Crusoe Managed Inference
by Crusoe
Official listing: built and published by Crusoe. More from Crusoe
Run open-source and fine-tuned models through Crusoe Cloud's OpenAI-compatible inference API, on serverless per-token endpoints or dedicated self-serve deployments.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Serverless Inference
Use Crusoe Managed Inference to send chat completion requests to hosted open-source models: ‹what you need›
- Self-Serve Deployments
Use Crusoe Managed Inference to deploy dedicated inference endpoints: ‹what you need›
- Serverless Fine-Tuning
Use Crusoe Managed Inference to train LoRA adapters: ‹what you need›
Call the API
https://api.inference.crusoecloud.com/v1
Auth An API key from Crusoe
Setup guide: docs.crusoe.ai/quickstart/getting-started-with-serverless-i…
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- API
- Auth
- API Key
- Skills
- 4
Skills
Serverless Inference
Sends chat completion requests to hosted open-source models through an OpenAI-compatible API, billed per token.
Self-Serve Deployments
Deploys dedicated inference endpoints with reserved GPUs, replica control and latency or throughput optimization profiles.
Serverless Fine-Tuning
Trains LoRA adapters through Serverless Fine-Tuning and serves them on self-serve deployments alongside base models.
Inference Metrics
Monitors Serverless Inference performance with built-in metrics and a Prometheus-compatible query API.