MiniMax M2.5 API pricing
MiniMax M2.5 by Melious costs €0.30 per 1M input tokens and €1.20 per 1M output tokens (1M in + 1M out = €1.50).
- API model id
MiniMax M2.5- Input / 1M
- €0.30
- Output / 1M
- €1.20
- Cached input / 1M
- €0.08
- Context window
- —
- Notes
- Melious pay-as-you-go (EU), EUR per 1M tokens, not converted. Only the top-10 models on the pricing page show prices in the page HTML.
- Source
- https://melious.ai/pricing
- Provider type
- Inference host (HQ: Germany)
- Regions
- Europe
- EU data residency
- yes — '60+ open models, served from European data centres'; About page: infrastructure 'European only', data stays under European jurisdiction, never retained or used for training. Melious AI GmbH, Saarbrücken, Germany. Prices published in EUR (the page says its coding subscriptions are B2B, plus VAT).
- Currency
- EUR (as published, not converted)
- Last verified
- 2026-10-16
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Melious | MiniMax M2.5 | €0.60 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other Melious models
- DeepSeek V4.1 Flash: €0.20 / €1.00
- DeepSeek V4 Flash 0731: €0.10 / €0.25
- GLM 5.3 Flash: €0.10 / €0.40
- GLM 5.3: €1.00 / €3.00
- Gemma 4 31B: €0.10 / €0.30
- Kimi K3: €2.80 / €14.00
- Qwen3.8 27B: €0.40 / €2.40