# Run an open model as my own OpenAI-compatible server for a while (slim)

> Run an open model as my own OpenAI-compatible server for a while: 3 companies fully do it, 17 with a limit, 24 carry the tag. Every listing in GPU & serverless compute with the reason and a source.

- Full: https://www.anchorterminal.com/niches/gpu-compute.self-hosted-llm-server/index.md (~2,150 tokens) · this version ~380 tokens · JSON https://www.anchorterminal.com/niches/gpu-compute.self-hosted-llm-server/index.json · canonical https://www.anchorterminal.com/niches/gpu-compute.self-hosted-llm-server/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-15
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Two or three companies' docs show a full fit. Full fit: 3 companies, with a limit: 17, tagged: 24. Weight 14, 7 accounts.

Done when: An OpenAI-compatible /v1/chat/completions URL answers correctly after the launch call, with model weights loaded from a template or one install step, and the machine is destroyed when done.
yes: baseten (Baseten Labs, Inc.)
yes: hugging-face-inference-endpoints (Hugging Face, Inc.)
yes: koyeb (Koyeb SAS)
caveat: beam (Smartshare, Inc.)
caveat: cerebrium (Cerebrium Inc.)
caveat: cloud-run-gpus (Google LLC)
caveat: coreweave (CoreWeave, Inc.)
caveat: crusoe-cloud (Crusoe Technologies LLC)
caveat: gpusmarket (Tyga.Cloud Ltd)
caveat: hyperbolic (Hyperbolic Labs, Inc.)
caveat: lambda (Lambda, Inc.)
caveat: massed-compute (Massed Compute, Inc.)
caveat: modal (Modal Labs, Inc.)
caveat: nebius-ai-cloud (Nebius B.V.)
caveat: northflank (Northflank Ltd)
caveat: runpod (Runpod, Inc.)
caveat: thunder-compute (Thunder GPU, Inc.)
caveat: together-gpu-clusters (Together Computer, Inc.)
caveat: vast-ai (Vast.ai Inc.)
caveat: verda (DataCrunch Oy)

Data: https://www.anchorterminal.com/api/v1/use-cases/gpu-compute.self-hosted-llm-server.json
