API Reference
Everstack REST API reference — OpenAI-compatible gateway and platform APIs.
Everstack exposes an OpenAI-compatible gateway API for LLM operations, plus platform APIs for agents, memory, workflows, functions, and more.
All endpoints are served on the same port (default 8089).
The base URL for OpenAI-compatible clients is https://{instance}.{region}.everstack.ai/v1. Pass it to an OpenAI SDK as base_url (Python) or baseURL (Node.js): the SDK appends the endpoint path, such as /chat/completions, itself. Authenticate with your Everstack API key, either as Authorization: Bearer <key> (what OpenAI SDKs send) or in the x-evs-api-key header.
curl https://{instance}.{region}.everstack.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-5.4-mini", "messages": [{"role": "user", "content": "Hello"}]}'Clients configured with the older /openai/v1 base URL keep working; it is still served as an alias.
Gateway
OpenAI-compatible endpoints — drop-in replacement for any OpenAI SDK.
Platform
Agents API
Create and manage agents, sessions, and HITL approvals.
Workflows API
Workflow CRUD and execution management.
Memory API
Vector memory collections and semantic search.
Functions API
Isolated function management and execution.
Providers API
Configure and manage LLM provider integrations.
API Keys
Create, list, and revoke API keys.
MCP API
Model Context Protocol server management.

