Crusoe
5 modelsProvider docs
As of Nov 22, 2026, Crusoe lists 5 supported models in the Sovyron catalog, including Nemotron 3 Nano Omni 30B A3B Reasoning, Gemma 4 31B IT, Nemotron 3 Super 120B A12B, Nemotron 3 Nano 30B A3B and GPT OSS 120B across the nemotron-nano, gemma, nemotron-super and gpt-oss families. The cheapest rate in the table is Nemotron 3 Nano 30B A3B at $0.2 per 1M output tokens, the priciest Nemotron 3 Super 120B A12B at $2.4. On a 3:1 input:output blend the metered rates span $0.0875–$0.825 per 1M tokens, and every price is Crusoe's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
5 of 5 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| Nemotron 3 Nano Omni 30B A3B Reasoning | $0.3 | $1.83 | $0.3 | 256k | Apr 28, 2026 |
| Gemma 4 31B IT | $0.14 | $0.4 | $0.14 | 262k | Apr 2, 2026 |
| Nemotron 3 Super 120B A12B | $0.3 | $2.4 | $0.15 | 262k | Mar 11, 2026 |
| Nemotron 3 Nano 30B A3B | $0.05 | $0.2 | $0.03 | 262k | Dec 15, 2025 |
| GPT OSS 120B | $0.05 | $0.25 | $0.05 | 131k | Aug 5, 2025 |