API Integration
One endpoint.
Any app, any language.
Every agent ships with a secure REST endpoint and a personal API key. Send a message, get a response — same shape, every time.
Standard REST
Predictable shape, every time.
POST a JSON payload, get a response. Same contract whether you're calling from Python, Go, or your phone.
Chat endpoint
Synchronous request/response for simple integrations. Perfect for serverless or scripts.
{ "agent": "support" "message": "..." }
Streaming endpoint
Tokens stream as they arrive. Use Server-Sent Events for chatbots and live UIs.
data: " support"
data: " refunds"
OpenAPI spec
Auto-generate clients in any language. Drop our spec into your codegen pipeline.
paths:
/v1/chat: ...
/v1/chat/stream: ...
API key auth
Send your key in the x-api-key header. One key per account, scoped to your usage. No OAuth dance, no SDK required.
x-api-key: sk-so-•••••••
Production ready
Built for real workloads.
Rate limits, retries, tracing, and version control — everything you need to ship AI safely at scale.
Rate limits
Per-account quotas keep your bill predictable and your downstream services safe.
Automatic retries
Transient errors retry with exponential backoff. Your code stays simple.
Tracing built in
Every request and response is logged with latency, tokens, and cost.
Swap models
Switch from GPT-4o to Claude in the dashboard — your code never changes.
“Every time you want to add AI to your app, you end up writing a ton of code — managing API keys, handling conversation history, engineering prompts, counting tokens. And then six months later a better model comes out and you have to refactor everything. SentientOne just removes all of that.”
Daniel Marsh
CTO
Transparent Plans for Every Team Size
Start with Starter, scale with Pro, or go unlimited with Enterprise. No hidden fees.
14 day free trial and cancel anytime.
Starter
For solo developers exploring AI agents.
- 1 AI agent + 10k API requests/month
- 1 MCP server per agent
- Chatbot widget
- Knowledge (Documents + FAQs) — 100 Credits †
- Rate limit 30 RPM
- 14-day log + chat history
- Analytics
- Community support
- Streamable HTTP endpoint
- AI Workspace (Team Chat)
- Organisational support
Pro
Integrating agents into production apps.
- 5 AI agents + 50k API requests/month
- 2 MCP servers per agent
- Chatbot widget
- Knowledge (Documents + FAQs) — 300 Credits †
- Rate limit 50 RPM
- 90-day log + chat history
- Full observability & analytics (Trace)
- Streamable HTTP endpoint
- AI Workspace (Team Chat)
- Organisational support
- Team members ($9/member)
- Email support (48h)
Enterprise
For orgs needing compliance at scale.
- Unlimited agents + API calls
- Unlimited MCP servers
- Unlimited document + Knowledge
- Custom rate limits
- Custom log retention
- Full observability & analytics (Trace)
- AI Workspace (Team Chat)
- Organisational support
- Self-hosted option
- Dedicated SLA & onboarding
All plans come with a free ChatGPT-like chat interface to talk to your agents.
All plans include BYOK (bring your own LLM API keys). Prices in USD. Cancel anytime.
† 1 Credit = 1 FAQ, 5 Credits = 1 Document. Additional credits available for purchase.
Add AI to anything in one POST request.
Skip the SDK marathon. One endpoint, one API key, one response shape — that's the entire integration.