REST API

One POST endpoint, two headers, JSON in / JSON out. The platform handles system prompt injection, conversation history, MCP tool round-trips, and response storage.

The whole API in one request

Anatomy of a SentientOne request

POST /v1/chatapi.sentientone.ai200 OK

Headers

X-Api-Key

sk-so-•••• 3F92

X-Agent-Id

a1b2c3d4-e5f6-…

Content-Type

application/json

Body

{
  "message": "Hello, agent!",
  "conversation_id": null
}

conversation_id (optional)message (required)

bash

curl -X POST https://api.sentientone.ai/v1/chat \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: sk-so-YOUR_KEY" \
  -H "X-Agent-Id: YOUR_AGENT_ID" \
  -d '{ "message": "Hello!" }'

That's it. X-Api-Key authenticates your account; X-Agent-Id selects which configured agent runs the request; the body carries the user's message and (optionally) the conversation id you want to continue.

What to read

Authentication

Headers, key formats, and where to find each value.

Chat Endpoint

Request body fields, response shape, and multi-turn handling.

Streaming

Server-Sent Events for progressive token delivery.

Error Codes

Every error the platform can return — with fixes.

Rate Limits

Per-account quotas, response headers, and retry strategy.

Performance

Prompt caching, auto-retries, token optimization.

Code Examples

Drop-in snippets — Python, JavaScript, TypeScript, C#, cURL.

Try before you wire

Use the API Sandbox in the dashboard to test any request shape end-to-end without writing code. It hits the same endpoint your integration will hit.