Leina 
Wanta 
Generate a chat answer
Call the selected model with your messages.
/oo OrcaRouter: Use OrcaRouter model [model ID] to answer these messages [messages], then summarize the returned response.
Connect OrcaRouter to Your AI Agent
Ask your AI assistant to work with OrcaRouter: generate Chat Responses and Embeddings.
4 tools API key
Try a OrcaRouter Task
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
oo Skill OrcaRouter
Generate text vectors
Create embeddings for supplied inputs using a chosen model.
/oo OrcaRouter: Create embeddings with OrcaRouter model [embedding model ID] for [input texts] and return the vectors.
Start Working with OrcaRouter
-
Install OOMOL
Set up oo CLI and the oo Skill in your agent.
Install OOMOL → -
Connect OrcaRouter
Connect using your OrcaRouter API Key.
Connect OrcaRouter → -
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
- An account with access to the OrcaRouter resources used in your task.
OrcaRouter Tools
OrcaRouter exposes model listings, chat completions, Anthropic-format messages, and embeddings through your API key.
Generate a chat answer
Call the selected model with your messages.
Generate text vectors
Create embeddings for supplied inputs using a chosen model.
4 tools
Create Chat Completion
Create an OrcaRouter chat completion through the OpenAI-compatible `/chat/completions` endpoint.
orcarouter.create_chat_completion Create Message
Create an OrcaRouter Anthropic-format message through the `/messages` endpoint.
orcarouter.create_message List Models
List the models available through OrcaRouter.
orcarouter.list_models Create Embeddings
Create embeddings through the OpenAI-compatible `/embeddings` endpoint.
orcarouter.create_embeddings No matching tools.
Frequently Asked Questions
Can I discover model IDs?
list_models returns models available through OrcaRouter.
Can I use Anthropic-format messages?
create_message accepts model, max_tokens, and messages for the /messages endpoint.
Does creating embeddings store a searchable knowledge base?
The action returns embeddings; storing and indexing them requires a separate system.