AI Glossary

Streaming

What does “Streaming” mean?

Streaming: Sending a model's reply to the user piece by piece as it is generated, rather than waiting for the whole answer. It doesn't make the total response faster, but people see text appear almost immediately, which makes apps feel more responsive.

Streaming visual guide: Sending a model's reply to the user piece by piece as it is generated, rather than waiting for the whole answer. It doesn't make the total response faster, but people see text appear almost immediately, which makes apps feel more responsive.
Visual guide Open full size (new tab)

What is an example of “Streaming”?

Chat apps that show words appearing as you watch are streaming the model's output.

Keep learning

See also

LatencyTermAPITermTokenTermAutoregressive modelTerm

Same topic

Structured outputTermSemantic searchTermSystem promptTermRetrieval-augmented generationTermTemperatureTerm