Log inSign up
Vipul Ved Prakash
Together AI
2,692 posts
Image
user avatar
Vipul Ved Prakash
Together AI
@vipulved
Co-founder, CEO @togethercompute
San Francisco, CA
Joined April 2008
1,080
Following
6,561
Followers
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Dec 22, 2023
    When it comes to LLMs, 2023 was the year of Open Source AI. At the end of 2022, the quality delta between best open (Bloom) and closed (GPT-3.5) LLM, as measured by MMLU scores, was 90%. At the end of 2023, this delta between GPT-4 and Mixtral-MoE-7B stands at 13%.
    89K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Jun 30, 2023
    The era of sub-quadratic LLMs is about to begin. At @togethercompute we've been building next gen models with large space state architectures and training them on very long sequences and the results from the recent builds are... incredible. Will share more as we get closer to
    Image
    80K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Aug 22, 2023
    Together.ai API now offers a 32K context model, built with FlashAttention-2 for $0.20 per 1 M tokens. 300x cheaper than closest commercial model at 32K context (GPT-4). Smaller, but for many long context tasks like RAG, it’s excellent. And you can fine tune it.
    71K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Jul 3, 2023
    Now hearing fairly regularly how well RedPajama-INCITE-7B performs across enterprise use cases. Several companies have replaced OpenAI with it, and we will soon announce a new partner who is deploying solutions in regulated industries based on the model. huggingface.co/togethercomput…
    Image
    103K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Aug 17, 2023
    We just got 1024 A100s up and running at @togethercompute!! We are offering short-term dedicated access to AI startups anywhere from 16-128 GPUs. Clusters come pre-configured with distributed training software. Available immediately (while supplies last) 🚀🚀🚀
    66K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Apr 1, 2025
    The @togethercompute inference team achieved another performance milestone. Now serving 140 TPS on 671B param R1 model, ~3x faster than Azure, ~5.5x faster than DeepSeek API on @nvidia GPUs. APIs @ api.together.xyz and chat + web search @ chat.together.ai
    Image
    31K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Jun 14, 2025
    .@togethercompute is building 2 gigawatts of AI factories (~100,000 GPUs) in the EU over the next 4 years with the first phase live in H2 '2025. AI compute is at <1% saturation relative to our 2035 forecast and we are starting early to build a large-scale sustainable AI cloud
    Image
    NVIDIA GPU Clusters: H100, H200, B200, GB200 | Together AI
    From together.ai
    35K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Dec 12, 2023
    OpenAI API compatibility shipped for 100+ models on @togethercompute API. Replace GPT calls with Mixtral or Llama-70B, get faster responses and for less $$ 🚀🚀🚀
    user avatar
    Together AI
    @togethercompute
    Dec 12, 2023
    Transitioning from OpenAI to Mixtral? Simply add your TOGETHER_API_KEY, change the base URL to api.together.xyz, and swap the model name. Oh, and Mixtral Instruct v0.1 is now live on Together API 🙌
    Image
    63K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Nov 22, 2023
    The RedPajama-V2 dataset has been downloaded 1.2M times in the last month on @huggingface. It’s a great metric of the level of agency in core AI development today, and how vast the open source (and custom) AI surface is going to be.
    Image
    togethercomputer/RedPajama-Data-V2 · Datasets at Hugging Face
    From huggingface.co
    59K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Apr 24, 2024
    Llama-3 is Linux.
    22K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Jul 2, 2025
    The first @togethercompute GB200 cluster CDUs imbibing coolant in prep to go live next week! Each rack here is 1.4 exaflops of inference performance!
    Image
    9.9K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Feb 8, 2025
    Rolling out a new inference stack for DeepSeek R1 @togethercompute that gets up to 110 t/s on the 671B parameter model!
    Image
    23K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Dec 22, 2023
    Wow @anyscalecompute is benchmark washing their API’s terrible performance. All you need is curl and time. Same request @togethercompute 3x faster for Llama2 70B model — 72 t/s vs 23 t/s (7.04s vs 21.87s) And this model is under heavy load! Our dedicated instances are
    Image
    Image
    user avatar
    Anyscale
    @anyscalecompute
    Dec 21, 2023
    📈We’re excited to introduce the LLMPerf leaderboard: the first public and open source leaderboard for benchmarking performance of various LLM inference providers in the market. Our goal with this leaderboard is to equip users and developers with a clear understanding of the
    78K
  • user avatar
    Vipul Ved Prakash
    Together AI
    @vipulved
    Jul 18, 2024
    We released Turbo and Lite versions of Llama-3 today that incorporate our latest research in optimization and quantization. Lite models are 6x cheaper than GPT-4o mini, possibly the most cost efficient inference in the world right now. Turbo models provide best
    user avatar
    Together AI
    @togethercompute
    Jul 18, 2024
    Replying to @togethercompute
    Together Lite endpoints provide the lowest cost for Llama 3, making high-quality AI models more affordable than ever, with Llama 3 8B Lite priced at $0.10 per million tokens, 6x lower cost than GPT-4o-mini. Together Lite leverages a number of optimizations including INT4
    26K

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms of Service|Privacy Policy|Cookie Policy|Accessibility|Ads info|© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up