Rime voice models now available on Together AI
Two enterprise-grade Rime TTS models now available on Together AI. Co-locate with LLM and STT on dedicated infrastructure. Proven at billions of calls.
en
Together AI Blog
93
Research POV: Yes, AGI Can Happen – A Computational Perspective
Dan Fu, our VP of Kernels, has published a new post challenging the idea that AI is hitting a hardware wall. He argues that we are vastly underutilizing current chips and that better software-hardware co-design will unlock the next order of magnitude in performance.
en
Announcing native availability of NVIDIA Nemotron 3 Nano, NVIDIA’s latest reasoning model
Nemotron 3 Nano, NVIDIA’s newest reasoning model, is now available on Together AI, the AI Native Cloud
en
Announcing Together Python SDK v2.0
Together AI ships a Python SDK v2.0 release candidate: a type-safe, OpenAPI-generated client replacing the legacy v1 SDK, with beta Instant Clusters APIs.
en
Introducing AutoJudge: Streamlined inference acceleration via automated dataset curation
AutoJudge accelerates LLM inference by identifying which token mismatches actually matter. Using self-supervised learning to train a lightweight classifier, it accepts up to 40 draft tokens per cycle—delivering 1.5–2× speedups over standard speculative decoding with minimal accur
en
How to run TorchForge reinforcement learning pipelines in the Together AI Native Cloud
How to run TorchForge reinforcement learning pipelines on Together AI's Instant Clusters, with a demo and configuration guidance for distributed training.
en
Together AI and Meta partner to bring PyTorch Reinforcement Learning to the AI Native Cloud
Build, train, and deploy advanced AI agents with integrated reinforcement learning on the Together platform.
en
Together AI delivers fastest inference for the top open-source models
Together AI achieves up to 2x faster inference for top open-source models like Qwen, DeepSeek, and Kimi through GPU optimization, advanced speculative decoding, and FP4 quantization—ranking #1 in speed benchmarks on NVIDIA Blackwell architecture.
en
FLUX.2: Multi-reference image generation now available on Together AI
Production-grade image generation with multi-reference consistency, exact brand colors, and reliable text rendering. FLUX.2 from Black Forest Labs, now on Together AI's platform.
en
How to evaluate and benchmark Large Language Models (LLMs)
Understanding how to evaluate and benchmark Large Language Models (LLMS). Test, compare, and understand LLMs.
en
Announcing the fastest inference for realtime voice AI agents
Together AI launches the fastest voice AI stack: streaming Whisper STT, serverless open-source TTS (Orpheus & Kokoro), and Voxtral transcription. Sub-second latency for production voice agents.
en
Dynamic AI agent testing for the real world with Collinear Simulations and Together Evals
Test AI agents in the real world with Collinear TraitMix and Together Evals: dynamic persona simulations, multi-turn dialogs, and LLM-as-judge scoring.
en
Large Reasoning Models Fail to Follow Instructions During Reasoning: A Benchmark Study
ReasonIF finds frontier LRMs fail to follow reasoning instructions >75% of the time; introduces a benchmark across languages, formatting, and length.
en