Dedicated Inference lets you run Large Language Models (LLMs) on Exoscale GPU infrastructure.

Read more
Operations quick access
GET /ai/help/inference-engine-parameters GET /ai/model POST /ai/model POST /ai/deployment/{id}/scale GET /ai/deployment POST /ai/deployment GET /ai/deployment/{id} DELETE /ai/deployment/{id} GET /ai/model/{id} DELETE /ai/model/{id} GET /ai/deployment/{id}/api-key GET /ai/deployment/{id}/logs