Engine

Reload a llama-server-backed model

Reloads the model bound to configId with a new context-window hint. Used by the live config-apply path so a contextWindowOverride or modelId edit on a local config is observed by the next chat turn. Only applies to llama-server configs — cloud / Ollama / Apple configs return 400. Body n_ctx overrides the stored ceiling for this reload.

post/v1/models/reload

Request

  • Base URL: http://localhost:9998
  • URL: http://localhost:9998/v1/models/reload
  • Auth: HTTP bearer

Request body

configIdstring required

EndpointConfig ID to reload

n_ctxinteger

Context window size override for this reload (positive integer)

Response

Model reloaded

modelIdstring required
oktrue required

Changes

No recorded changes to this operation across all 1 revision of this API.