Comparison of Performance Indicators for Large Model API
In depth analysis of key indicators such as TTFT and TPS
- Support filtering performance indicators of different models based on conditions
- Provide the speed at which the model processes requests and starts outputting text (TTFT)
- Show the speed at which the model generates text (TPS)
- Display the total time from the start of the request to the completion of the response
- List the supported context lengths
- Display price information for input and output
Product Details
This website provides performance metrics for API services provided by common model providers in China, including detailed data such as TTFT (first token latency), TPS (number of tokens output per second), total time consumption, context length, and input-output prices. It provides developers and enterprises with a basis for evaluating the performance of different large models, helping them choose the model service that best suits their needs.
