Overview
Crusoe Cloud's Managed Inference service allows you to interact with supported models via our APIs, available on the Intelligence Foundry. Models are served on our proprietary inference engine with MemoryAlloy, a cluster-wide memory fabric with cache aware routing that maximizes cache hits, improving TTFT and throughput.
You can find more information on available models below. Pricing is listed for each model on the model cards, accessible here.
Available Models
For text generation
We provide an OpenAI-API compatible endpoint at api.crusoe.ai for the models below. All Meta models provided by Crusoe are “Built with Llama”. You may also interact with all of the models via a chat interface on the Intelligence Foundry, access via theCrusoe Cloud console.
| Name | Provider | Type | Context Length | License | Acceptable Use Policy |
|---|---|---|---|---|---|
| meta-llama/Llama-3.3-70B-Instruct (Model card¹) | Meta | instruct | 128k | Llama 3.3 Community License Agreement | Llama 3.3 Acceptable Use Policy |
| openai/gpt-oss-120b (Model card¹) | OpenAI | instruct | 128k | Apache License 2.0 | Acceptable Use Policy |
| deepseek-ai/DeepSeek-V3-0324 (Model card¹) | DeepSeek | instruct | 160k | MIT License | MIT License |
| deepseek-ai/DeepSeek-R1-0528 (Model card¹) | DeepSeek | instruct | 160k | MIT License | MIT License |
| deepseek-ai/DeepSeek-V3.1 (Model card¹) | DeepSeek | instruct | 160k | MIT License | MIT License |
| Qwen/Qwen3-235B-A22B (Model card¹) | Qwen | instruct | 131k | Apache License 2.0 | Apache License 2.0 |
| google/gemma-3-12b-it (Model card¹) | instruct | 128k | Gemma Terms of Use | Gemma Terms of Use, note use restrictions in Section 3.2 | |
| moonshotai/Kimi-K2-Thinking (Model card¹) | Moonshot AI | instruct | 131k | Moonshot Terms of Use |