Managed inference for open models — EEA-resident, zero data retention by default.
Sference (operated by Neural Compute Ltd, registered in England and Wales) runs a managed inference platform for open-weight models, built as its own scheduler and runtime rather than a wrapper around a hyperscaler. Inference and storage of customer content run on infrastructure within the EEA, and every model is pinned to a specific version so a silent upstream swap can't change your outputs. Zero data retention is the default rather than an upsell, there is no training on customer data, and a DPA is published rather than negotiated. On Opper it serves GLM-5.2, DeepSeek V4 Flash, Qwen 3.6 35B-A3B, Qwen3-VL 30B, and BottleCap AI's reasoning-efficient ThinkingCap. A strong pick when you want European residency for frontier open weights with always-on ZDR.
Every model we route through Sference. Compare residency, ZDR, training posture, and price at a glance — full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| EU | Zero data retention | No | 1M | $0.14 | $0.28 | |
| EU | Zero data retention | No | 262K | $0.20 | $1.25 | |
| EU | Zero data retention | No | 262K | $0.40 | $2.00 | |
| EU | Zero data retention | No | 1M | $2.25 | $11.25 | |
| EU | Zero data retention | No | 1M | $1.20 | $4.20 | |
| EU | Zero data retention | No | 262K | $0.40 | $2.60 |
Sference hosts on 1 route. Each route has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EEA; SCCs; DPA available.
