Send a query to multiple models in parallel and combine results using a configurable resolution strategy (summary, fast, multiple_choice).
API key authentication. Pass your API key as a Bearer token.
The question or prompt sent to all models
Models to query in parallel
Literal options for multiple_choice resolution
Per-model retry count on transient errors (default 1 / max 3)
JSON Schema for structured output — applied to all model calls and the consolidation call
Resolution mode: summary (default) / fast / multiple_choice
Enable SSE streaming
Override the model used for consolidation in summary mode