Together AI
2.9K posts
@togethercompute
Accelerate inference, model shaping, and pre-training on a research-optimized platform.
We @togethercompute believe intelligence should be abundant, not expensive. Today we announced our Series C funding of $800m @ $8.3B valuation, to continue to build the world's most efficient platform for generative AI. Thanks @nikogallogly for telling our story in @nytimes! shorturl.at/SooOP
Big day for Ollama! When we started, open models and the open source AI ecosystem were in their early days with few believers. Our belief in open source has never wavered. With today's fundraising announcement and our 9M+ active builders, we’re ready to scale open models into AI that you can own. All aboard open models! 🧵
We're introducing Provisioned Throughput: reserved inference capacity for frontier open models, with token-based pricing and a 99% uptime SLA. Serverless simplicity, guaranteed capacity, up to 90% lower cost vs. Opus 4.8. Get started with MiniMax M3 + GLM-5.2, read more 🧵
AI that responds in under 100ms doesn't happen by accident. @togethercompute VP of Kernels @realDanFu shares how they use NVIDIA CUDA, TensorRT-LLM, Dynamo and Together ATLAS on NVIDIA Blackwell to power ultra-low-latency inference and long context code generation for @cursor_ai. From building megakernels that fuse an entire model's forward pass into a single launch to enabling real-time voice agents, Together AI is optimizing latency at every layer of the stack.
Palantir CEO Alex Karp on what customers actually want, the real business of frontier labs, and the importance of open source models: “What the technical customers want is control over their compute, their models, their data stack, and their alpha. They want to know they own the means of production, and it's not being transferred to someone else.” "Who owns the data? Are the prompts secure? Is this being transferred to you?" "If it was so valuable, and I can make you a billion dollars, wouldn't I say I'll make you a billion dollars and I want 30%? Why are they charging for tokens if it's so valuable?"
Full slides for our 2 hr inference engines deepdive from AI Engineer World's Fair 2026 👇 We cover: > the lifetime of a request > how the enginecore works > how GPU workers function > parallelism configs > spec decoding
Deepdive: Sonnet 5 and GLM-5.2 on DeepSWE > both max reasoning effort > on full DeepSWE benchmark 113 original long-horizon SWE tasks > 4 trials each This is the what the trajectories show 👇(1/n)🧵
