NextBit: Models and Prices
EU-only inference API on bare-metal GPU clusters.
NextBit served 154B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #35 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | Gemma | 27.9% | 74B | $0.068 | $0.225 | 84 | 100.0% | 262K |
| Gemma 3 12B | Gemma | 100.0% | 2B | $0.05 | $0.15 | 69 | 96.3% | 131K |
| Gemma 3 27B | Gemma | 2.9% | 1B | $0.08 | $0.30 | 44 | 95.0% | 131K |
| Qwen3 14B | Qwen | 100.0% | 943M | $0.10 | $0.22 | 58 | 99.8% | 41K |
| Llama 3.3 Euryale 70B | Other open-weight | 100.0% | 310M | $0.65 | $0.75 | 11 | 97.0% | 131K |
| Gemma 2 27B | Gemma | 100.0% | 28M | $0.65 | $0.65 | 42 | 100.0% | 8K |
| ReMM SLERP 13B | Other open-weight | 5.9% | 5M | $0.45 | $0.65 | 24 | 100.0% | 6K |
List prices per million tokens as of October 9, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.
Company
- Website
- nextbit256.com
- Headquarters
- Zaragoza, Spain
- Compute
- Says it owns and operates its own GPU infrastructure in Spain.
Sources: Nextbit on Product Hunt.
Finance your GPUs
Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.
Prefer email? hello@amcompute.com