), or when output generation volume favors its $2.5/M rate.