Agentic Control Plane Proxy API
Governed model proxy — OpenAI- and Anthropic-compatible.
Governed model proxy — OpenAI- and Anthropic-compatible.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/agenticcontrolplane-com:agenticcontrolplane-com-proxy-api"
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Agentic Control Plane — Gateway Proxy API
version: 0.1.0
description: 'The public, gsk_-key-authenticated surface of the ACP gateway: agent profiles, run summaries,
self-introspection (cost / usage / decisions / traces), delegation-chain child-key minting,
scoped-token issuance, the governed model proxy, and the MCP endpoint.
**Rate limits.** Rate-limited endpoints return IETF draft-7 `RateLimit` / `RateLimit-Policy`
headers on every response and a 429 with the same headers when exceeded.
**Errors.** Three envelopes coexist and are documented per-endpoint: `{ error: string }` on
/api/v1/*, `{ error: ''validation_failed'', details }` on schema-validated bodies, and the
OpenAI-compatible `{ error: { message, type, param, code } }` on the model proxy.
**Feature-flagged surfaces.** `/api/v1/keys/child`, `/api/v1/scoped-tokens`, and
`/v1/sandbox-tenants` are deployment-flagged; when disabled they 404.
Human docs: https://agenticcontrolplane.com/agents/configure-as-code — agent-facing site
index: https://agenticcontrolplane.com/llms.txt'
contact:
name: Agentic Control Plane
email: hello@agenticcontrolplane.com
url: https://agenticcontrolplane.com/contact
servers:
- url: https://api.agenticcontrolplane.com
security:
- ApiKeyAuth: []
tags:
- name: Proxy
description: Governed model proxy — OpenAI- and Anthropic-compatible.
paths:
/v1/chat/completions:
post:
tags:
- Proxy
operationId: proxyChatCompletions
summary: OpenAI-compatible chat completions (governed)
description: '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.'
requestBody:
required: true
content:
application/json:
schema:
type: object
additionalProperties: true
responses:
'200':
description: Vendor-shaped completion (or SSE stream).
'401':
description: Auth error.
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
'402':
description: Budget exhausted.
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
'403':
description: Denied by policy.
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
'429':
description: Rate limited (Retry-After set).
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
/v1/models:
get:
tags:
- Proxy
operationId: proxyListModels
summary: List models (OpenAI-compatible)
responses:
'200':
description: OpenAI-shaped model list.
'401':
description: Auth error.
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
/anthropic/v1/messages:
post:
tags:
- Proxy
operationId: proxyAnthropicMessages
summary: Anthropic-compatible messages (governed)
description: Anthropic-native proxy path — same governance treatment as /v1/chat/completions with Anthropic request/response shapes.
requestBody:
required: true
content:
application/json:
schema:
type: object
additionalProperties: true
responses:
'200':
description: Vendor-shaped response (or SSE stream).
'401':
description: Auth error.
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
'403':
description: Denied by policy.
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
'429':
description: Rate limited (Retry-After set).
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
/openai/v1/responses:
post:
tags:
- Proxy
operationId: proxyOpenAiResponses
summary: OpenAI Responses API (governed)
requestBody:
required: true
content:
application/json:
schema:
type: object
additionalProperties: true
responses:
'200':
description: Vendor-shaped response (or SSE stream).
'401':
description: Auth error.
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
'403':
description: Denied by policy.
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
'429':
description: Rate limited (Retry-After set).
content:
application/json:
schema:
$ref: '#/components/schemas/ProxyError'
components:
schemas:
ProxyError:
type: object
description: OpenAI-compatible error envelope used by the model-proxy endpoints (/v1/chat/completions, /anthropic/v1/messages, /openai/v1/responses).
required:
- error
properties:
error:
type: object
required:
- message
- type
properties:
message:
type: string
type:
type: string
description: authentication_error | permission_error | rate_limit_error | billing_error | invalid_request_error | api_error
param:
type:
- string
- 'null'
code:
type:
- string
- 'null'
securitySchemes:
ApiKeyAuth:
type: http
scheme: bearer
description: 'Workspace API key (`gsk_{slug}_…`) as a Bearer token. Mint keys in the console: https://cloud.agenticcontrolplane.com'