> ## Documentation Index
> Fetch the complete documentation index at: https://docs.savegate.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pricing

> Transparent pricing for all AI models with 30-50% savings

## Save 30-50% on AI Costs

SaveGate offers significantly lower prices than direct provider pricing through shared infrastructure and enterprise agreements.

<Card title="Free Tier" icon="gift">
  Get started free with 100K tokens per month included.
  No credit card required.
</Card>

## Pay-As-You-Go Pricing

Pay only for what you use. No monthly minimums or commitments.

### Pricing Comparison

See how much you save compared to direct provider pricing:

<Tabs>
  <Tab title="OpenAI Models">
    | Model             | SaveGate Input | SaveGate Output | OpenAI Input | OpenAI Output | Savings    |
    | ----------------- | -------------- | --------------- | ------------ | ------------- | ---------- |
    | **GPT-4 Turbo**   | \$0.007        | \$0.021         | \$0.01       | \$0.03        | **30%**    |
    | **GPT-4**         | \$0.021        | \$0.042         | \$0.03       | \$0.06        | **30%**    |
    | **GPT-3.5 Turbo** | \$0.0003       | \$0.0006        | \$0.0005     | \$0.0015      | **40-60%** |

    *Prices per 1,000 tokens*
  </Tab>

  <Tab title="Anthropic Models">
    | Model                 | SaveGate Input | SaveGate Output | Anthropic Input | Anthropic Output | Savings |
    | --------------------- | -------------- | --------------- | --------------- | ---------------- | ------- |
    | **Claude 3.5 Sonnet** | \$0.002        | \$0.010         | \$0.003         | \$0.015          | **33%** |
    | **Claude 3 Opus**     | \$0.010        | \$0.050         | \$0.015         | \$0.075          | **33%** |
    | **Claude 3 Haiku**    | \$0.00018      | \$0.00090       | \$0.00025       | \$0.00125        | **28%** |

    *Prices per 1,000 tokens*
  </Tab>

  <Tab title="Google Models">
    | Model                | SaveGate Input | SaveGate Output | Google Input | Google Output | Savings    |
    | -------------------- | -------------- | --------------- | ------------ | ------------- | ---------- |
    | **Gemini 1.5 Pro**   | \$0.002        | \$0.006         | \$0.0025     | \$0.0075      | **20%**    |
    | **Gemini 1.5 Flash** | \$0.00005      | \$0.00015       | \$0.000075   | \$0.0003      | **33-50%** |

    *Prices per 1,000 tokens*
  </Tab>
</Tabs>

<Note>
  Prices are per 1,000 tokens. Most models have separate pricing for input and output tokens.
</Note>

## Free Tier

Every SaveGate account includes:

* **100K tokens/month** free
* Access to all models
* No credit card required
* Full API access
* Real-time analytics

Perfect for:

* Testing and development
* Small projects
* Learning and experimentation

## Usage-Based Billing

<AccordionGroup>
  <Accordion title="How Billing Works" icon="credit-card">
    1. **Track Usage**: We track your token usage across all models
    2. **Monthly Billing**: Charges accumulate throughout the month
    3. **Auto-Pay**: Automatically charged at month-end
    4. **Detailed Invoices**: View breakdown by model and day
  </Accordion>

  <Accordion title="Understanding Tokens" icon="coins">
    Tokens are pieces of words used for processing. On average:

    * **English**: \~4 characters per token
    * **Code**: \~3 characters per token
    * **Other languages**: Varies by language

    Example: "Hello, world!" = \~4 tokens

    Use our token calculator in the dashboard to estimate costs.
  </Accordion>

  <Accordion title="Billing Alerts" icon="bell">
    Set up alerts to monitor spending:

    * Daily spending alerts
    * Monthly budget limits
    * Per-model cost tracking
    * Automatic email notifications
  </Accordion>

  <Accordion title="Payment Methods" icon="wallet">
    We accept:

    * Credit/Debit cards (Visa, Mastercard, Amex)
    * Wire transfer (for enterprise)
    * Crypto payments (coming soon)
  </Accordion>
</AccordionGroup>

## Enterprise Plans

For large-scale deployments and organizations:

<CardGroup cols={2}>
  <Card title="Team Plan" icon="users">
    **Starting at \$500/month**

    * Volume discounts
    * Team management
    * Priority support
    * Dedicated account manager
    * Custom rate limits
  </Card>

  <Card title="Enterprise Plan" icon="building">
    **Custom Pricing**

    * Maximum discounts
    * SLA guarantees
    * On-premises deployment
    * Custom integrations
    * 24/7 phone support
    * Legal & compliance review
  </Card>
</CardGroup>

<Card title="Contact Sales" icon="envelope" href="mailto:contact@savegate.ai">
  Get a custom quote for your organization
</Card>

## Cost Calculator

Estimate your monthly costs:

<AccordionGroup>
  <Accordion title="Example: Chatbot Application" icon="robot">
    **Assumptions:**

    * 10,000 conversations/month
    * Average 10 messages per conversation
    * 100 tokens input + 150 tokens output per message
    * Using GPT-3.5 Turbo

    **Calculation:**

    * Total messages: 10,000 × 10 = 100,000
    * Input tokens: 100,000 × 100 = 10M
    * Output tokens: 100,000 × 150 = 15M
    * Input cost: 10M × $0.0003 / 1K = $3
    * Output cost: 15M × $0.0006 / 1K = $9
    * **Total: \$12/month**
  </Accordion>

  <Accordion title="Example: Content Generation" icon="file-lines">
    **Assumptions:**

    * 1,000 articles/month
    * 500 tokens prompt + 2,000 tokens generated
    * Using GPT-4 Turbo

    **Calculation:**

    * Input tokens: 1,000 × 500 = 500K
    * Output tokens: 1,000 × 2,000 = 2M
    * Input cost: 500K × $0.007 / 1K = $3.50
    * Output cost: 2M × $0.021 / 1K = $42
    * **Total: \$45.50/month**
  </Accordion>

  <Accordion title="Example: Code Assistant" icon="code">
    **Assumptions:**

    * 500 coding sessions/month
    * Average 20 requests per session
    * 200 tokens input + 300 tokens output
    * Using Claude 3.5 Sonnet

    **Calculation:**

    * Total requests: 500 × 20 = 10,000
    * Input tokens: 10,000 × 200 = 2M
    * Output tokens: 10,000 × 300 = 3M
    * Input cost: 2M × $0.002 / 1K = $4
    * Output cost: 3M × $0.010 / 1K = $30
    * **Total: \$34/month**
  </Accordion>
</AccordionGroup>

## Billing FAQs

<AccordionGroup>
  <Accordion title="When am I charged?" icon="calendar">
    * Charges accumulate throughout the month
    * Billed on the 1st of each month
    * Free tier resets monthly
    * Invoice sent via email
  </Accordion>

  <Accordion title="Can I get a refund?" icon="rotate-left">
    * Refunds available for billing errors
    * Contact support within 30 days
    * Unused credits can be refunded
    * Enterprise plans have custom terms
  </Accordion>

  <Accordion title="What if I exceed my budget?" icon="triangle-exclamation">
    * Set up budget alerts in dashboard
    * API access continues by default
    * Can set hard limits to stop API calls
    * Email notifications before limits
  </Accordion>

  <Accordion title="Do you offer volume discounts?" icon="percent">
    Yes! Automatic discounts apply:

    * \$1,000+/month: 10% discount
    * \$5,000+/month: 20% discount
    * \$10,000+/month: 30% discount
    * Enterprise: Custom pricing
  </Accordion>
</AccordionGroup>

## View Your Usage

Track costs in real-time:

1. Go to [Dashboard](https://app.savegate.ai)
2. Navigate to "Usage & Billing"
3. View breakdown by:
   * Model
   * Day/Week/Month
   * Application (if using multiple keys)
   * Cost trends

## Save Even More

<CardGroup cols={2}>
  <Card title="Use Cheaper Models" icon="piggy-bank">
    Start with GPT-3.5 or Claude Haiku for simple tasks, upgrade only when needed.
  </Card>

  <Card title="Optimize Prompts" icon="wand-magic-sparkles">
    Shorter prompts = lower costs. Be concise and specific.
  </Card>

  <Card title="Cache Responses" icon="database">
    Cache common responses to avoid duplicate API calls.
  </Card>

  <Card title="Batch Requests" icon="layer-group">
    Process multiple items in single requests when possible.
  </Card>
</CardGroup>