Mistral Small 3.2 24B
Mistral Small 3.2 24B by Mistral AI: 9 offers. From €0.067 per 1M input tokens, with EU processing from €0.15.
Calculate costs for this modelCompare offersView price history
Profile
| Profile | |
|---|---|
| Developer | Mistral AI |
| Type | Language models |
| Origin | FR |
| Input types | text+bild |
| Context (tokens) | 131,072 |
| Max. output (tokens) | 16,384 |
| Reasoning | ohne |
| Parameters (bn) | 24.01 |
| Open weights | ✓ yes |
| Licence | Apache-2.0 |
| VRAM at 4-bit (GB) | 18 (RTX PRO 4000) |
| Released | 7 Oct 2025 |
searchit Entity Extraction (24 Sept 2026): 34.9 %
Offers with processing in the EU (5)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| cortecs | AT | standard | €0.09 | €0.28 | api.cortecs.ai | 14 Oct 2026 |
| Scaleway | FR | standard | €0.15 | €0.35 | www.scaleway.com | 13 Oct 2026 |
| HostYourAI | NL | standard | €0.17 | €0.40 | hostyourai.com | 14 Oct 2026 |
| Berget AI | SE | standard | €0.30 | €0.30 | api.berget.ai | 14 Oct 2026 |
| GreenPT | NL | standard | €0.20 | €0.40 | docs.greenpt.ai | 12 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
Offers outside the EU (4)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| DeepInfra | US | standard | €0.067 | €0.18 | deepinfra.com | 14 Oct 2026 |
| Venice.ai | US | standard | €0.08 | €0.22 | docs.venice.ai | 14 Oct 2026 |
| Parasail | US | standard | €0.08 | €0.27 | www.parasail.io | 2 Oct 2026 |
| Parasail | US | serverless | €0.08 | €0.27 | www.parasail.io | 2 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
AI Act
Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. EU processing and AI Act
Benchmarks
| Benchmarks | |
|---|---|
| GPQA Diamond (Artificial Analysis) | 50.5 |
| Humanity's Last Exam (Artificial Analysis) | 4.3 |
| Berkeley Function-Calling Leaderboard V4 | 37.1 |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 30.3 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen | 21.7 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten | 48 |