# Ray Serve HTTP API

**Canonical:** https://apis.io/apis/ray/serve-api/  
**Provider:** Ray — https://apis.io/providers/ray/  
**Base URL:** http://127.0.0.1:8000  
**Documentation:** https://docs.ray.io/en/latest/serve/index.html

Ray Serve HTTP API is one of 5 APIs that [Ray](https://apis.io/providers/ray/) publishes on the [APIs.io](https://apis.io/) network. Tagged areas include Model Serving, Inference, and HTTP. The published artifact set on APIs.io includes API documentation.

HTTP interface for invoking models and applications deployed via Ray Serve. Each deployed application is exposed as an HTTP endpoint on the Serve HTTP proxy (default port 8000); authentication and routing are configured per deployment.

## Machine-readable artifacts (2)

- **Documentation** — https://docs.ray.io/en/latest/serve/index.html
- **Production Guide** — https://docs.ray.io/en/latest/serve/production-guide/index.html

## Other Ray APIs (4)

- [Ray Jobs REST API](https://apis.io/apis/ray/jobs-api/)
- [Ray Dashboard API](https://apis.io/apis/ray/dashboard-api/)
- [Ray Jobs API](https://apis.io/apis/ray/ray-jobs-api/)
- [Ray Version API](https://apis.io/apis/ray/ray-version-api/)

## Tags

Model Serving, Inference, HTTP

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/apis/ray/serve-api/). The API's provider profile, Kin Score and agent-readiness rating are at https://apis.io/providers/ray/.