Preguntas frecuentes

Image, video and music models run as asynchronous tasks: POST /api/v1/jobs returns immediately with a task ID, and you poll GET /api/v1/jobs/{id} until a terminal status. Language models are synchronous through POST /api/v1/chat/completions.

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and your Hermes key as the API key. Chat completions, streaming, tools and JSON output work unchanged; pick a model id from GET /api/v1/chat/models.

Cada pocos segundos. El playground web consulta cada 4 segundos. Detente en succeeded, failed o reconciliation_required.

Reintenta con la misma Idempotency-Key y el mismo cuerpo. Si la tarea se aceptó, la recibirás de nuevo (200, replayed: true) sin un segundo cargo.

Check that the model is available and your balance covers the task price. The error code explains why a request cannot run.

Open Billing in the console to buy credits and view your balance, payments and usage. Credits become available after payment confirmation.

Súbelos con POST /api/v1/media y coloca la referencia media:<uuid> devuelta en el campo de imagen o vídeo del modelo. Las URL HTTPS públicas también funcionan.