@togethercompute

Accelerate inference, model shaping, and pre-training on a research-optimized platform.

 San Francisco, CA
together.ai
Joined November 2022
  • Tweets3.2K
  • Following277
  • Followers64.7K
978Media

Together Post-Training: frontier-grade model shaping, the way that fits you

We are introducing Together Post-Training, a new service for building custom models on our platform — both from environment rewards via RL and supervision data via SFT. This service is designed to g…

Article · @togethercompute
21
38
9
340
209,874

How a global fintech scaled coding agent traffic with Dedicated Model Inference

This customer ships financial products to millions of users across dozens of markets, and growth shows no sign of slowing. Sustaining that pace is an engineering problem before anything else, and the …

Article · @togethercompute
3
2
1
16
6,945

Migrating from closed to open source models, Together

TL;DR: A practical, five-stage playbook for moving from closed models to open source models: discover, evaluate, adapt, decide, and take it to production.

Article · @togethercompute
12
5
6
47
16,118

The Open Source AI Stack

As the quality of open source models have bridged the gap with closed source models, a lot of developers and organizations are looking to move to open source models for more ownership, control and eco…

Article · @togethercompute
27
15
7
79
32,104
The Washington Post processed 1.79B input tokens per month through Together AI, running open models like Llama and Mistral in production with predictable costs and full control over the model stack.

How The Washington Post Achieved AI Independence with Together

The Washington Post serves millions of users with award-winning journalism for all of America while pioneering AI innovation. Under CTO Vineet Khosla's leadership, The Post launched "Ask The Post AI" …

Article · @togethercompute
1
2
1
16
6,225

What does 99.9% uptime mean for AI inference?

TL;DR

Article · @togethercompute
1
2
16
4,532

How Cartesia Runs Real-Time Voice AI on Together AI

Cartesia’s growth in real-time voice AI created four specific infrastructure requirements that many hosted platforms were not fit for.

Article · @togethercompute
1
1
22
7,461

How Decagon Engineered Sub-Second Voice AI with Together AI

Voice latency is audible. Decagon’s leadership frames voice as the most demanding surface because latency is immediately perceptible. Long pauses create awkward moments, users talk over the agent, o…

Article · @togethercompute
1
3
12
8,866

Learn how Cursor partnered with Together AI to deliver real-time, low-latency inference at scale

Cursor is an AI-powered coding platform with continuous background intelligence, built by a research team that trains agentic coding models and ships them into production. As developers type, Cursor m…

Article · @togethercompute
1
1
33
18,166

Serving MiniMax-M3 on Together AI: sparse attention, paged decode, and multimodal inference

MiniMax-M3 combines three serving challenges in one model: a 1M-token context window, native multimodality, and MiniMax Sparse Attention. Together AI is the preferred cloud partner for MiniMax-M3, ser…

Article · @togethercompute
4
7
5
68
56,755

Serving DeepSeek-V4: why million-token context is an inference systems problem

Benchmark tables miss the main point of DeepSeek-V4: the important change is architectural. V4 turns million-token context into a serving-systems problem.

Article · @togethercompute
14
3
125
40,394

How to Use OpenClaw with Together AI

OpenClaw is the first Jarvis-like agent that actually gets things done — writing and executing scripts, browsing the web, using apps, and managing tasks from Telegram, WhatsApp, or any chat interfac…

Article · @togethercompute
1
1
2,362
Load more