# ChatWithHuman.ai — The human layer for your AI agents

> When your agent hits a wall, ChatWithHuman.ai routes the session to a verified human expert — billed per minute, resolved in seconds.

## Hand off to a human in one API call

One REST call to escalate any session. Works with any agent framework.

```http
POST https://chatwithhuman.ai/api/sessions
Authorization: Bearer <API_KEY>
Content-Type: application/json

{
  "agent_id": "agent_abc123",
  "context": "User is asking about a refund for order #8821",
  "tier": "standard"
}

// Response 201
{ "session_id": "ses_x9k2m", "status": "queued", "eta_seconds": 12, "billing_started": false, "tier": "standard", "rate_cents_per_minute": 1000, "metadata": {} }
```

```bash
curl -X POST https://chatwithhuman.chrismai.ai/api/sessions \
  -H "Authorization: Bearer $CHATWITHHUMAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "agent_id": "agent_abc123",
  "context": "User is asking about a refund for order #8821",
  "tier": "standard"
}'
```

## At a glance

| Metric | Value |
| --- | --- |
| Standard rate | $10/min |
| To hand off | 1 call |
| Uptime target | 99.9% |

## Billing examples (computed from published rates)

- Standard · 2m 00s connected → 2 min × $10 = $20.00
- Standard · 0m 45s connected → 1-min minimum = $10.00
- Priority · 3m 00s connected → 3 min × $25 = $75.00
- Priority · 1m 30s connected → whole minutes: 1 × $25 = $25.00
- Platform fee → $0.00
- Enterprise → from $250,000 / year, by contract

## How it works

1. **AI hits a wall** — Your agent detects a scenario it can't resolve — ambiguous intent, sensitive context, or a task requiring human judgment.
2. **Routes to ChatWithHuman.ai** — A single API call escalates the session. ChatWithHuman.ai matches it to an available human expert based on topic, language, and urgency.
3. **Human responds in seconds** — The expert joins the live session, resolves the issue, and hands control back to your agent. Billed per minute at your tier's rate.

## Built for production

- **Real-time chat interface** — Human operators get a live dashboard with session queue, typing indicators, full message history, and context from your agent. Zero latency handoff.
- **Per-minute billing** — Metered per minute while a human is connected: $10/min Standard, $25/min Priority. No platform fee. Usage dashboard with per-agent breakdowns and per-session invoices.
- **Scheduling & availability** — Set expert availability windows, timezone-aware scheduling, and live/busy status. Overflow routing built in.
- **Webhooks (planned)** — Planned: POST events to your endpoint on session start, message, and close. Today, stream the same events over SSE.
- **Session history** — Full transcript storage with search, export, and replay.

## Transparent pricing

No subscriptions. No seat fees. Pay only for what you use.

| Item | Value | Unit | Note |
| --- | --- | --- | --- |
| Standard | $10 | / min | Pay-as-you-go · developers, small teams |
| Priority | $25 | / min | Guaranteed fast human response |
| Enterprise | from $250,000 | / year | Dedicated expert, SLA, contract |
| Platform fee | None | — | No subscriptions or seat fees |

## Ready to add a human layer?

Get your API key and make your first escalation in under 5 minutes.

```yaml
# Session escalated successfully
session_id: "ses_x9k2m"
status: "connected"
tier: "standard"
rate_cents_per_minute: 1000
billingStartedAt: "2026-10-14T21:18:04Z"
```

## Machine-readable

- [/llms.txt](https://chatwithhuman.chrismai.ai/llms.txt): llmstxt.org index: summary + links
- [/llms-full.txt](https://chatwithhuman.chrismai.ai/llms-full.txt): All docs, pricing and FAQ inlined in one file
- [/openapi.json](https://chatwithhuman.chrismai.ai/openapi.json): OpenAPI 3.1 spec of the implemented /api routes
- [/agents.md](https://chatwithhuman.chrismai.ai/agents.md): Guide for AI agents: when and how to hand off to a human
- [/.well-known/ai-plugin.json](https://chatwithhuman.chrismai.ai/.well-known/ai-plugin.json): AI plugin manifest (points to openapi.json)
- [/.well-known/mcp.json](https://chatwithhuman.chrismai.ai/.well-known/mcp.json): MCP server descriptor — status: planned
- [/index.md](https://chatwithhuman.chrismai.ai/index.md): Markdown twin of every page (/docs.md, /pricing.md …)
- [/sitemap.xml](https://chatwithhuman.chrismai.ai/sitemap.xml): Sitemap incl. markdown twins
- [/robots.txt](https://chatwithhuman.chrismai.ai/robots.txt): Crawl policy — AI crawlers explicitly welcome

## Pages

- [Home](https://chatwithhuman.chrismai.ai/) · [markdown](https://chatwithhuman.chrismai.ai/index.md)
- [For agents](https://chatwithhuman.chrismai.ai/agents) · [markdown](https://chatwithhuman.chrismai.ai/agents.md)
- [Developer docs](https://chatwithhuman.chrismai.ai/docs) · [markdown](https://chatwithhuman.chrismai.ai/docs.md)
- [Pricing](https://chatwithhuman.chrismai.ai/pricing) · [markdown](https://chatwithhuman.chrismai.ai/pricing.md)
- [System status](https://chatwithhuman.chrismai.ai/status) · [markdown](https://chatwithhuman.chrismai.ai/status.md)