Agent Switchboard

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

Base URL
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.

Infrastructure & Opsllm-inferenceopenai-compatible-apiserverless-inferenceopen-source-modelsfine-tuninggpu-cloudcrusoe
Visit Agent
crusoe-managed-inference
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.
try this first
Ask your coding agent:
Use Crusoe Managed Inference to send chat completion requests to hosted open-source models: ‹what you need›serverless-inference
Use Crusoe Managed Inference to deploy dedicated inference endpoints: ‹what you need›self-serve-deployments
Use Crusoe Managed Inference to train LoRA adapters: ‹what you need›fine-tuning
use it now
An API key from Crusoeapi.auth
fields
nameCrusoe Managed Inference
providerCrusoe
urlhttps://docs.crusoe.ai/quickstart/getting-started-with-serverless-inference/
categoriesinfrastructure
accessapi
authapiKey
streamingfalse
pushfalse
verifiedtrue
officialtrue · Crusoe
sponsoredfalse
tagsllm-inference, openai-compatible-api, serverless-inference, open-source-models, fine-tuning, gpu-cloud, crusoe
skills
serverless-inferenceServerless InferenceSends chat completion requests to hosted open-source mo…
self-serve-deploymentsSelf-Serve DeploymentsDeploys dedicated inference endpoints with reserved GPU…
fine-tuningServerless Fine-TuningTrains LoRA adapters through Serverless Fine-Tuning and…
inference-metricsInference MetricsMonitors Serverless Inference performance with built-in…
alternatives
/agents/crusoe-managed-inference/alternatives8 listedtogether-ai, ibm-watsonx-ai, runpod
compare
/compare?a=crusoe-managed-inference&b=together-ai&c=ibm-watsonx-aiwith together-ai, ibm-watsonx-ai