---
title: "OpenAI-compatible chat completions (governed)"
method: POST
path: "/v1/chat/completions"
tags: ["proxy"]
---

# OpenAI-compatible chat completions (governed)

`POST /v1/chat/completions`

## Request

- Base URL: `https://api.agenticcontrolplane.com`
- URL: `https://api.agenticcontrolplane.com/v1/chat/completions`
- Auth: HTTP bearer

Drop-in replacement for the OpenAI chat-completions endpoint: point your client's base URL at the gateway and every call is policy-checked, priced, and audited. Request/response bodies follow the OpenAI API. Errors use the OpenAI-compatible envelope; 429s carry Retry-After.

## Request body

- object

## Response `200`

Vendor-shaped completion (or SSE stream).

## Other responses

- `401`: Auth error.
- `402`: Budget exhausted.
- `403`: Denied by policy.
- `429`: Rate limited (Retry-After set).

---

[API](https://skmtc.dev/agenticcontrolplane/apis/agentic-control-plane-gateway-api.md) · [All operations](https://skmtc.dev/agenticcontrolplane/apis/agentic-control-plane-gateway-api/llms.txt) · [OpenAPI document](https://skmtc.dev/agenticcontrolplane/apis/agentic-control-plane-gateway-api/revisions/161819f3df00?raw)