Crusoe API pricing
10 Crusoe models. Source: https://www.crusoe.ai/cloud/pricing
- Provider type
- Cloud
- Server location (where inference runs)
- unknown
- Regions
- unknown
- Company HQ (secondary)
- US (outside EU) · Crusoe, Inc. (site footer); HQ country US per OpenRouter's provider list.
- EU data residency
- unknown
- Residency notes
- Serverless Inference docs and pricing page do not say which region serves requests. Crusoe Cloud data centers (docs locations page): Houston TX, Ohio, Sparks NV, Virginia (US); Iceland x2 and Norway (eu-iceland1-a, eu-iceland2-a, eu-norway1-a).
- Residency source
- https://docs.crusoecloud.com/locations
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 |
|---|---|---|---|---|---|---|---|
| Crusoe Cloud | Nemotron 3.5 Lightning | $0.05 | $0.20 | $0.03 | $0.0875 | — | unknown |
| Crusoe Cloud | GPT-OSS 120B | $0.05 | $0.25 | $0.05 | $0.10 | — | unknown |
| Crusoe Cloud | DeepSeek V4 Flash | $0.14 | $0.28 | $0.03 | $0.175 | — | unknown |
| Crusoe Cloud | Nemotron 3.5 Super VL | $0.10 | $0.40 | $0.08 | $0.175 | — | unknown |
| Crusoe Cloud | Gemma 4 31B-it | $0.14 | $0.40 | $0.14 | $0.205 | — | unknown |
| Crusoe Cloud | GLM 5.3 Flash | $0.15 | $0.50 | $0.03 | $0.237 | — | unknown |
| Crusoe Cloud | DeepSeek V4.1 Flash | $0.29 | $1.20 | $0.007 | $0.517 | — | unknown |
| Crusoe Cloud | Nemotron 3 Super 120B-A12B-FP8 | $0.30 | $2.40 | $0.15 | $0.825 | — | unknown |
| Crusoe Cloud | GLM 5.3 | $1.40 | $4.40 | $0.26 | $2.15 | — | unknown |
| Crusoe Cloud | DeepSeek V4 Pro | $1.74 | $3.48 | $0.15 | $2.17 | — | unknown |
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. 10 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.