Sference API pricing
5 Sference models. Source: https://sference.com/
- Provider type
- Inference host
- Server location (where inference runs)
- EU
- Regions
- EU
- Company HQ (secondary)
- United Kingdom (outside EU)
- EU data residency
- yes
- Residency notes
- Home page: 'Every request runs on European GPUs' (low-latency realtime inference on European GPUs). Security page: production runs in a dedicated AWS VPC in eu-central-1 (Frankfurt). Sference is a trading name of Neural Compute Ltd, London, England (company no. 17195150). Serverless rates are published in USD at realtime priority and 'confirmed per model when your account is provisioned'.
- Residency source
- https://sference.com/security
Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.
Blend input:output
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Sference Inference host | GLM 5.3 Flash | $0.20 | $0.60 | $0.07 | $0.30 | — | yes |
| Sference Inference host | DeepSeek V4 Flash (0731) | $0.28 | $0.56 | $0.07 | $0.35 | — | yes |
| Sference Inference host | DeepSeek V4.1 Flash (1017) | $0.50 | $1.50 | $0.05 | $0.75 | — | yes |
| Sference Inference host | GLM 5.3 | $1.20 | $4.20 | $0.26 | $1.95 | — | yes |
| Sference Inference host | Kimi K3 | $3.00 | $15.00 | $0.45 | $6.00 | — | yes |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. Click a header to sort. 5 models.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.