skills.rest
BerriAI
BerriAIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

add-model

Register a new LLM deployment in LiteLLM via POST /model/new and validate routing.

77|12|Updated Mar 14, 2026
Search Tags:#credentials#curl#model-management#provider-integration#litellm#add-model#proxy-management
One-click install
npx skills add https://github.com/BerriAI/litellm-skills --skill add-model-berriai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-model
Source: https://github.com/BerriAI/litellm-skills/tree/main/add-model
Command: npx skills add https://github.com/BerriAI/litellm-skills --skill add-model-berriai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Add a new LLM to a live LiteLLM proxy by guiding through provider selection, deployment naming, and credential entry, then calling POST /model/new and validating routing with a test.

Core Features & Use Cases

  • Guided onboarding: select a provider, specify deployment name, and provide required credentials.
  • Automated provisioning & validation: create the model via POST /model/new and perform a test call to ensure routing works.
  • Multi-provider support: handles major providers (OpenAI, Azure OpenAI, Anthropic, AWS Bedrock, Google Vertex, Ollama, Groq, Together AI, Mistral) with provider-specific parameters.

Quick Start

Provide the public model name, select a provider, supply credentials, and run the add-model workflow to register and verify the model.

Frequently Asked Questions about add-model

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add a new model to a live LiteLLM proxy?▼

To add a new model to a live LiteLLM proxy, you select a provider, specify the deployment name, provide credentials, and POST the payload to /model/new. The workflow then executes a test call to verify chat routing works correctly.

What providers are supported for LiteLLM proxy model management?▼

LiteLLM proxy model management supports multiple providers including OpenAI, Azure OpenAI, Anthropic, AWS Bedrock, Google Vertex, Ollama, Groq, Together AI, and Mistral. Each provider requires specific parameters and credential collection for deployment onboarding.

What credentials do I need to integrate a provider into a LiteLLM proxy?▼

Integrating a provider into a LiteLLM proxy requires a base URL, an admin API key, and a provider deployment identifier. These credentials are collected during the guided onboarding process before sending the POST request to register the model.

Does adding a model to LiteLLM validate routing automatically?▼

Yes, adding a model to LiteLLM validates routing automatically by performing a test call after the POST /model/new request. This ensures the newly registered LLM deployment is correctly routing chat completions before finishing the workflow.

Why is my new model not routing correctly on the LiteLLM proxy?▼

If a new model is not routing correctly on the LiteLLM proxy, the automated test call during the add-model workflow will fail. Verify that your provider credentials, base URL, and deployment name are accurate in the POST /model/new payload.

Related Skills

Explore More Software Engineering Skills→
BerriAIBerriAI
77

update-key

Update existing LiteLLM proxy API keys via POST /key/update.

Official
Intermediate
hung-phanhung-phan
1

litellm

Manage LLM provider interactions through a unified OpenAI-compatible API.

Community
Advanced
BerriAIBerriAI
77

update-user

Update existing LiteLLM proxy users via the POST /user/update endpoint.

Official
Intermediate
BerriAIBerriAI
77

add-mcp

Register MCP servers on a live LiteLLM proxy via POST /v1/mcp/server.

Official
Intermediate