🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I’ll be joining my Baseten colleague Philip Kiely at the AI Engineer World’s Fair AI Engineer in San Francisco, June 3–5, to Introduce LLM serving with SGLang LMSYS Org. We’d love for you to stop by and exchange ideas in person!🤗

Product launch with the backstory: Internally we had always said let's do *1 thing* but do it well. For us that was inference. And we said at some point we'll earn the rights to expand the surface area beyond that. That some point is today. The vast majority of our revenue

🚀 Our "technical" marketer might not be looped in, but today is our biggest launch day yet. We're introducing two new products to serve the inference lifecycle: Model APIs and Training. Model APIs are frontier models running on the Baseten Inference Stack, purpose-built for

We’re working with oxen.ai (moo!) to power model training with robust data management tooling. Learn more here: oxen.ai/entry/fine-tun… We're also partnering with Mixedbread to support their frontier embedding models, and Elias and Amu at Canopy Labs to deliver

Lower Latency. Higher Throughput. Lower Cost.🤗 #DeepSeek #Llama

Excited to be partnering with Baseten to combine oxen.ai's datasets with their multi-node GPU infra 🚀 reach out if you want early access!

Our secret sauce? The Baseten Inference Stack. It consists of two core layers: the Inference Runtime and Inference-optimized Infrastructure. Our engineers break down all the levers we pull to optimize each layer in our new white paper.

Introducing Mirage Studio. Powered by our proprietary omni-modal foundation model. Generate expressive videos at scale, with actors that actually look and feel alive. Our actors laugh, flinch, sing, rap — all of course, per your direction. Just upload an audio, describe the

Impressed by these ultra-realistic, multilingual AI actors — a huge unlock for creative teams scaling content. Congrats to our friends at Captions on launch day!

x.com/i/article/1929…

We’re excited to partner with oxen.ai on their fine-tuning launch. It’s almost too easy — zero-code fine-tuning, from dataset to custom model in a few clicks.

Today we’re excited to introduce Bland TTS, the first voice AI to cross the uncanny valley. Several months ago, our team solved one-shot style transfer of human speech. That means, from a single, brief MP3, you can clone any voice or remix another clone’s style (tone, cadence,

Riffscape

Our customers run AI products where every millisecond and request matter. Over the years, we found fundamental limitations in traditional deployment approaches — single points of failure, regional and cloud-specific capacity constraints, and the operational headache of managing

So in early 2024, we launched our multi-cloud capacity management (MCM) system to address those challenges head-on. Today, it powers production workloads at companies like Writer, Abridge, Patreon, and many more. Our MCM system unlocks: ⏫Active-active routing across 10+

Best of all, you can choose exactly where to run workloads—Baseten Cloud, Self-hosted, or Hybrid—without changing a line of code. Read our post to learn how MCM makes multi-cloud function as one elastic GPU pool → baseten.co/blog/how-baset…

The Redpoint InfraRed 100 is now live! This list honors 100 infrastructure innovators who are transforming how businesses scale, secure, and succeed. Check out this year's honorees and dive deeper with the dynamic list and our complete InfraRed Report linked below.

"Where are your GPUs?" I get this question on sales calls. The answer is 10 different public clouds in 40+ regions. The hard part wasn't acquiring compute; it was using them dynamically to scale a single model across the world. It took us time to build, but the gains are worth

cloud redundacy is necessary...

We're excited to introduce the Baseten Performance Client, a new open-source Python library for up to 12x higher throughput for high-volume embedding tasks! Stand up a new vector database, preprocess text, and run massive workloads in <2 minutes (vs. 15+ with AsyncOpenAI).