AI News HubLIVE
Public articles 36Collected articles 37Trust 88Refresh 5 min
Health HealthySource type OfficialFull-text rights Official full textLast ingested 2026-08-07ID together-ai-blogStatus Enabled

Official source; confirm reuse terms before enabling full body display.

Latest public articles

DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and Coding

We ran 900 DeepSWE rollouts on DeepSeek-V4 Flash and GPT-5.6 Luna. Luna leads pass@1 by 14 points; DeepSeek delivers 4.8x the solves per dollar.

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • We ran 900 DeepSWE rollouts on DeepSeek-V4 Flash and GPT-5.6 Luna. Luna leads pass@1 by 14 points; DeepSeek delivers 4.8x the solves per dollar.
In-site article

Kimi K3: The Complete Developer Guide

Kimi K3 is Moonshot AI's 2.8T-parameter open-weight model—the first in the 3-trillion-parameter class. Here's how it's architected, what it costs on Together AI, and how to call it with code examples for reasoning effort, streaming, vision, structured output, tools, and dynamic tool loading.

  • Kimi K3 is a 2.8T-parameter open-weights model, the largest open-weight model ever released, with 1M context support.
  • New architecture: Kimi Delta Attention, Attention Residuals, and Stable LatentMoE activate only 16 of 896 experts per token.
In-site article

ThunderAgent: 2x Faster Agentic Inference for Synthetic Data Generation at Scale

ThunderAgent is a program-aware scheduler for agentic inference. By treating each agent workflow as a schedulable program, it eliminates KV cache thrashing to deliver more than 2x single-node throughput and near-linear multi-node scaling.

  • Introduces a program abstraction for agentic LLM request scheduling, eliminating KV cache thrashing
  • Achieves up to 2.5x single-node throughput and 2.4x speedup on an 8-node cluster
In-site article

Together AI announces strategic partnership with Moonshot AI to natively serve Kimi models

Together AI and Moonshot AI form a strategic partnership, making Together AI the launch platform for Moonshot's open models, starting with Kimi K3, a 2.8-trillion-parameter sparse MoE model.

  • Together AI becomes the launch platform for Moonshot AI models, offering day-zero access and US-hosted infrastructure.
  • Kimi K3 is a 2.8T parameter sparse MoE model with native vision and 1M context, featuring Kimi Delta Attention and Attention Residuals.
In-site article

Configuring Dedicated Model Inference

A detailed guide on Together AI's Dedicated Model Inference architecture: endpoints, deployments, configs, and capacity-aware routing.

  • The system consists of endpoints (stable names), deployments (model+hardware), and configs (immutable recipes).
  • Traffic routing is based on effective capacity (weight × ready replicas), not fixed percentages.
In-site article

Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing

We ran 904 DeepSWE rollouts on Kimi K3 and GPT-5.6 Sol. Sol leads pass@1; Kimi K3 wins pass@4 at 2.8x the solves per dollar, and routing between them reaches ~85.6%.

  • Sol achieves 72.7% pass@1 vs Kimi's 68.5%.
  • Kimi K3 achieves 89.4% pass@4 vs Sol's 85.8%.
In-site article

Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding

We ran 452 DeepSWE rollouts on Kimi K3 and Claude Fable 5. Fable leads pass@1 by 1.4 points; Kimi K3 wins pass@4 and delivers 2.8x the solves per dollar.

  • Kimi K3 achieves 68.5% pass@1 vs Fable's 69.9%, but wins at pass@2 (82.0% vs 80.2%) and pass@4 (89.4% vs 88.5%).
  • Kimi K3 costs $4.65 per rollout vs $13.41 for Fable, yielding 2.8x more solved tasks per dollar.
In-site article

The production platform for open-weight AI inference

Together AI releases a major update to its inference platform, giving users control over performance, cost, and quality. New features include canary deployments, A/B testing, autoscaling, and a closed beta for custom training with reinforcement learning and fine-tuning.

  • Deploy open-weight models in minutes with production-grade controls
  • Supports canary, blue-green, and rolling updates with auto rollback
In-site article

Together AI and Y Combinator partner to launch the first dedicated GPU cluster for the YC community

Together AI and Y Combinator have partnered to provide YC startups with a dedicated GPU cluster, addressing the compute bottleneck. Startups can commit for weeks instead of two-year contracts, and manage GPUs directly through a self-service portal without YC involvement. The cluster is fully utilized and supports needs from single-node to large-scale expansion.

  • Together AI and YC launch first dedicated GPU cluster for YC startups, providing direct compute access.
  • Commitments are for weeks instead of two-year contracts, freeing capital for other business needs.
In-site article

What does 99.9% uptime mean for inference?

This article breaks down the real meaning behind reliability numbers like 99%, 99.9%, and 99.99% uptime for AI inference services, explaining the failure domains each tier must survive and the architectural requirements. The authors from Together AI share their experience building reliable inference infrastructure and provide key questions to ask any provider before committing.

  • Each reliability tier maps to a specific failure domain: 99% for node failures, 99.9% for data center failures, 99.99% for regional outages.
  • Achieving high uptime requires proactive health checks, multi-facility deployment, and reserved capacity.
In-site article

New in Together GPU Clusters: Reliability and control for production GPU clusters

See how Together AI is improving production GPU clusters with passive health checks, node repair, stronger Slurm reliability, OIDC, and startup scripts.

  • Together AI introduces passive health checks and auto node repair for faster failure detection and recovery.
  • Slurm-on-K8s 2.0 provides self-healing daemons, durable job accounting, and reliable process cleanup.
In-site article

Together AI brings Thinking Machines Lab’s new model Inkling on day 0

Thinking Machines Lab released Inkling, a multimodal mixture-of-experts model for token-efficient reasoning, native multimodal understanding, and broad task versatility. Together AI makes it available on its inference platform with support for controllable reasoning effort, text/image/audio inputs, and a 1M context window.

  • Inkling is a multimodal MoE model with 975B total parameters, 40B active per token, and a 1M context window.
  • It accepts text, image, and audio inputs and supports adjustable reasoning effort for cost-latency trade-offs.
In-site article

Open, convenient and predictable: Introducing Provisioned Throughput

Provisioned Throughput offers reserved inference capacity for frontier open models with token-based pricing and a 99% uptime SLA, reducing costs by up to 90% compared to proprietary APIs.

  • Reserved inference capacity with token-based pricing and 99% uptime SLA.
  • Priced at $0.05 per PTU per minute; no GPU-hour math or infrastructure management.
In-site article

Announcing our $800M Series C to accelerate the shift to open-source AI

Together AI raised $800M in Series C funding to accelerate the shift to open-source AI. The company argues that closed models' economics don't scale, and open models combined with full-stack optimization can achieve 6-20x cost reductions. Together AI has launched innovations like FlashAttention-4 and Together Megakernel, becoming one of the world's largest AI token producers.

  • Together AI raised $800M in Series C funding to accelerate open-source AI
  • Closed models' cost structure is unsustainable at scale
In-site article

Together AI at ICML 2026: Frontier Research Across the Full Stack

Eight papers from Together AI accepted to ICML 2026, covering the full AI stack from agents to GPU kernels. These research works are integrated into the Together platform and already benefit production workloads.

  • Eight papers accepted to ICML 2026, spanning the full AI stack from agents to kernels.
  • DSGym provides a unified framework for data science agent evaluation and training with over 1,000 tasks across 10+ domains.
In-site article

ParallelKernelBench: Frontier LLMs can't write fast multi-GPU kernels (yet)

ParallelKernelBench tests whether LLMs can write fast multi-GPU CUDA kernels across 87 real workloads. The best model solves under a third, but a few generated kernels beat any public implementation.

  • ParallelKernelBench (PKB) includes 87 multi-GPU kernel generation problems from real codebases.
  • The best frontier model (GPT-5.5) solves under a third of problems in zero-shot setting, with only 22 faster than baseline.
In-site article

Kimi K2.7 Code vs Claude Fable 5: Landing pages that cost 94% less

We generated 12 landing pages with Kimi K2.7 Code and Claude Fable 5. Kimi cost 94% less and scored within a few points on every page. Open-source models are not only cheaper but genuinely competitive on quality, and the gap is closing fast.

  • Kimi K2.7 Code costs about 94% less than Claude Fable 5 for generating landing pages.
  • Quality scores show a small gap between Kimi and Fable, especially after using a design inspiration MCP.
In-site article

Building trust in enterprise AI: Together AI earns ISO 27001:2022 certification

Together AI has achieved ISO 27001:2022 certification from A-LIGN, validating its information security management system for enterprise-grade AI workloads, complementing existing SOC 2 controls.

  • ISO 27001:2022 certification awarded by A-LIGN Compliance and Security
  • Scope covers global platform, corporate HQ, and third-party data centers
In-site article

Serving MiniMax-M3 for efficient inference: Unlocking 1M-Token Context and Multimodality Without Regrets

Together AI optimizes MiniMax M3 serving with KV-block-major sparse attention, paged MSA decode, optimized index scoring, and a Rust-based multimodal gateway, achieving 81–125% throughput improvements across concurrency levels.

  • MiniMax M3 combines coding, agentic workflows, and multimodal reasoning with a 1M-token context window.
  • Together AI's kernel team developed KV-block-major sparse attention and integrated MSA with paged attention.
In-site article

How Together AI built the world’s fastest speech-to-text stack

Together AI built the fastest speech-to-text stack on Artificial Analysis by treating ASR as a full-path systems problem, not just a GPU inference problem. This article details optimizations including TensorRT multi-profile encoders, conditional CUDA graphs, shared memory, evented I/O, and gc.freeze() to eliminate tail latency.

  • Together AI achieved fastest STT by optimizing the entire system path, not just GPU inference.
  • Key techniques: TensorRT multi-profile encoders, conditional CUDA graphs, zero-copy shared memory, and evented I/O.
In-site article

Benchmarking inference at scale: coding agents

On a production coding agent workload, Together Inference Engine delivers 31% more TPS than the next fastest OSS engine on the same hardware, and maintains 2× better TTFT at saturation. The gains come from full-stack optimization: ThunderMLA, custom kernel rewrites, and end-to-end profiling on real traffic.

  • Real-world inference benchmarks for coding agents: 31% more TPS than TensorRT-LLM, 2× better TTFT at saturation, and 76% lower cost than Claude Opus 4.6.
  • Full-stack optimization includes ThunderMLA fused kernel, custom kernel rewrites, and end-to-end profiling.
In-site article

Together AI and Pearl Research Labs Team Up to Reduce the Cost of AI Inference

Together AI partners with Pearl Research Labs to launch a discounted Pearl-powered inference endpoint for Gemma-4-31B-it-pearl, using Proof of Useful Work to turn AI workloads into crypto emissions.

  • Together AI partners with Pearl Research Labs to offer a discounted inference endpoint.
  • The endpoint uses Proof of Useful Work to mine cryptocurrency while performing AI inference.
In-site article

Violin: An open-source video translation skill that breaks language barriers

Violin is an open-source AI video translation tool combining speech recognition, LLM translation, and text-to-speech to make video content accessible across languages. It offers a web app, CLI, and agent skills, featuring a video-aware chat assistant and personalized voice selection. Built with Together API using models like Whisper, DeepSeek, and Cartesia, it's released under the MIT license.

  • Violin integrates ASR, LLM translation, and TTS for open-source video translation.
  • Supports web app, CLI, and agent skills for diverse users.
In-site article

Deploy and inference any model from HuggingFace

Learn how to deploy any HuggingFace model in one session using Goose and Together's Dedicated Container Inference. Skip the setup complexity — one prompt gets your model running in a production-grade GPU environment on release day.

  • Use Goose and Together's Dedicated Container Inference to deploy models with zero lag on release day.
  • Author deployed Netflix's void-model with a single session and prompt.
In-site article

Serving DeepSeek-V4: why million-token context is an inference systems problem

DeepSeek-V4's hybrid attention design (CSA, HCA, SWA) compresses KV cache, turning million-token context from a model challenge into a serving-systems problem. Together AI's early bring-up on NVIDIA HGX B200 reveals how cache policy, prefix caching, and endpoint profiles impact long-context workloads.

  • DeepSeek-V4's compressed sparse attention (CSA) and heavily compressed attention (HCA) reduce KV cache size, but the inference engine must manage multiple cache layouts.
  • Sliding window attention (SWA) becomes a bottleneck at long context, requiring careful storage strategy.
In-site article

Foundational research powering efficient inference at scale

As AI moves from research to production, the challenge for AI-native teams shifts from building models to running them — efficiently, reliably, and at scale. Inference costs account for 80-90% of total lifetime cost of a production AI system. Together AI's research (FlashAttention-4, ATLAS) and full-stack optimization enable efficient inference, improving unit economics for customers.

  • Inference costs dominate AI system economics, comprising 80-90% of total lifetime cost.
  • Together AI introduces FlashAttention-4 (up to 1.3× faster than cuDNN) and ATLAS (adaptive speculative decoding for 4× faster inference).
In-site article

Announcing Together AI and Adaption Partnership

Together AI and Adaption partner to bring Together Fine-Tuning natively into Adaptive Data, helping teams optimize datasets, run fine-tuning, evaluate results, and deploy stronger open models.

  • Together AI partners with Adaption to integrate fine-tuning into Adaptive Data.
  • The partnership aims to simplify the workflow from data optimization to model deployment.
In-site article

From 732 bytes to nowhere: shutting down Copy Fail in production

Together AI details their rapid response to the Linux kernel vulnerability Copy Fail (CVE-2026-31431), which allowed local unprivileged users a precise 4-byte write primitive via the AF_ALG interface, leading to privilege escalation. The team mitigated by unloading the vulnerable kernel module, rolling out patches, and enhancing detection, ensuring AI infrastructure security.

  • Copy Fail (CVE-2026-31431) is a logic bug in the Linux kernel's crypto subsystem allowing precise 4-byte writes to any readable file's page cache.
  • Together AI unloaded the algif_aead module and removed its file within hours, blocking exploits without reboot.
In-site article

DeepSeek-V4 Pro now available on Together AI

DeepSeek-V4 Pro, a 1.6T-parameter MoE reasoning model, is now available on Together AI with a 512K context window, controllable reasoning modes, and cached-input pricing for long-context workloads like code agents, document intelligence, and research synthesis.

  • 1.6T-parameter MoE with 49B activated parameters, 512K context on Together AI (model supports 1M)
  • Three reasoning modes: Non-Think, Think High, Think Max to match effort to task
In-site article

All sources