# What Tinker handles during model fine-tuning

> Thinking Machines provides training infrastructure while researchers control the data and training logic.

Source: https://fullbytedeveloper.com/blog/tinker-managed-model-training-api
Originally posted: 2025-10-04
Published here: 2026-11-06

Thinking Machines Lab introduced Tinker on 2025-10-01 as an API for fine-tuning language models. Researchers control their algorithms and data while the service handles distributed training infrastructure, scheduling and recovery. [1]

## Decide what you need to control

The launch described support for open-weight models of different sizes, including mixture-of-experts models. A managed training service can remove infrastructure work while leaving the researcher responsible for the experiment itself. [1]

Before a run, define the behavior you want to change and keep evaluation examples separate from training examples. Record the starting model, data preparation and evaluation criteria so a later result can be compared with the original.

Tinker's launch establishes the service's intended division of responsibilities. It does not guarantee that a fine-tuned model will improve on your task. Check current model support, data terms and pricing before sending a dataset or starting a paid run.

## Sources

1. [Thinking Machines Tinker announcement](https://thinkingmachines.ai/news/announcing-tinker/)

## Original posts

- [Instagram post](https://www.instagram.com/fullbytedeveloper/p/DPZaSXcjJ0s/)