Companies Radar
Model APIs and Serverless logo

Model APIs and Serverless

by Jarvislabs · Source: Official website

Hosted open models via an OpenAI-compatible API and serverless GPU workers.

Sign in to save or follow.

About Model APIs and Serverless

The inference side of the platform includes hosted open models billed per token, managed endpoints that Jarvislabs maintains, and serverless workers for custom models on vLLM, SGLang or Ollama that scale to zero when idle. A CLI and Python SDK manage deployments.

Features

  • OpenAI-compatible API
  • Managed endpoints
  • Serverless workers
  • Scale to zero
  • CLI and SDK

Alternatives to Model APIs and Serverless

More from Jarvislabs

  • GPU Clusters

    Instant and reserved multi-node GPU clusters on InfiniBand.

  • GPU VMs

    On-demand GPU virtual machines with root SSH access and ready-made templates.