APICHECK / AI TOOLBOX
API Speed Test: Time to First Token and Generation Speed
Measure time to first token, output speed and total duration with real model requests. Inspect each call to evaluate your API connection.
API connection
Open to guestsYour key stays in page memory and is forwarded through our server for requests. It is not saved to a database or browser storage. Refreshing clears it.
API speed test
Sample time to first text, generation speed, and completion rate. Inspect medians and individual request details.
Run settings
Up to 3 calls. Output length follows the model provider defaults. Calls use your API credit. Stop at any time.
Enter your API URL, key, and model above to run this tool.
Results
Ready when you areYour next experiment starts here
Set up your API and run settings, then use the button on the left. Progress and results will appear here.
How to use and interpret results
- Enter an API endpoint and key and select a discovered model.
- Configure a prompt and start the test.
- Compare latency, throughput and completion status for each call.
Measurements include this platform's connection to the upstream API, queueing and generation. This is not a local broadband test. Missing usage affects token-speed metrics; one run cannot establish long-term reliability.

