sference Models
EU-based inference provider serving MiniMax models on infrastructure hosted in Finland. Fully EU-hosted with zero data retention: prompts and outputs are processed transiently and not stored or trained on. Requesty routes to 1 sference model starting at $0.45 per 1M input tokens with context windows up to 1.0M tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
minimax-m3Intelligence Index
44.4
Coding Index
58.6
GPQA Diamond
92.9%
Terminal-Bench Hard
42.4%
All sference models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
minimax-m3 | 1.0M | 131K | $0.45 | $1.80 | 🧠🔧⚡ | 59 |
About sference on Requesty
How many sference models are available through Requesty?
Requesty routes to 1 sference model including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest sference model?
The cheapest sference model starts at $0.45 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on sference pricing?
No. Requesty passes through exactly what sference charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train sference models?
sference's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are sference models hosted?
sference models are hosted in 🇪🇺 EU (Finland). Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the sference rows in the models explorer.