Side-by-side technical and economic comparison between Mistral AI's Mistral Small 4 and xAI's Grok 2.
• Grok 2: Classified as a Legacy Reference model (Generally Available).
| Metric | Mistral Small 4 | Grok 2 | Advantage |
|---|---|---|---|
| Provider Organization | Mistral AI | xAI | — |
| Standard Input / 1M | $0.15 | $2.00 | Mistral Small 4 (93% lower) |
| Cached Input / 1M | $0.015 | None | Mistral Small 4 lower |
| Output / 1M | $0.60 | $10.00 | Mistral Small 4 lower |
| Context Window | 256k | 128k | Mistral Small 4 (256k) |
| Max Generation Tokens | 8.2k | 8.2k | Mistral Small 4 |
| Tokenizer Family | Mistral Tekken Tokenizer (131k vocabulary) | xAI Byte-level BPE (~131k vocabulary) | — |
Opt for Mistral Small 4 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 $0.15/M input rate.
Opt for Grok 2 when looking for xAI's tooling integration, specific context window depth (128k tokens), or when output generation volume favors its $10/M rate.