Nextbit API pricing
11 Nextbit models. Source: https://www.nextbit256.com/en/models
- Provider type
- Inference host
- Server location (where inference runs)
- Spain (EU)
- Regions
- Spain (EU)
- Company HQ (secondary)
- Spain (EU)
- EU data residency
- some models / regions (see each model)
- Residency notes
- Serverless runs on Nextbit's own infrastructure in Spain (region eu-south, Where-we-deploy page). The EU-only endpoint eu.api.nextbit256.com serves only the models marked 'EU' (6 of 11); models marked 'Multi' on the global endpoint run from the EU by default but may run outside it. NEXTBIT 256, S.L., Valencia, Spain ('No US parent'). Prices published in USD; usage is deducted from a EUR balance at the ECB reference rate.
- Residency source
- https://www.nextbit256.com/en/models
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 |
|---|---|---|---|---|---|---|---|
| Nextbit Inference host | gemma3:12b-it | $0.05 | $0.15 | — | $0.075 | 131K | yes |
| Nextbit Inference host | Qwen3 14B | $0.10 | $0.22 | — | $0.13 | 41K | yes |
| Nextbit Inference host | Gemma 4 26B A4B | $0.09 | $0.30 | $0.05 | $0.143 | 262K | yes |
| Nextbit Inference host | gemma3:27b | $0.08 | $0.35 | $0.04 | $0.147 | 131K | yes |
| Nextbit Inference host | GLM 5.3 Flash | $0.12 | $0.40 | $0.04 | $0.19 | 1.048576M | partial |
| Nextbit Inference host | deepseek:v4.1-flash | $0.21 | $0.84 | $0.004 | $0.367 | 1.048576M | partial |
| Nextbit Inference host | ALIA-40B | $0.30 | $0.60 | — | $0.375 | 66K | yes |
| Nextbit Inference host | DeepSeek V4 Flash (0731) | $0.352 | $1.06 | $0.012 | $0.528 | 1.048576M | partial |
| Nextbit Inference host | Gemma 2 27B | $0.65 | $0.65 | — | $0.65 | 8K | yes |
| Nextbit Inference host | DeepSeek V4 Pro (0813) | $1.06 | $3.17 | $0.035 | $1.58 | 1.048576M | partial |
| Nextbit Inference host | DeepSeek V4 Pro | $1.74 | $3.48 | $0.145 | $2.17 | 1.048576M | partial |
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. 11 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.