---
title: "Not supported -- updating a runtime LLM is disabled (admin)."
method: PUT
path: "/llm-registry/admin/runtime-models/{id}"
tags: ["LLM Registry"]
deprecated: true
---

# Not supported -- updating a runtime LLM is disabled (admin).

`PUT /llm-registry/admin/runtime-models/{id}`

## Request

- Base URL: `https://h2ogpte.genai.h2o.ai/api/v1`
- URL: `https://h2ogpte.genai.h2o.ai/api/v1/llm-registry/admin/runtime-models/{id}`
- Auth: HTTP bearer
- TypeScript: <https://skmtc.dev/h2o/apis/h2ogpte-rest-api/docs/llm-registry/admin/runtime-models/:id/put.ts> (a function with typed inputs; its response is checked against the schema)

> **Deprecated.**

Disabled: a runtime LLM can only be created and deleted. Any request returns 400 -- delete the model and create it again to change its configuration. display_name is the routing key at the serving proxy, so an in-place edit can leave a saved, successfully probed model whose every request fails at the proxy. Admin only.

## Path parameters

- `id` string, required

## Response `default`

Unexpected error

- EndpointError
  - `code` integer, required: Error code
  - `message` string, required: Error message
  - `error_type` string: Optional machine-readable error category. For model-access failures: "model_access" (the model is genuinely unauthorized or unknown) vs "authorization_unavailable" (the grant lookup itself failed, e.g. a transient DB error). "authorization_unavailable" also accompanies a 503 or 500 whose identity lookup could not verify the caller's API key, as opposed to a 401, which means the key itself was rejected. Omitted for most errors.

## Other responses

- `400`: Bad request
- `401`: Unauthorized - Invalid or missing API key
- `403`: Forbidden

---

[API](https://skmtc.dev/h2o/apis/h2ogpte-rest-api.md) - [All operations](https://skmtc.dev/h2o/apis/h2ogpte-rest-api/llms.txt) - [OpenAPI document](https://skmtc.dev/h2o/apis/h2ogpte-rest-api/revisions/a82a117320f4?raw)