Leina 
Wanta Draft and compare responses
Ask available models to summarize notes or draft a reply.
/oo LiteLLM: List my available models, then use [model] to summarize these notes and draft a customer reply: [notes].
Connect LiteLLM to Your AI Agent
Choose a model, draft a response, or turn text into vectors while checking the limits available to your key.
6 tools API key
Try a LiteLLM Task
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
oo Skill LiteLLM
Generate text vectors
Create embeddings for text comparison or a downstream search workflow.
/oo LiteLLM: Use [embedding model] to generate vectors for these passages: [text].
Check model limits and spending
Compare model capabilities and pricing, then inspect the key’s remaining budget.
/oo LiteLLM: Show the context limits and prices of my chat models, then report the spend and remaining budget for this key.
Start Working with LiteLLM
-
Install OOMOL
Set up oo CLI and the oo Skill in your agent.
Install OOMOL → -
Connect LiteLLM
Connect a publicly reachable gateway with a LiteLLM key.
Connect LiteLLM → -
Give Your Agent a Task
Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →
Choose Your Agent
- A publicly reachable LiteLLM gateway URL.
- A virtual key or proxy master key from your gateway administrator.
- Inference uses the gateway’s upstream model accounts. Streaming and private-network gateways are not supported here.
- Key budget queries require a virtual key; permissions depend on your gateway configuration.
LiteLLM Tools
Connect your LiteLLM gateway to use chat and message models, generate embeddings, compare model capabilities and prices, and inspect key spending.
Generate content and vectors
Call chat, message, and embedding models.
Inspect model access and budgets
Read model names, capabilities, pricing, and virtual-key spending.
6 tools
Create Chat Completion
Create a chat completion through the LiteLLM proxy's OpenAI-compatible `/v1/chat/completions` endpoint. LiteLLM routes the request to whichever upstream provider serves the model, with its load balancing, fallbacks, and budget checks applied.
litellm.create_chat_completion Create Message
Create an Anthropic-format message through the LiteLLM proxy's `/v1/messages` endpoint, for any model the proxy serves.
litellm.create_message Create Embedding
Create embeddings through the LiteLLM proxy's OpenAI-compatible `/v1/embeddings` endpoint.
litellm.create_embedding List Models
List the model names this LiteLLM key can call.
litellm.list_models Get Model Info
Read the context window, output limit, per-token pricing, and capabilities LiteLLM reports for each model deployment, so an agent can pick a model before calling it.
litellm.get_model_info Get Key Info
Read the spend, remaining budget, rate limits, and allowed models of the LiteLLM virtual key used by this connection. The proxy master key has no stored record, so this action needs a virtual key.
litellm.get_key_info No matching tools.
Frequently Asked Questions
Can I use a master key?
Yes for inference and model queries. Use a virtual key to inspect its stored budget record.