- AI Model (LLM) Pricing: billed per token
- Per-Call API Pricing: billed per request
1. AI Model (LLM) Pricing
AI model APIs are billed based on token usage.
- Input tokens (prompt tokens)
- Output tokens (generated tokens)
- Chat completions
- Text generation
- Vision-enabled models
- Tool-enabled models
- Streaming responses
2. Per-Call API Pricing
All non-LLM APIs use a fixed per-request billing model.
- Search APIs
- Financial APIs
- YouTube APIs
- Scholar APIs
- Twitter APIs
- Other structured data and retrieval services
Choosing the Correct Pricing Model
If your API request:- Uses a language model to generate text → Token-based pricing applies
- Retrieves structured data or performs a search → Per-call pricing applies
Usage Tracking and Transparency
All API activity, whether token-based or per-call, is recorded in:- Usage Logs
- Account billing summaries
- Tokens consumed (for AI models)
- Number of requests (for per-call APIs)
- Final cost per request
- Applied pricing rules or group ratios
Additional Notes
- Pricing is usage-based; no fixed monthly platform fees.
- Pricing may vary by model, provider, group, or endpoint.
- Always refer to the Marketplace for the most up-to-date rates.
- Detailed billing breakdowns are available in Usage Logs.