Event-driven channels

Replicate

Replicate lets you run machine learning models in the cloud with a simple API. Thousands of open-source models are available, and you can run your own custom models at scale. Run image generation, language models, audio synthesis, video generation, and more with a few lines of code. Replicate makes

2 channels across 1 AsyncAPI spec · Provider profile

Channels

predictions.stream

SSE stream of a single prediction's output. Returned per-prediction at `urls.stream` when the model supports streaming. Three event types are emitted: `output` (plain text, token/chunk-by-chunk), `err

Replicate Streaming and Webhooks API
webhooks.prediction

Outbound webhook callbacks for a prediction. Which of the four event types fire is controlled by the prediction's `webhook_events_filter` array (`start`, `output`, `logs`, `completed`). Default behavi

Replicate Streaming and Webhooks API