Streaming
Two apps use the same model and give the same answer. One feels instant, the other feels broken. The only difference is whether the words appear as they're written.
In this lesson you'll learn to
- Explain why streaming makes apps feel faster, using time to first token and output speed.
- Read a server-sent event stream and name the events that carry text, the stop reason and usage.
- Stream a reply with the SDK and still get the final message, stop reason and token counts.
- Design a streaming UI path that keeps the API key on the server and handles cancel and errors.
Create a free account to open this lesson
It's free. You'll get every free lesson, quizzes that save your progress, daily flashcards and streaks.