Models & Labs
Together AI Launches Provisioned Throughput for Open Models
Together AI Bloghigh confidence
Why it matters
- →Provides a cost-effective alternative to proprietary models, reducing inference costs by up to 90%.
- →Offers predictable pricing and guaranteed capacity, crucial for production workloads.
- →Facilitates the adoption of open models in enterprise environments, enhancing scalability and reliability.
Together AI has introduced Provisioned Throughput, a new service offering reserved inference capacity for open models with token-based pricing and a 99% uptime SLA. This service aims to provide companies with a cost-effective and reliable alternative to proprietary models, offering up to 90% savings compared to models like Claude Opus 4.8. Provisioned Throughput is available for models such as MiniMax M3 and GLM-5.2, with capacity in North America and EMEA. This development is expected to facilitate the adoption of open models in production environments by providing predictable pricing and guaranteed capacity.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1OpenAI Launches DeployCo for Enterprise AI
The AI Daily Brief · May 13, 2026 · Background
- 2OpenAI and Dell Partner for Enterprise Codex Deployment
OpenAI · May 18, 2026 · Related
- 3NVIDIA and Dell Unveil AI Infrastructure at Scale
NVIDIA Blog · May 18, 2026 · Background
- 4Specialized AI Models Outperform Larger Counterparts
Hugging Face Blog · May 22, 2026 · Background
- 5OpenAI Models Now Available on Oracle Cloud
OpenAI · June 10, 2026 · Background
- 6GLM 5.2 Emerges as Leading Open Weights Model
Sam Witteveen · June 17, 2026 · Background
- 7OpenAI's GPT-5.6 Sol Model Released to Limited Partners
The Rundown AI · June 29, 2026 · Background
- 8Together AI Secures $800M in Series C Funding
Crunchbase News · July 2, 2026 · Related
What happened next
- 9Together AI Enhances Open-Weight Inference Platform
Together AI Blog · July 23, 2026 · Related
- 10Open-weight AI models near top-tier capabilities
TechCrunch AI · August 4, 2026 · Background
- 11OpenAI buys Macs for private AI agents
Wes Roth · September 1, 2026 · Background
- 12Together Link bridges open models to coding agents
Together AI Blog · October 5, 2026 · Same story
- 13Liquid AI releases efficient on-device agent model
Hugging Face Blog · October 13, 2026 · Background
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
Apple Intelligence arrives in China via iOS 27.3
Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.
The Verge AI
© Matt WolfeModels & Labsmodels
Google Releases Gemini 4 Carbon for Cost-Efficient Inference
Google launched Gemini 4 Carbon, a new model variant aimed at providing high performance at a lower cost for inference tasks.
Matt Wolfe