Connect Cheaper Inference to Your AI Agent

Choose an available model and give it a clear writing or reasoning task.

3 tools API key

Try a Cheaper Inference Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill Cheaper Inference

Draft from supplied material

Turn notes into a chosen format through an available model.

/oo Cheaper Inference: Check available Cheaper Inference models and use [model ID] to draft [document type] from these notes [notes]. Apply tone [tone], length [length] and required points [points]. Return the complete draft and any source gaps needing my input.

Compare answers to one prompt

Evaluate selected responses against your own task criteria.

/oo Cheaper Inference: Use available Cheaper Inference models [model IDs] to answer this prompt [prompt], using the compatible chat or message request for each. Apply output limit [limit]. Show each answer separately and compare against criteria [criteria], explaining differences in the text without inventing price or speed measurements.

Start Working with Cheaper Inference

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect Cheaper Inference

Connect with a Cheaper Inference API key.
Connect Cheaper Inference →
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

Codex Claude Code Cursor Hermes

Choose a model available to your account and provide the source material or prompt.
Responses are non-streaming. Model availability and accepted options depend on the selected model.

Cheaper Inference Tools

Discover the models available through Cheaper Inference and generate complete responses using chat or message requests. You can draft from supplied material or compare how selected models answer a shared question.

Available models

Read the current model catalog.

Text generation

Generate complete model responses from supplied messages and instructions.

3 tools

Create Chat Completion

Create a Cheaper Inference chat completion through the OpenAI-compatible `/chat/completions` endpoint.

cheaperinference.create_chat_completion

Create Message

Create a Cheaper Inference Anthropic-format message through the `/messages` endpoint.

cheaperinference.create_message

List Models

List the models available through Cheaper Inference.

cheaperinference.list_models

Frequently Asked Questions

How do I choose a model?

Start with the current model catalog and your task requirements. Provide a model ID rather than relying on an assumed model name or version.

Can I request a specific output format?

Yes, describe the desired structure in your prompt. Chat requests also expose response-format options when accepted by the selected model; review the result before using it as structured data.

Do model tool calls execute external actions?

These operations return model responses, including any proposed tool calls. They do not automatically execute external tools.