Berget AI API pricing
5 Berget AI models. Source: https://api.berget.ai/v1/models
- Provider type
- Inference host
- Headquarters
- Sweden (EU)
- Regions
- Sweden
- EU data residency
- yes
- Residency notes
- Open models on Berget's own hardware in Sweden, under Swedish jurisdiction, zero data retention ('Your data stays in Europe'). Prices published in EUR via the public models API.
- Residency source
- https://berget.ai/
HQ country is from public company information; regions and EU residency are only filled from the cited source page, otherwise 'unknown'.
Blend input:output
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Berget AI Inference host | Mistral-Small-3.2-24B-Instruct-2506 | €0.30 | €0.30 | — | €0.30 | — | yes |
| Berget AI Inference host | GLM-5.3-Flash | €0.25 | €0.50 | — | €0.313 | — | yes |
| Berget AI Inference host | gemma-4-31B-it | €0.25 | €0.50 | — | €0.313 | — | yes |
| Berget AI Inference host | Qwen3.8-27B-FP8 | €0.40 | €3.00 | — | €1.05 | — | yes |
| Berget AI Inference host | Kimi-K3 | €3.00 | €15.00 | — | €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.