Billing & Credits

AssistantRouter uses a pre-paid wallet system for transparent cost management.

Wallet System

Your workspace has a wallet that holds credits. API requests deduct credits based on token usage.

Adding Credits

Go to Billing in the dashboard
Click Add Credits
Choose an amount and complete payment
Credits are available immediately

Credit Pricing

Amount	Price
$10	$10.00
$25	$25.00
$50	$50.00
$100	$100.00
$500	$500.00

How Costs Are Calculated

Costs are based on:

Input tokens - Tokens in your prompt
Output tokens - Tokens generated by the model
Model pricing - Each model has different rates
Tool usage - Web search and RAG have additional costs

Total = LLM cost + Tool costs
LLM cost = (input_tokens × input_rate) + (output_tokens × output_rate)

View real-time costs for each request in the response's x_assistantrouter.cost_cents field.

Streaming Reservations

When streaming responses, credits are reserved upfront and adjusted after completion:

Reserve - Estimated cost is reserved from available balance
Stream - Response streams to the client
Settle - Actual cost is calculated, excess is refunded

This ensures you never run out of credits mid-stream.

Auto Top-up

Enable automatic top-up to ensure uninterrupted service:

Go to Settings > Billing in the dashboard
Enable Auto Top-up
Set a Threshold (default: $5.00)
Set a Top-up Amount (default: $25.00)

When your balance drops below the threshold, we automatically charge your payment method.

Checking Balance via API

Get your current balance:

const response = await fetch('https://api.assistantrouter.com/v1/wallet', {
  headers: {
    'Authorization': `Bearer ${process.env.API_KEY}`,
  },
});

const { data } = await response.json();
console.log(`Balance: $${(data.balance_cents / 100).toFixed(2)}`);
console.log(`Available: $${(data.available_cents / 100).toFixed(2)}`);

Response:

{
  "data": {
    "balance_cents": 5000,
    "reserved_cents": 50,
    "available_cents": 4950,
    "auto_topup_enabled": true,
    "auto_topup_threshold_cents": 500,
    "auto_topup_amount_cents": 2500
  }
}

Monitoring Usage

Dashboard Analytics

View usage analytics in the dashboard:

Daily/weekly/monthly spending
Costs by assistant
Costs by model
Token usage trends

API Usage Endpoint

Get usage statistics via API:

const response = await fetch('https://api.assistantrouter.com/v1/usage', {
  headers: {
    'Authorization': `Bearer ${process.env.API_KEY}`,
  },
});

const { data } = await response.json();

Response:

{
  "data": {
    "period": {
      "start": "2024-01-01T00:00:00Z",
      "end": "2024-01-31T23:59:59Z"
    },
    "summary": {
      "total_requests": 1250,
      "total_tokens": 450000,
      "total_cost_cents": 125,
      "average_latency_ms": 850
    },
    "by_model": [
      {
        "model": "anthropic/claude-haiku-4.5",
        "requests": 800,
        "cost_cents": 95
      }
    ]
  }
}

See the Usage API reference for more options.

Cost Optimization

Choose appropriate models - Use cheaper models (Gemini 2.5 Flash, Claude Haiku 4.5) for simple tasks
Optimize prompts - Shorter prompts = fewer input tokens
Set max_tokens - Limit response length when possible
Use conversations - Reuse conversation context instead of repeating history
Monitor regularly - Review usage patterns in the dashboard

Insufficient Balance

If your wallet runs low, requests will fail with insufficient_balance:

{
  "error": {
    "type": "insufficient_balance",
    "message": "Insufficient balance. Please add credits.",
    "required_cents": 10,
    "available_cents": 5
  }
}

Enable auto top-up or set up low balance alerts to avoid service interruptions.

Transaction History

View your transaction history via API:

const response = await fetch('https://api.assistantrouter.com/v1/wallet/transactions', {
  headers: {
    'Authorization': `Bearer ${process.env.API_KEY}`,
  },
});

const { data } = await response.json();

Response:

{
  "data": [
    {
      "id": "txn_abc123",
      "type": "topup",
      "amount_cents": 2000,
      "balance_after_cents": 5000,
      "description": "Manual top-up",
      "created_at": "2024-01-15T10:30:00Z"
    },
    {
      "id": "txn_xyz789",
      "type": "usage",
      "amount_cents": -15,
      "balance_after_cents": 3000,
      "description": "Chat completion - claude-haiku-4.5",
      "created_at": "2024-01-15T09:15:00Z"
    }
  ]
}

Invoices & Receipts

Invoices are generated for each credit purchase
Download from Billing > Invoices in the dashboard
Available in PDF format for accounting

Billing & Credits

AssistantRouter uses a pre-paid wallet system for transparent cost management.

Wallet System

Your workspace has a wallet that holds credits. API requests deduct credits based on token usage.

Adding Credits

Go to Billing in the dashboard
Click Add Credits
Choose an amount and complete payment
Credits are available immediately

Credit Pricing

Amount	Price
$10	$10.00
$25	$25.00
$50	$50.00
$100	$100.00
$500	$500.00

How Costs Are Calculated

Costs are based on:

Input tokens - Tokens in your prompt
Output tokens - Tokens generated by the model
Model pricing - Each model has different rates
Tool usage - Web search and RAG have additional costs

Total = LLM cost + Tool costs
LLM cost = (input_tokens × input_rate) + (output_tokens × output_rate)

View real-time costs for each request in the response's x_assistantrouter.cost_cents field.

Streaming Reservations

When streaming responses, credits are reserved upfront and adjusted after completion:

Reserve - Estimated cost is reserved from available balance
Stream - Response streams to the client
Settle - Actual cost is calculated, excess is refunded

This ensures you never run out of credits mid-stream.

Auto Top-up

Enable automatic top-up to ensure uninterrupted service:

Go to Settings > Billing in the dashboard
Enable Auto Top-up
Set a Threshold (default: $5.00)
Set a Top-up Amount (default: $25.00)

When your balance drops below the threshold, we automatically charge your payment method.

Checking Balance via API

Get your current balance:

const response = await fetch('https://api.assistantrouter.com/v1/wallet', {
  headers: {
    'Authorization': `Bearer ${process.env.API_KEY}`,
  },
});

const { data } = await response.json();
console.log(`Balance: $${(data.balance_cents / 100).toFixed(2)}`);
console.log(`Available: $${(data.available_cents / 100).toFixed(2)}`);

Response:

{
  "data": {
    "balance_cents": 5000,
    "reserved_cents": 50,
    "available_cents": 4950,
    "auto_topup_enabled": true,
    "auto_topup_threshold_cents": 500,
    "auto_topup_amount_cents": 2500
  }
}

Monitoring Usage

Dashboard Analytics

View usage analytics in the dashboard:

Daily/weekly/monthly spending
Costs by assistant
Costs by model
Token usage trends

API Usage Endpoint

Get usage statistics via API:

const response = await fetch('https://api.assistantrouter.com/v1/usage', {
  headers: {
    'Authorization': `Bearer ${process.env.API_KEY}`,
  },
});

const { data } = await response.json();

Response:

{
  "data": {
    "period": {
      "start": "2024-01-01T00:00:00Z",
      "end": "2024-01-31T23:59:59Z"
    },
    "summary": {
      "total_requests": 1250,
      "total_tokens": 450000,
      "total_cost_cents": 125,
      "average_latency_ms": 850
    },
    "by_model": [
      {
        "model": "anthropic/claude-haiku-4.5",
        "requests": 800,
        "cost_cents": 95
      }
    ]
  }
}

See the Usage API reference for more options.

Cost Optimization

Choose appropriate models - Use cheaper models (Gemini 2.5 Flash, Claude Haiku 4.5) for simple tasks
Optimize prompts - Shorter prompts = fewer input tokens
Set max_tokens - Limit response length when possible
Use conversations - Reuse conversation context instead of repeating history
Monitor regularly - Review usage patterns in the dashboard

Insufficient Balance

If your wallet runs low, requests will fail with insufficient_balance:

{
  "error": {
    "type": "insufficient_balance",
    "message": "Insufficient balance. Please add credits.",
    "required_cents": 10,
    "available_cents": 5
  }
}

Enable auto top-up or set up low balance alerts to avoid service interruptions.

Transaction History

View your transaction history via API:

const response = await fetch('https://api.assistantrouter.com/v1/wallet/transactions', {
  headers: {
    'Authorization': `Bearer ${process.env.API_KEY}`,
  },
});

const { data } = await response.json();

Response:

{
  "data": [
    {
      "id": "txn_abc123",
      "type": "topup",
      "amount_cents": 2000,
      "balance_after_cents": 5000,
      "description": "Manual top-up",
      "created_at": "2024-01-15T10:30:00Z"
    },
    {
      "id": "txn_xyz789",
      "type": "usage",
      "amount_cents": -15,
      "balance_after_cents": 3000,
      "description": "Chat completion - claude-haiku-4.5",
      "created_at": "2024-01-15T09:15:00Z"
    }
  ]
}

Invoices & Receipts

Invoices are generated for each credit purchase
Download from Billing > Invoices in the dashboard
Available in PDF format for accounting

Billing & Credits

Billing & Credits

Wallet System

Adding Credits

Credit Pricing

How Costs Are Calculated

Streaming Reservations

Auto Top-up

Checking Balance via API

Monitoring Usage

Dashboard Analytics

API Usage Endpoint

Cost Optimization

Insufficient Balance

Transaction History

Invoices & Receipts

On this page

Billing & Credits

Billing & Credits

Wallet System

Adding Credits

Credit Pricing

How Costs Are Calculated

Streaming Reservations

Auto Top-up

Checking Balance via API

Monitoring Usage

Dashboard Analytics

API Usage Endpoint

Cost Optimization

Insufficient Balance

Transaction History

Invoices & Receipts

On this page