Qwen3.8-27B-FP8 API pricing
Qwen3.8-27B-FP8 by Berget AI costs €0.40 per 1M input tokens and €3.00 per 1M output tokens (1M in + 1M out = €3.40).
- API model id
Qwen/Qwen3.8-27B-FP8- Input / 1M
- €0.40
- Output / 1M
- €3.00
- Cached input / 1M
- —
- Context window
- —
- Notes
- Listed as preview.
- Source
- https://api.berget.ai/v1/models
- Provider type
- Inference host (HQ: Sweden)
- Regions
- Sweden
- EU data residency
- yes — 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.
- Currency
- EUR (as published, not converted)
- Last verified
- 2026-10-15
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Berget AI | Qwen3.8-27B-FP8 | €1.15 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other Berget AI models
- Kimi-K3: €3.00 / €15.00
- GLM-5.3-Flash: €0.25 / €0.50
- gemma-4-31B-it: €0.25 / €0.50
- Mistral-Small-3.2-24B-Instruct-2506: €0.30 / €0.30