Baseten's banner

Baseten

@baseten • 22,353 subscribers

Inference is everything.

Shorts

Today, we're releasing GLM-5.3 Fast: one of the most intelligent open-weight models ever at an even higher TPS. Designed for real-time use cases that demand consistent performance. Get access here:

Today, we're releasing GLM-5.3 Fast: one of the most intelligent open-weight models ever at an even higher TPS. Designed for real-time use cases that demand consistent performance. Get access here:

17,593 görüntüleme

We've launched the fastest GLM 5 API available at 190 TPS and 0.79 sec TTFT with the Baseten Inference Stack. Ready for your coding and agentic workflows.

We've launched the fastest GLM 5 API available at 190 TPS and 0.79 sec TTFT with the Baseten Inference Stack. Ready for your coding and agentic workflows.

19,731 görüntüleme

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

AI researchers' idea of a good time: playing HORSE and debating continual learning between shots. Charlie O'Neill (co-head of training at Baseten) and Jack Morris (co-founder and head of research at Engram) discuss: - when to put knowledge in weights vs. the KV cache, - why forgetting matters less for specialized models, - on-policy self-distillation vs. RL, and - what research publishing should look like today. Watch the full game (and discussion) here:

AI researchers' idea of a good time: playing HORSE and debating continual learning between shots. Charlie O'Neill (co-head of training at Baseten) and Jack Morris (co-founder and head of research at Engram) discuss: - when to put knowledge in weights vs. the KV cache, - why forgetting matters less for specialized models, - on-policy self-distillation vs. RL, and - what research publishing should look like today. Watch the full game (and discussion) here:

48,574 görüntüleme • 16 gün önce

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI.

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI.

115,468 görüntüleme • 3 ay önce

Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with Goodfire to bring inference and in-line monitoring together for the first time, so safety signals are caught proactively. Read more in our announcement:

Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with Goodfire to bring inference and in-line monitoring together for the first time, so safety signals are caught proactively. Read more in our announcement:

26,068 görüntüleme • 19 gün önce

Nobody knows what inference means but it's provocative

Nobody knows what inference means but it's provocative

497,374 görüntüleme • 1 yıl önce

let there be inference

let there be inference

332,507 görüntüleme • 1 yıl önce

Until now, adding web search to open-source models meant hand-wiring orchestration, managing separate keys, and paying latency taxes on every round trip. Today, we're solving that. We're excited to introduce Baseten Hosted Tools and Baseten Grounded Inference to bring real-time web search server-side to open models running on Baseten through a single configuration: - 15% lower latency compared to client-side execution - No extra vendor key required - Zero orchestration We're launching this preview version with four leading web search partners, Exa, Keenable AI, Parallel Web Systems, and You.com. Get frontier-level web search parity for your open-weight models. More here:

Until now, adding web search to open-source models meant hand-wiring orchestration, managing separate keys, and paying latency taxes on every round trip. Today, we're solving that. We're excited to introduce Baseten Hosted Tools and Baseten Grounded Inference to bring real-time web search server-side to open models running on Baseten through a single configuration: - 15% lower latency compared to client-side execution - No extra vendor key required - Zero orchestration We're launching this preview version with four leading web search partners, Exa, Keenable AI, Parallel Web Systems, and You.com. Get frontier-level web search parity for your open-weight models. More here:

31,107 görüntüleme • 1 ay önce

Notion's AI Meeting Notes run on Baseten, and Baseten's knowledge base runs on Notion. Our teams have been working together closely to push the frontier on both fronts. For AI Meeting Notes, our voice engineers built the fastest, highest-quality, yet lowest-cost solution on the market for speaker-attributed transcripts. We're proud to partner with the Notion team.

Notion's AI Meeting Notes run on Baseten, and Baseten's knowledge base runs on Notion. Our teams have been working together closely to push the frontier on both fronts. For AI Meeting Notes, our voice engineers built the fastest, highest-quality, yet lowest-cost solution on the market for speaker-attributed transcripts. We're proud to partner with the Notion team.

36,867 görüntüleme • 1 ay önce

We're proud to be the fastest inference provider on Artificial Analysis, OpenRouter, and Hugging Face for GLM-5.3-Flash, at 122+ TPS. All served from the US only, starting on day 0, with ZDR by default. Stay tuned for updates as our engineers continue to optimize GLM-5.3-Flash for even higher throughput and lower latency.

We're proud to be the fastest inference provider on Artificial Analysis, OpenRouter, and Hugging Face for GLM-5.3-Flash, at 122+ TPS. All served from the US only, starting on day 0, with ZDR by default. Stay tuned for updates as our engineers continue to optimize GLM-5.3-Flash for even higher throughput and lower latency.

23,114 görüntüleme • 2 ay önce

DeepSeek-V3 dropped today and the LLM world just got turned upside down. Again. Early indicators are that this model completely transforms the closed and open-source model landscapes. Tl;Dr - OSS is now SOTA/Top3 again. Here are the key details to know: - Open source and licensed for commercial use - Beats Llamas, Qwens, GPT-4o, Sonnet 3.5 - MoE w/ 671B params, 37B active per token - 128K-token context window - Distilled o3-style reasoning Deeper dive in 🧵 This is one of the first models that need the horsepower of H200s GPUs, so we’re getting them ready to go. If you’re interested in running DeepSeek-V3, reach out to us about a dedicated deployment on H200s: h/t zhyncs for putting us on this early, Dhruv Singal for getting it running on H200s, and Philip Kiely for the demo!

DeepSeek-V3 dropped today and the LLM world just got turned upside down. Again. Early indicators are that this model completely transforms the closed and open-source model landscapes. Tl;Dr - OSS is now SOTA/Top3 again. Here are the key details to know: - Open source and licensed for commercial use - Beats Llamas, Qwens, GPT-4o, Sonnet 3.5 - MoE w/ 671B params, 37B active per token - 128K-token context window - Distilled o3-style reasoning Deeper dive in 🧵 This is one of the first models that need the horsepower of H200s GPUs, so we’re getting them ready to go. If you’re interested in running DeepSeek-V3, reach out to us about a dedicated deployment on H200s: h/t zhyncs for putting us on this early, Dhruv Singal for getting it running on H200s, and Philip Kiely for the demo!

69,598 görüntüleme • 1 yıl önce

DeepSeek-R1 is blowing up right now, but we're not surprised. And not just because we’ve been working closely with DeepSeek to bring these models to production. We've been betting on powerful, open-source models like DeepSeek-R1 from day one. 1/n 🧵

DeepSeek-R1 is blowing up right now, but we're not surprised. And not just because we’ve been working closely with DeepSeek to bring these models to production. We've been betting on powerful, open-source models like DeepSeek-R1 from day one. 1/n 🧵

59,342 görüntüleme • 1 yıl önce

🚀 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 production. Baseten Training (Beta) provides infra and tooling without limitations for AI models destined for production. Huge shoutout to the many partners and customers we've worked with as we built these two new products—more details below.

🚀 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 production. Baseten Training (Beta) provides infra and tooling without limitations for AI models destined for production. Huge shoutout to the many partners and customers we've worked with as we built these two new products—more details below.

35,382 görüntüleme • 1 yıl önce

🚀 New Generally Available Whisper drop: The fastest, most accurate, and cost-effective transcription with over 1000x real-time factor for production AI workloads. 🚀 Our new Generally Available Whisper implementation delivers: 🏎️ Over 1000x real-time factor ✨ The lowest word error rate 💪 Production-grade reliability 🧩 Custom scaling and hardware per processing step 👉 See how in our blog: Reach out to get record-breaking performance for your mission-critical AI workloads!

🚀 New Generally Available Whisper drop: The fastest, most accurate, and cost-effective transcription with over 1000x real-time factor for production AI workloads. 🚀 Our new Generally Available Whisper implementation delivers: 🏎️ Over 1000x real-time factor ✨ The lowest word error rate 💪 Production-grade reliability 🧩 Custom scaling and hardware per processing step 👉 See how in our blog: Reach out to get record-breaking performance for your mission-critical AI workloads!

15,527 görüntüleme • 1 yıl önce

Daha fazla içerik yok.