CREST is a training-free test-time steering framework that discovers cognitive heads via simple offline calibration and then rotates activations during decoding to guide the model’s reasoning—preserving norms to avoid per-model hyperparameter tuning. This improves accuracy and reduces tokens across models and datasets.

Elixir Client for the Stytch B2B SaaS authentication API

Shared modules and utilities for Elixir services at Together

The official Together AI TypeScript library.

Official Together AI Go library

An OpenAPI API specifications file describes an API in its entirety and are typically written in YAML or JSON. including: Endpoints: which are available (/users) and operations on each (GET /users, POST /users) Authentication methods. Operation parameters for each operation (Input and output)

The Official Python Client for Together's API

A collection of notebooks/recipes showcasing usecases of open-source models with Together AI.