AI Models & Pricing

Compare pricing and capabilities across all available AI models. Transparent, per-token pricing for every model.

Addons

Enhance your API experience with powerful addon features. All addons are currently free.

Automatic Fallback

Automatically switch to backup models if the primary model fails or is unavailable.

Free
$10/month$10/month

Currently free for all users

Multiple Routing

Route requests across multiple models simultaneously for redundancy and performance.

Free
$15/month$15/month

Currently free for all users

Advanced Analytics

Get detailed insights, usage reports, and performance metrics for your API usage.

Free
$20/month$20/month

Currently free for all users

Model Pricing & Details

All prices are per million tokens. Input tokens are what you send to the model, output tokens are what the model generates.

How to Use

1. Get Your API Key

Create an account and generate your API key from the dashboard. Your API key is required for all requests.

2. Make API Requests

Use our unified API endpoint /v1/chat/completions with your preferred model. All models use the same OpenAI-compatible format.

3. Choose a Provider

Specify the provider (gemini, openai, xai) or use intelligent routing strategies (static, cheapest, fastest, failover) to automatically select the best model.

4. Monitor Usage

Track your usage, costs, and performance in real-time through your dashboard. Costs are automatically deducted from your wallet balance.

Pricing Information

Pay-As-You-Go

All pricing is per million tokens. Input tokens are what you send to the model, and output tokens are what the model generates. You only pay for what you use.

Cost Calculation

Total cost = (Input tokens × Input price) + (Output tokens × Output price). Prices are shown per million tokens.

Wallet Balance

Maintain a minimum balance of $0.10 to make API requests. Top up your wallet anytime using Stripe. Funds are deducted automatically after each request.

Best Value Models

For cost-effective options, consider GPT-5 Nano, GPT-4o Mini, or Gemini Flash models. For maximum capability, use GPT-5, GPT-4o, or Gemini Pro models.

Need Help?

For detailed API documentation, code examples, and integration guides, visit our API Documentation page. If you need assistance or have questions, feel free to contact us.