Together AI

2026Together AIfree

Together Link

vBeta
AI Development
Coding Agents

Together Link is a tool that connects popular coding agents and desktop applications to models hosted by Together AI. It enables users to run tools like Claude Code, Codex, OpenCode, Pi Code, Claude Desktop, and ChatGPT Desktop with high-performance open-source models while maintaining their existing configurations.

Automatic model routing for optimized performance and cost
Support for Claude Code, Codex, OpenCode, Pi Code, Claude Desktop, and ChatGPT Desktop
Headless mode for automated script and agent integration
versionBeta
regionUnited States
2026Together AIopen source

DSGym

v1.0
AI Agents
Agentic AI

DSGym is a comprehensive framework designed to evaluate and train data science agents within self-contained execution environments. It offers a modular architecture that facilitates the addition of tasks, agent scaffolds, and tools, positioning it as a live, extensible testbed for data science agents.

Modular architecture for easy addition of tasks and tools
Holistic task suite standardizing existing benchmarks
Support for diverse scientific domains and file types
pricingFree
version1.0
2026Together AIopen source

ThunderAgent

AI Infrastructure
Inference Optimization

ThunderAgent is a program-aware scheduling system designed to optimize high-throughput agentic inference. By treating agentic workflows as schedulable programs rather than independent requests, it effectively eliminates KV cache thrashing and improves multi-node scaling.

Program-level scheduling to eliminate KV cache thrashing
Global waiting queue for efficient multi-node load balancing
Drop-in compatibility with OpenAI-compatible inference backends
pricingFree
regionUnited States
2026Together AIpaid

Together AI Voice Finder

vinitial release
Text-to-Speech
TTS

A developer tool to search, filter, and audition over 600 text-to-speech voices across leading TTS models using natural-language prompts or audio samples, making it easy to find the perfect voice for any application.

Search and filter 600+ voices across leading TTS models with natural language prompts or audio samples
Audition voices in-browser before committing to an API call
Integrated directly with Together AI inference API for seamless TTS model access
versioninitial release
regionUnited States