Crusoe Managed Inference API

name: Crusoe Managed Inference API
description: OpenAI-compatible inference API from the Crusoe Intelligence Foundry. Send chat/completions
  and embeddings requests to Crusoe-hosted open models (DeepSeek, Llama, Gemma, GLM, Kimi, Nemotron and
  others) without managing GPU infrastructure, or run reserved-capacity self-serve deployments and LoRA-based
  serverless fine-tuning jobs. Authenticated with an Inference API key issued from the Crusoe Cloud console.
  The endpoint requires credentials for every request, including discovery paths, so no anonymous machine-readable
  contract is published for it.
humanURL: https://docs.crusoecloud.com/serverless-inference/overview
baseURL: https://api.inference.crusoecloud.com/v1
tags:
- inference
- machine-learning
- openai-compatible
- fine-tuning
properties:
- type: Documentation
  url: https://docs.crusoecloud.com/serverless-inference/overview
- type: GettingStarted
  url: https://docs.crusoecloud.com/quickstart/getting-started-with-serverless-inference
- type: Pricing
  url: https://www.crusoe.ai/cloud/pricing
- type: Authentication
  url: authentication/crusoe-authentication.yml