Crusoe
11 modelsProvider docs
As of Oct 4, 2026, Crusoe lists 11 supported models in the Sovyron catalog, including GLM-5.2, Nemotron 3 Nano Omni 30B A3B Reasoning, Kimi K2.6, GLM-5.1 and Gemma 4 31B IT — glm, nemotron, kimi-k2, gemma, gpt-oss and qwen families. Its metered rates span $0.0875–$2.15 per 1M tokens on a 3:1 input:output blend, and every price in the table is Crusoe's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
11 of 11 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| GLM-5.2 | $1.4 | $4.4 | $0.26 | 1.0M | Jun 13, 2026 |
| Nemotron 3 Nano Omni 30B A3B Reasoning | $0.3 | $1.83 | $0.3 | 256k | Apr 28, 2026 |
| Kimi K2.6 | $0.7 | $3.5 | $0.35 | 262k | Apr 21, 2026 |
| GLM-5.1 | $1.2 | $4.4 | $0.25 | 200k | Apr 7, 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 | $0.2 | $0.05 | 131k | Aug 5, 2025 |
| Qwen3 235B A22B Instruct 2507 | $0.22 | $0.8 | $0.11 | 262k | Jul 21, 2025 |
| DeepSeek V3 0324 | $0.5 | $1.5 | $0.25 | 164k | Mar 24, 2025 |
| Llama-3.3-70B-Instruct | $0.25 | $0.75 | $0.13 | 128k | Dec 6, 2024 |