# vLLM

**Canonical:** https://apis.io/providers/vllm/  
**Website:** https://docs.vllm.ai/  
**APIs profiled:** 7

vLLM is a high-throughput, memory-efficient open-source inference and serving engine for LLMs. It provides an OpenAI-compatible REST server (vllm serve) plus a Python API. vLLM is Apache 2.0 and run on your own GPU infrastructure; there is no hosted vLLM SaaS from the project itself.

## Kin Score — 27.0 / 100 (thin)

Scored 2026-08-25 under rubric 0.14.0. Trend: flat (+0.0 from 27.0).

| Facet | Score |
|---|---|
| Discoverability | 72.2 |
| Contract Quality | 46.9 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 5.3 |
| Developer Ergonomics | 23.8 |
| Commercial Clarity | 13.2 |
| Access Clarity | 13.2 |

## Agent readiness — 19.8 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | bearer |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | documented |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: high).

## APIs (7)

- **vLLM OpenAI-Compatible Server** — OpenAI-compatible REST API exposed by `vllm serve`. Endpoints include /v1/chat/completions, /v1/completions, /v1/embeddings, /v1/score, /v1/audio/transcriptions, /v1/audio/trans...
- **vLLM Audio API** — OpenAI-compatible audio endpoints
- **vLLM Chat API** — OpenAI-compatible chat completions
- **vLLM Completions API** — OpenAI-compatible text completions
- **vLLM Embeddings API** — OpenAI-compatible embeddings
- **vLLM Scoring API** — vLLM-specific scoring and reranking endpoints
- **vLLM Tokenize API** — vLLM-specific tokenize/detokenize utilities

## Agentic access (1)

- **Vllm Agentic Access** — 12 operations · 12 acting

## Security (2)

- **Vllm Authentication** — http · 1 scheme
- **Vllm Domain Security** — TLSv1.3

## Plans (1)

- **Vllm Plans Pricing**

## Tags

LLM, Inference, Open-Source, GPU, OpenAI-Compatible, Self-Hosted

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/vllm/). Scores are computed from the provider's own public artifacts under a published rubric.