Together AI Blog
105 posts indexed since 2025
Post Details
| Title | Author | Published | Words | HN Pts |
|---|---|---|---|---|
| Build ultra low latency voice AI applications with Together AI and Cartesia … | Together AI | 2025-01-23 | 829 | -- |
| How to deploy DeepSeek-R1 and distilled models securely on Together AI | Together AI | 2025-01-31 | 1,004 | -- |
| Mistral Small 3 API now available on Together AI: A new category … | Together AI | 2025-01-30 | 712 | -- |
| Generate images with specific styles using Flux LoRAs on Together AI | Together AI | 2025-01-27 | 891 | -- |
| Deploy DeepSeek-R1 at scale: Fast, secure serverless APIs and large-scale Together Reasoning … | Together AI | 2025-02-12 | 984 | -- |
| Together AI Achieves 90% Faster BF16 Training with NVIDIA Blackwell Platform and … | Together AI | 2025-02-13 | 1,422 | -- |
| Minions: embracing small LMs, shifting compute on-device, and cutting cloud costs in … | Avanika Narayan*, Dan Biderman*, Sabri Eyuboglu*, Avner May, Scott Linderman, James Zou, Christopher Ré | 2025-02-25 | 1,257 | -- |
| Together AI Announces $305M Series B to Scale AI Acceleration Cloud for … | Together AI | 2025-02-20 | 808 | -- |
| Together AI becomes NVIDIA Cloud Partner to bolster accelerated AI offerings | Together AI | 2025-03-11 | 744 | -- |
| ThunderKittens Now Optimized for NVIDIA Blackwell GPUs | Benjamin Spector, Aaryan Singhal, Dan Fu, Chris Ré | 2025-03-15 | 1,573 | -- |
| On-demand dedicated endpoints: run inference with unmatched price-performance & control at scale | Together AI | 2025-03-13 | 1,191 | -- |
| Introducing Together Instant GPU Clusters Accelerated by NVIDIA GPUs, with Self-Service Provisioning … | Together AI | 2025-03-18 | 800 | -- |
| Together AI Powers Pioneers at GTC: NVIDIA Blackwell GPUs, Instant GPU Clusters, … | Together AI | 2025-03-18 | 1,836 | -- |
| Deploy Leading AI Models Accelerated by NVIDIA NIM on Together AI | Together AI | 2025-03-18 | 744 | -- |
| Introducing Together Chat: use DeepSeek R1 for free, hosted in North America | Hassan El Mghari | 2025-03-24 | 648 | -- |
| Together AI Awarded ClusterMAX™ Gold Rating by SemiAnalysis | Together AI | 2025-03-27 | 973 | -- |
| Together AI partners with Meta to offer Llama 4: SOTA Multimodal MoE … | Together AI | 2025-04-05 | 608 | -- |
| Scaling AI Companions: How Dippy AI Reached Over 4 Million Tokens/Minute with … | Together AI | 2025-04-01 | 1,074 | -- |
| DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level | Michael Luo*, Sijun Tan*, Roy Huang*, Ameen Patel*, Alpay Ariyak*, Qingyang Wu*, Xiaoxiang Shi, Rachel Xin, Colin Cai, Maurice Weber, Ce Zhang, Li Erran Li, Raluca Ada Popa, Ion Stoica | 2025-04-08 | 2,870 | 31 |
| Together Fine-Tuning Platform, Now With Preference Optimization and Continued Training | Anirudh Jain, Ivan Provilkov, Artem Chumachenko, Alex Moldovan, George Grigorev, Gleb Vazhenin, Arsh Zahed, Avner May, Tristan Dubbeld, Max Ryabinin | 2025-04-17 | 1,360 | -- |
| Direct Preference Optimization | Ivan Provilkov, Zain Hasan, Max Ryabinin | 2025-04-17 | 1,472 | 37 |
| Continued Fine-tuning of LLMs | Artem Chumachenko, Zain Hasan, Max Ryabinin | 2025-04-17 | 1,292 | -- |
| Open Deep Research | Together AI | 2025-04-16 | 3,100 | -- |
| Chipmunk: Training-Free Acceleration of Diffusion Transformers with Dynamic Column-Sparse Deltas | Austin Silveria, Soham Govande, Dan Fu | 2025-04-21 | 1,550 | -- |
| Salesforce, Zoom, InVideo Train Faster with Together AI Turbocharged with NVIDIA Blackwell | Together AI | 2025-04-24 | 1,145 | -- |
| Together AI acquires Refuel.ai to unlock data for developers and businesses building … | Together AI | 2025-05-15 | 792 | -- |
| Together Code Sandbox: the most robust infrastructure for building AI coding products … | Together AI | 2025-05-20 | 920 | 1 |
| Together Code Interpreter: execute LLM-generated code seamlessly with a simple API call | Together AI | 2025-05-20 | 946 | -- |
| Introducing Together Code Sandbox & Together Code Interpreter: SOTA code execution for … | Together AI | 2025-05-20 | 1,112 | -- |
| Boosting DeepSeek-R1’s Speed with Customized Speculative Decoding | Wai Tong Chung, Dan Waters, Avner May, Ben Athiwaratkun | 2025-05-12 | 1,284 | -- |
| FLUX.1 Kontext models: Character consistency and precise image editing without fine-tuning | Together AI | 2025-05-29 | 734 | -- |
| From AWS to Together Dedicated Endpoints: Arcee AI's journey to greater inference … | Together AI | 2025-05-05 | 1,448 | -- |
| Mixture-of-Agents Alignment: Harnessing the Collective Intelligence of Open-Source LLMs to Improve Post-Training | Junlin Wang, Roy Xie, Shang Zhu, Jue Wang, Ben Athiwaratkun, Bhuwan Dhingra, Shuaiwen Leon Song, Ce Zhang, James Zou | 2025-05-28 | 1,394 | -- |
| Model-Preserving Adaptive Rounding with YAQA | Albert Tseng, Zhaofeng Sun, and Chris De Sa | 2025-06-05 | 2,091 | -- |
| How to Build a Coding Agent from Scratch: A Practical Guide for … | Zain Hasan | 2025-06-12 | 1,060 | -- |
| Introducing the Together AI Batch API: Process Thousands of LLM Requests at … | TOGETHER AI | 2025-06-11 | 637 | -- |
| The Frontier is Open | Charles Zedlewski | 2025-06-09 | 1,351 | 1 |
| Bringing 100,000 GPUs to Europe | Together AI | 2025-06-12 | 731 | -- |
| Announcing the Together AI Startup Accelerator, purpose-built for AI Native Apps | Deveaux Barron, Prem Prakash | 2025-10-15 | 671 | -- |
| Together AI delivers fastest inference for the top open-source models | Jue Wang, Wai Tong Chung, Chenxi Li, Chandra Mourya, John Heo, Shirley Wu, Alaskar Alizada, Rupert Wu, Roy Yuan, Pragaash Ponnusamy, Ben Athiwaratkun, Leon Song | 2025-12-01 | 870 | -- |
| How to choose the right open model for production | Nicholas Broad, Dan Waters | 2026-01-08 | 1,617 | -- |
| Fine-Tuning Platform Upgrades: Larger Models, Longer Contexts, Enhanced Hugging Face Integrations | Artem Chumachenko, Maksim Abraham, Soroush Bassam, Gleb Vazhenin, Egor Timofeev, Conner Manuel, Zain Hasan, Will Van Eaton, Max Ryabinin | 2025-09-10 | 1,410 | -- |
| Together Evaluations: Benchmark Models for Your Tasks | Ivan Provilkov, Ruslan Khaidurov, Kirah Sapong, George Grigorev, Gleb Vazhenin, Yogish Baliga, Zain Hasan, Max Ryabinin | 2025-07-28 | 1,176 | -- |
| Transform OpenAI gpt-oss Models into Domain Experts with Together AI Fine-Tuning | Maksim Abraham, Conner Manuel, Eddie Hou, Will Van Eaton, Max Ryabinin | 2025-08-19 | 635 | -- |
| Announcing General Availability of Together Instant Clusters, offering ready to use, self-service … | Nikitha Suryadevara, Clark Zinzow, Ryan Pollock | 2025-09-09 | 1,061 | -- |
| Announcing native availability of NVIDIA Nemotron 3 Nano, NVIDIA's latest reasoning model | Together AI | 2025-12-15 | 515 | -- |
| Expanding Together AI Model Library into multimedia generation with 40+ new image … | Justin Driemeyer, Necoline Hubner, Derek Petersen, Blaine Kasten, Rishabh Bhargava, Sonny Khan | 2025-10-21 | 903 | -- |
| Powering Secure AI: Together AI Achieves SOC 2 Type 2 Compliance | Derek Chamorro, Head of Security, Together AI | 2025-07-08 | 325 | -- |
| Rime voice models now available on Together AI | Arielle Fidel, Rajas Bansal, Sahil Yadav, Rishabh Bhargava, Sonny Khan | 2025-12-18 | 1,231 | -- |
| Back to The Future: Evaluating AI Agents on Predicting Future Events | Federico Bianchi, Junlin Wang, Zain Hasan, Shang Zhu, Roy Yuan, Clémentine Fourrier, James Zou | 2025-07-17 | 1,867 | -- |
| Inside multi-node training: How to scale model training across GPU clusters | Andrew Way, Gagan Gill | 2026-01-12 | 979 | -- |
| FLUX.2: Multi-reference image generation now available on Together AI | Necoline Hubner, Sonny Khan, Rishabh Bhargava | 2025-11-25 | 849 | -- |
| Announcing the fastest inference for realtime voice AI agents | Rajas Bansal, Sahil Yadav, Garima Dhanania, Sri Yanamandra, Charles Zedlewski, Zain Hasan, Derek Petersen, Blaine Kasten, Sonny Khan, Rishabh Bhargava | 2025-11-04 | 1,148 | -- |
| DeepSWE: Training a Fully Open-sourced, State-of-the-Art Coding Agent by Scaling RL | Michael Luo*, Naman Jain*, Jaskirat Singh*, Sijun Tan*, Ameen Patel*, Qingyang Wu*, Alpay Ariyak*, Colin Cai*, Tarun Venkat, Shang Zhu, Ben Athiwaratkun, Manan Roongta, Ce Zhang, Li Erran Li, Raluca Ada Popa, Koushik Sen, Ion Stoica | 2025-07-02 | 3,655 | -- |
| How Together AI Uses AI Agents to Automate Complex Engineering Tasks: Lessons … | Shang Zhu, Federico Bianchi, Wai Tong Chung, Zain Hasan, Rupert Wu, Ce Zhang, James Zou, Ben Athiwaratkun | 2025-08-21 | 2,208 | -- |
| Together AI welcomes Mahadev Konar as SVP for Infrastructure Engineering | Vipul Ved Prakash | 2025-09-10 | 479 | -- |
| How to Build a State-of-the-Art Search Stack for LLMs: RAG, Reranking, and … | Together AI | 2026-01-13 | 725 | -- |
| Announcing Together Python SDK v2.0 | Blaine Kasten, Zain Hasan | 2025-12-12 | 1,369 | -- |
| Large Reasoning Models Fail to Follow Instructions During Reasoning: A Benchmark Study | Yongchan Kwon, Shang Zhu, Federico Bianchi, Kaitlyn Zhou, James Zou | 2025-10-22 | 2,221 | -- |
| Improved Batch Inference API: Enhanced UI, Expanded Model Support, and 3000Ã Rate … | Rajas Bansal, Mitali Meratwal, Nikitha Suryadevara, Will Van Eaton, Rishabh Bhargava | 2025-09-15 | 374 | -- |
| How to evaluate and benchmark Large Language Models (LLMs) | Zain Hasan | 2025-11-04 | 2,180 | -- |
| Dynamic AI agent testing for the real world with Collinear Simulations and … | Anand Kumar, Muyu He, Nazneen Rajani, Zain Hasan, Ivan Provilkov | 2025-10-28 | 589 | -- |
| Together AI and Meta partner to bring PyTorch Reinforcement Learning to the … | Together AI Training and Research, The PyTorch team at Meta | 2025-12-03 | 305 | -- |
| DeepSeek-V3.1: Hybrid Thinking Model Now Available on Together AI | Together AI | 2025-08-27 | 650 | -- |
| Together AI Delivers Top Speeds for DeepSeek-R1-0528 Inference on NVIDIA Blackwell | Together AI | 2025-07-17 | 1,527 | -- |
| Research POV: Yes, AGI Can Happen – A Computational Perspective | Together AI | 2025-12-17 | 252 | -- |
| How to run TorchForge reinforcement learning pipelines in the Together AI Native … | Together AI Training and Research, The PyTorch team at Meta | 2025-12-03 | 546 | -- |
| Introducing AutoJudge: Streamlined inference acceleration via automated dataset curation | ROMAN GARIPOV, FEDOR VELIKONIVTSEV, IVAN ERMAKOV, RUSLAN SVIRSCHEVSKI, VAGE EGIAZARIAN, MAX RYABININ | 2025-12-03 | 1,077 | -- |
| OpenAI's New Open gpt-oss Models vs o4-mini: A Real-World Comparison | Hassan El Mghari | 2025-08-11 | 810 | -- |
| Together AI Launches Speech-to-Text: High-Performance Whisper APIs | Rajas Bansal, Rishabh Bhargava, Sonny Khan | 2025-07-10 | 592 | -- |
| Qwen3-Coder: The Most Capable Agentic Coding Model Now Available on Together AI | Together AI | 2025-07-25 | 643 | -- |
| Fine-Tuning Small Open-Source LLMs to Outperform Large Closed-Source Models by 60% on … | Charles O'Neill, Mudith Jayasekara, David Nugent, James Zou | 2025-08-15 | 1,571 | -- |
| MiniMax Speech 2.6 Turbo now available natively on Together AI | Arielle Fidel, Rajas Bansal, Sahil Yadav, Rishabh Bhargava, Sonny Khan | 2025-12-23 | 1,248 | -- |
| VirtueGuard: Enterprise-Grade AI Security and Safety Now on Together AI | Together AI | 2025-07-29 | 608 | -- |
| From Zero to One: Building An Autonomous and Open Data Scientist Agent … | Federico Bianchi, Shang Zhu, Zain Hasan, Ben Athiwaratkun and James Zou | 2025-06-12 | 3,316 | -- |
| Announcing the Availability of OpenAI's Open Models on Together AI | Vipul Ved Prakash | 2025-08-05 | 1,010 | -- |
| Kimi K2: Leading Open-Source Model Now Available on Together AI | Together AI | 2025-07-14 | 910 | -- |
| AdapTive-LeArning Speculator System (ATLAS): A New Paradigm in LLM Inference via Runtime-Learning … | Junxiong Wang, Shirley Wu, Zelei Shao, Vikranth Srivatsa, Jue Wang, Roy Yuan, Qingyang Wu, Alpay Ariyak, Rupert Wu, Wai Tong Chung, Chenfeng Xu, Yonatan Oren, Pragaash Ponnusamy, Yineng Zhang, Avner May, Leon Song, Tri Dao, Percy Liang, Ce Zhang, Ben Athi | 2025-10-10 | 2,048 | -- |
| Learn how Cursor partnered with Together AI to deliver real-time, low-latency inference … | Dan Fu, Ingrid Xu, Ce Zhang, Cyrus Lalkaka, Sonny Khan | 2026-01-13 | 683 | -- |
| Optimizing inference speed and costs: Lessons learned from large-scale deployments | David Nugent, Ingrid Xu | 2026-01-22 | 1,234 | -- |
| DSGym: A holistic framework for evaluating and training data science agents | Fan Nie, Junlin Wang, Harper Hua, Federico Bianchi, Yongchan Kwon, Zhenting Qi, Owen Queen, Shang Zhu, James Zou | 2026-01-26 | 1,270 | -- |
| Together Evaluations now supports comparing top commercial APIs vs. open source models | Ivan Provilkov, Conner Manuel, Kirah Sapong, Ruslan Khaidurov, Jasmine Li, Zain Hasan, Jennifer Wu, Max Ryabinin | 2026-02-02 | 634 | -- |
| Fine-tuning open LLM judges to outperform GPT-5.2 | Zain Hasan, Jasmine Li, Ivan Provilkov | 2026-02-02 | 2,468 | -- |
| Together AI welcomes Alon Gavrielov as VP of Infrastructure Strategy | Vipul Ved Prakash | 2026-02-03 | 476 | -- |
| Rime Arcana V3 Turbo and Rime Arcana V3 now available on Together … | Sahil Yadav, Arielle Fidel, Rajas Bansal, Rishabh Bhargava, Sonny Khan | 2026-02-04 | 886 | -- |
| TogetherCoder-Preview: SOTA Open Dataset for Training Efficient Agents | Alpay Ariyak*, Junda Zhang, Junxiong Wang, Shang Zhu, Federico Bianchi, Sanjana Srivastava, Ashwinee Panda, Siddhant Bharti, Chenfeng Xu, John Heo, Xiaoxia Shirley Wu, James Zhou, Percy Liang, Leon Song, Ce Zhang, Ben Athiwaratkun, Zhongzhu Zhou*, Qingyan | 2026-02-05 | 3,143 | -- |
| What do LLMs think when you don't tell them what to think … | Yongchan Kwon and James Zou | 2026-02-06 | 1,143 | -- |
| Cache-aware disaggregated inference for long-context LLM serving | Jiejing Zhang, Yubo Wang, Yinghui Liu, Mourya Vangala Srinivasa, Chenxi Li, Jue Wang, Yineng Zhang, Shuaiwen Leon Song, Ce Zhang | 2026-02-11 | 1,975 | -- |
| Introducing Dedicated Container Inference: Delivering 2.6x faster inference for custom AI models | Sylvie Liberman, Rasul Nabiyev, Mohamad Rostami, Dulaj Disanayaka, Will Van Eaton, Nikitha Suryadevara | 2026-02-12 | 952 | -- |
| Consistency diffusion language models: Up to 14x faster inference without sacrificing quality | Minseo Kim, Chenfeng Xu, Coleman Richard Charles Hooper, Harman Singh, Ben Athiwaratkun, Ce Zhang, Kurt Keutzer, Amir Gholami | Seoul National University, University of California, Berkeley, Together AI | 2026-02-19 | 1,316 | -- |
| How speech models fail where it matters the most and what to … | Kaitlyn Zhou, Martijn Bartelds, Federico Bianchi, James Zou | 2026-02-23 | 983 | -- |
| CoderForge-Preview: SOTA open dataset for training efficient coding agents | Alpay Ariyak*, Junda Zhang, Junxiong Wang, Shang Zhu, Federico Bianchi, Sanjana Srivastava, Ashwinee Panda, Siddhant Bharti, Chenfeng Xu, John Heo, Xiaoxia Shirley Wu, James Zou, Percy Liang, Leon Song, Ce Zhang, Ben Athiwaratkun, Zhongzhu Zhou*, Qingyang | 2026-02-25 | 3,083 | -- |
| Key research and product announcements at the AI Native Conf | Together AI | 2026-03-05 | 2,407 | -- |
| FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling | Together AI | 2026-03-05 | 3,416 | -- |
| Introducing Together AI’s new look | Together AI | 2026-03-05 | 1,372 | -- |
| Best practices to accelerate inference for large-scale production workloads | Together AI | 2026-03-05 | 4,850 | -- |
| Optimizing Training Workloads for GPU Clusters | Together AI | 2026-03-05 | 1,805 | -- |
| New in Together GPU Clusters: Autoscaling, observability, and self-healing | Together AI | 2026-03-11 | 1,799 | -- |
| Together AI Brings NVIDIA Nemotron 3 to Developers on Day 0 | Together AI | 2026-03-11 | 1,674 | -- |
| Build real-time voice agents on Together AI | Together AI | 2026-03-13 | 1,796 | -- |
| Together AI at NVIDIA GTC 2026: Explore our latest innovations across research … | Together AI | 2026-03-17 | 1,618 | -- |
| Mamba-3 | Together AI | 2026-03-18 | 4,544 | -- |
| Together AI expands fine-tuning service with tool calling, reasoning, and vision support | Together AI | 2026-03-19 | 2,889 | -- |
| Divide, conquer, and plan: How weaker models beat GPT-4o on long context … | Together AI | 2026-03-25 | 2,606 | -- |
| Plan, divide, and conquer: How weak models excel at long context tasks | Together AI | 2026-03-27 | 2,607 | -- |