Melious Models
Saarbrücken-based European inference platform (Melious AI GmbH) running open-weight models on EU infrastructure partners in Finland and Ireland. Processing stays within the EU/EEA under its DPA; only operational metadata is logged, and prompts and outputs are not stored or used for training. Requesty routes to 4 Melious models starting at $0.12 per 1M input tokens with context windows up to 1M tokens. One API key and an OpenAI-compatible SDK. Provider rates plus 5% on pay as you go, or 0% with your own keys.
Flagship model
deepseek-v4.1-flashIntelligence Index
39.5
All Melious models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
| 1M | 384K | $0.23 | $1.14 | 👁🧠🔧⚡ | N/A | |
| 1M | 131K | $0.12 | $0.46 | 👁🧠🔧⚡ | 72 | |
| 1M | 131K | $1.14 | $3.42 | 🧠🔧⚡ | 75 | |
| 1M | 384K | $0.12 | $0.29 | 🧠🔧⚡ | 69 |
About Melious on Requesty
How many Melious models are available through Requesty?
Requesty routes to 4 Melious models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Melious model?
The cheapest Melious model starts at $0.12 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Melious pricing?
No. Requesty passes through exactly what Melious charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 600+ models.
Is my data used to train Melious models?
Melious's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Melious models hosted?
Melious models are hosted in 🇪🇺 EU (Germany, Finland, Ireland). Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Melious rows in the models explorer.