passdrill
AI & LLM Engineering · Building with LLM APIs · Card 002/012 easy

Many LLM provider APIs offer a "streaming" mode for text generation, typically implemented over Server-Sent Events (SSE). What does enabling streaming change about how a client receives the model's output?

  1. The client receives the complete response in a single payload, but compressed with gzip to reduce total bandwidth compared to a non-streaming request
  2. The model generates its answer in a single internal pass regardless of the setting; streaming only changes how the response is logged on the provider's servers, not how the client receives it
  3. The client receives the response as a sequence of incremental chunks over an open connection as tokens are generated, rather than waiting for generation to finish before anything is returned
  4. The client must poll a separate status endpoint at fixed intervals to check whether generation has completed, since no data is returned until the full response is ready
Next card → Shuffle