Streaming
Token streaming via SSE
What is streaming?
Streaming means the model sends its response token by token as it generates, rather than waiting until the entire response is complete. This dramatically improves perceived latency — the user sees output appearing immediately. For chatbot interfaces, streaming is essential for user experience. For batch processing, it is unnecessary overhead.
Why it matters
For any user-facing application, streaming is the difference between a 3-second blank wait and immediate character-by-character response. The total generation time is the same — but the perceived latency drops to near-zero. For APIs and batch processing, streaming adds unnecessary overhead. sourc.dev tracks streaming support because it determines which models are suitable for real-time applications.
Where models stand
No data available yet for this metric.
How sourc.dev tracks this
sourc.dev verifies streaming manually from official provider documentation, API responses, and published specifications. Every data point includes a source URL and verification date. When a value changes, the old value is preserved in the history table and the new value is recorded alongside it. Nothing is overwritten — the full timeline is always available.
sourc.dev verifies this attribute manually from provider documentation. Every data point includes a source URL and verification date. Changes are recorded in the history table — nothing is overwritten.
This attribute is verified periodically against provider documentation. When sourc.dev detects a change, the new value is recorded alongside the old one with full provenance.
Understanding streaming helps developers make informed decisions when choosing between models and providers. Rather than relying on marketing claims, sourc.dev provides verified, dated, source-linked data so the data decides.