Skip to main content

Models & Pricing

This section introduces the model types supported in the console, billing modes, and how to query prices.

🤖 Supported Model List​

The platform provides a variety of mainstream large language models (LLM), multimodal models, and dedicated interface services, supporting on-demand access and calling.

⚖️ Billing Rules & Multipliers​

  • Token-based Billing: The system's billing unit is Token. Input, output, cache creation, and cache reading are calculated separately.
  • Model Completion Multiplier: Different models have different output generation costs. The system applies the corresponding completion multiplier to output Tokens.
  • Group Multiplier: According to the service group or concurrent channel selected by the user, the system applies the corresponding group multiplier.

🔍 Price Query​

Users can view in real time on the “Model Square” page of the console:

  • Prompt and Completion Token unit prices for each model;
  • Current free quota and free call counts for the model (if any);
  • Model availability and detailed group rate information.