streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
Why it matters
Spark 2.0 adds level-of-detail streamingSending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.Full definition → so multi-million splat scenes render in a browser on phones, laptops and VR headsets using WebGL2, which is what makes AI-generated 3D worlds shippable without WebGPU or a native app.
