BerriAI/delete-modelv1.0

delete-model

Delete a model from a live LiteLLM proxy. Asks for the model name or model_id and confirms before calling POST /model/delete. Use when the user wants to remove, delete, or unregister a model from a LiteLLM proxy instance.

v1.0LATEST

NewUpdated Oct 12, 2026

Delete Model

Remove a model from a live LiteLLM proxy.

Setup

LITELLM_BASE_URL  — e.g. https://my-proxy.example.com
LITELLM_API_KEY   — proxy admin key

Ask the user

Model name or model_id — if they give a name, look up the ID first:

curl -s "$BASE/model/info" -H "Authorization: Bearer $KEY" | python3 -c "
import sys,json
for m in json.load(sys.stdin).get('data',[]):
  print(m['model_info']['id'], m['model_name'])
"

Confirm — show the model name and ask for confirmation before deleting.

Run

curl -s -X POST "$BASE/model/delete" \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{"id": "<model_id>"}'

Output

Show the success message. Warn the user that any keys scoped to this model name will start getting errors.

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

76/100

Grade

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

Quality

Clarity

Completeness

Summary

Skill to delete a model from a live LiteLLM proxy instance. The agent collects the model name/ID from the user, optionally looks up the model ID via GET /model/info, confirms deletion with the user, and executes POST /model/delete with the model ID. The skill is scoped to LiteLLM proxy operations and requires valid admin credentials and base URL to be set.

Detected Capabilities

curl network requestenvironment variable read (LITELLM_BASE_URL, LITELLM_API_KEY)JSON parsing with python3POST request with authorization headeruser interaction / confirmation prompt

Trigger Keywords

Phrases that agents use to match this skill to user intent.

delete litellm modelremove model from proxyunregister proxy modellitellm model cleanupmodel deletion confirm

Risk Signals

WARNING

Environment variable dependency on LITELLM_API_KEY (proxy admin credential)

Setup section

WARNING

POST request to /model/delete endpoint causes destructive state change (model removal)

Run section

INFO

Credential passed via Authorization header in curl command

Run section, curl command

Referenced Domains

External domains referenced in skill content, detected by static analysis.

my-proxy.example.com

Use Cases

Remove an unused or deprecated model from a LiteLLM proxy
Unregister a model after it is no longer needed
Delete a misconfigured model from the proxy
Revoke access by removing a model when keys are scoped to it

Quality Notes

Clear, concise structure with Setup, Ask, Run, Output sections
Explicit user confirmation step documented before delete operation
Helpful lookup mechanism provided to resolve model names to IDs
Setup environment variables clearly documented with examples
Output section warns user about downstream effects (keys scoped to model)
No error handling guidance for failed lookups, network errors, or invalid model IDs
No guidance on how to handle cases where multiple models match a name
Missing documented scope boundaries (is deletion reversible? who can invoke?)
Missing guidance on recovery or rollback procedures

Model: claude-haiku-4-5-20251001Analyzed: Oct 12, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use BerriAI/delete-model in your dev environment — a Developer account adds skills to your library and syncs them via the SkillRepo CLI.

Start a Developer trial