Billing & Usage
Understand how thinnestAI billing works — token-based pricing, free tier credits, model-specific rates, and usage tracking.
Billing & Usage
thinnestAI uses a simple, transparent billing system based on USD tokens. You add funds to your account, and usage is deducted as you go. No surprise invoices, no complex tiers — just pay for what you use.
How Billing Works
- Add funds to your account balance (in USD).
- Use your agents — each chat message, voice call, and knowledge ingestion consumes tokens.
- Tokens are deducted from your balance in real time.
- Top up when your balance runs low, or enable auto-topup.
Your current balance and usage history are always visible in the dashboard under Settings > Billing.
Free Tier and Trial Credits
Every new account receives free trial credits to get started:
| What You Get | Amount |
|---|---|
| Trial credits | Enough for ~100 chat messages or ~10 minutes of voice |
| Duration | No expiry on trial credits |
| Limitations | Some advanced features require a paid balance |
Trial credits let you build, test, and deploy your first agent without entering payment information.
Token Pricing
Usage is metered across three categories:
Chat (Text Conversations)
Chat billing is based on the number of input and output tokens processed by the language model.
| Component | Rate |
|---|---|
| Input tokens | Varies by model (see below) |
| Output tokens | Varies by model (see below) |
| Knowledge retrieval | Small per-query fee |
Voice Calls
Voice is billed per minute of active call time.
| Component | Rate |
|---|---|
| Voice call | Per-minute rate (see Phone Billing) |
| Phone number rental | Monthly fee per number |
Knowledge Ingestion
Uploading documents to your agent's knowledge base incurs a one-time ingestion fee.
| Component | Rate |
|---|---|
| Document ingestion | Per-page or per-chunk fee |
| Embedding generation | Included in ingestion |
| Storage | Included |
Model-Specific Pricing
Different AI models have different costs. More capable models cost more per token.
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|
| GPT-4o | $2.50 | $10.00 |
| GPT-4o-mini | $0.15 | $0.60 |
| GPT-4 Turbo | $10.00 | $30.00 |
| Claude 3.5 Sonnet | $3.00 | $15.00 |
| Claude 3 Haiku | $0.25 | $1.25 |
| Gemini 1.5 Pro | $1.25 | $5.00 |
| Gemini 1.5 Flash | $0.075 | $0.30 |
Note: Prices are subject to change as model providers update their rates. The dashboard always shows the current pricing.
Choosing a Model
- High quality, higher cost: GPT-4 Turbo, Claude 3.5 Sonnet — best for complex reasoning tasks.
- Good quality, balanced cost: GPT-4o, Gemini 1.5 Pro — great for most use cases.
- Fast and affordable: GPT-4o-mini, Claude 3 Haiku, Gemini 1.5 Flash — ideal for high-volume, simpler tasks.
You can set different models for different agents. Use a cheaper model for your FAQ bot and a premium model for your research agent.
Topping Up Your Balance
From the Dashboard
- Go to Settings > Billing.
- Click Add Funds.
- Enter the amount (minimum $5).
- Complete payment via credit card or supported payment method.
- Funds are available immediately.
Auto-Topup
Never run out of credits unexpectedly. Enable auto-topup to automatically add funds when your balance drops below a threshold:
- Go to Settings > Billing > Auto-Topup.
- Toggle Enable Auto-Topup.
- Set the trigger threshold (e.g., $5.00).
- Set the topup amount (e.g., $25.00).
- Save.
When your balance drops below $5.00, $25.00 is automatically charged to your payment method.
Via the API
curl -X POST https://api.thinnest.ai/billing/v3/topup \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"amount": 25.00,
"payment_method_id": "pm_abc123"
}'Viewing Usage
Usage Dashboard
The billing dashboard shows:
- Current balance: Your available funds.
- Usage this month: Total spend broken down by category.
- Usage by agent: Which agents are consuming the most tokens.
- Usage by model: Cost breakdown per model.
- Daily trend: A chart of daily spending over the past 30 days.
Usage API
curl https://api.thinnest.ai/billing/v3/balance?period=month \
-H "Authorization: Bearer YOUR_API_KEY"{
"period": "2026-03",
"total_spent": 47.82,
"balance": 152.18,
"breakdown": {
"chat": 32.15,
"voice": 12.40,
"knowledge": 3.27
},
"by_agent": [
{"agent": "Customer Support", "spent": 28.50},
{"agent": "Sales Assistant", "spent": 12.05},
{"agent": "Research Bot", "spent": 7.27}
]
}Billing Records
Every charge is recorded with full details:
curl https://api.thinnest.ai/billing/history/{user_id}?limit=10 \
-H "Authorization: Bearer YOUR_API_KEY"{
"records": [
{
"id": "bill_abc123",
"type": "chat",
"agent": "Customer Support",
"model": "gpt-4o-mini",
"input_tokens": 1250,
"output_tokens": 340,
"cost": 0.0004,
"timestamp": "2026-03-05T10:30:00Z"
}
]
}Spending Alerts
Set up alerts to stay on top of your spending:
- Go to Settings > Billing > Alerts.
- Add a spending threshold (e.g., "Alert me when daily spend exceeds $10").
- Choose notification method (email or dashboard notification).
What Happens When Your Balance Runs Out
| Scenario | Behavior |
|---|---|
| Balance reaches $0 | Chat requests return an error; voice calls are not placed |
| Auto-topup enabled | Balance is automatically replenished |
| Phone numbers | Enter a grace period (see Phone Billing) |
| Scheduled campaigns | Paused until balance is restored |
Your agents, configuration, and data are never deleted due to low balance. Only active usage is paused.
Next Steps
- Phone & Voice Billing — Detailed voice and phone number pricing.
- Deployment — Self-host to manage your own costs.
- Agents — Optimize your agents for cost efficiency.