Skip to content
Omni Octo Docs 
from openai import OpenAI

client = OpenAI(
    api_key="sk-octo_…",
    base_url="https://api.omniocto.com/v1",
)
resp = client.responses.create(
    model="claude-sonnet-4-6",
    input="Reply to my last email",
)
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-octo_…",
  baseURL: "https://api.omniocto.com/v1",
});
const resp = await client.responses.create({
  model: "claude-sonnet-4-6",
  input: "Reply to my last email",
});
{
  "mcpServers": {
    "octo": {
      "url": "https://api.omniocto.com/mcp",
      "headers": {
        "Authorization": "Bearer sk-octo_…"
      }
    }
  }
}

Omni Octo API

Talk to Octo from any OpenAI-compatible tool, MCP client, or the platform REST API. Flip base_url + api_key and go.
Get started OpenAI API reference

OpenAI-compatible API

Point the OpenAI SDK (or LiteLLM, LangChain, n8n…) at https://api.omniocto.com/v1 with your API key. Overview →

MCP servers

Connect an MCP client to Octo’s public and meta-agent servers. Connect →

Platform REST API

The full /api/* surface — agents, campaigns, contacts, voice, billing. Reference →

Built for agents

llms.txt, per-page markdown, OpenAPI JSON, and a live docs-search MCP. Agent resources →