MiniMax M3
MiniMax M3 by MiniMax: 11 offers. From €0.27 per 1M input tokens, with EU processing from €0.36.
Calculate costs for this modelCompare offersView price history
Profile
| Profile | |
|---|---|
| Developer | MiniMax |
| Type | Language models |
| Origin | CN |
| Input types | text |
| Context (tokens) | 1,048,576 |
| Max. output (tokens) | 512,000 |
| Reasoning | ohne |
| Parameters (bn) | 427.04 |
| Open weights | ✓ yes |
| Licence | eigene Lizenz |
| VRAM at 4-bit (GB) | 239 (4 × RTX PRO 6000) |
| Released | 1 Jul 2026 |
Offers with processing in the EU (4)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| cortecs | AT | standard | €0.27 | €1.08 | api.cortecs.ai | 14 Oct 2026 |
| Lyceum | DE | standard | €0.36 | €1.79 | lyceum.technology | 13 Oct 2026 |
| GreenPT | NL | standard | €0.44 | €2.20 | greenpt.com | 12 Oct 2026 |
| HostYourAI | NL | standard | €0.46 | €2.30 | hostyourai.com | 14 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
Offers outside the EU (7)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| Modular (Modular Cloud) | US | standard | €0.27 | €1.07 | www.modular.com | 14 Oct 2026 |
| Nebius Token Factory | NL | standard | €0.27 | €1.07 | tokenfactory.nebius.com | 14 Oct 2026 |
| Parasail | US | standard | €0.27 | €1.07 | www.parasail.io | 2 Oct 2026 |
| Parasail | US | serverless | €0.27 | €1.07 | www.parasail.io | 2 Oct 2026 |
| SiliconFlow | SG | standard | €0.27 | €1.07 | www.siliconflow.com | 2 Oct 2026 |
| SambaNova (SambaCloud) | US | standard | €0.54 | €2.15 | api.sambanova.ai | 12 Oct 2026 |
| Infercom | DE | standard | €0.60 | €2.40 | infercom.ai | 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) | 92.9 |
| Humanity's Last Exam (Artificial Analysis) | 39 |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 71.1 |
| LiveBench (Aufgabensatz 2026-01-08) | 67.26 |
| MMMU-Pro (llm-stats-Abzug, Rang 1..50 von 69) | 0.78 |