Official documentationNot tested by BlueFish
vLLM
A model-serving inference engine with an OpenAI-compatible HTTP server.
A quick glossary
Models generate and reason. Agents use tools to work on tasks. A harness manages an agent’s environment. MCP connects tools and data. Skills are reusable task guidance.
Research notes
A model-serving inference engine with an OpenAI-compatible HTTP server.
Validation
- A model-serving inference engine with an OpenAI-compatible HTTP server.
Cost
Free software; check license and compute costs
Source code is public; model licensing, hardware, electricity and hosting are separate. Total cost is not verified.
Limits & boundaries
- Do not rely on --api-key alone; some paths outside protected prefixes are not authenticated by it.
- Official documentation reviewed; this site has not run this combination or tested the device.
Original sources
- vLLM official documentation ↗
docs.vllm.ai · 2026-10-15 · Official documentation