Skip to content

Blog

Insights, updates, and deep dives from the Chutes team on the future of decentralized AI compute.

RSS Feed
We’re expanding our model catalog with GLM, DeepSeek, Qwen, and Kimi

We’re expanding our model catalog with GLM, DeepSeek, Qwen, and Kimi

We’ve added seven models from Z.ai, DeepSeek, Alibaba’s Qwen team, and Moonshot AI to our catalog. The lineup includes GLM-5.3, DeepSeek V4.1 Flash 1017, and Kimi K2.7 Code, all accessible through our OpenAI-compatible API with an existing key and account credits. You can compare models for coding, research, and agent workflows without setting up a separate provider integration. Regular input prices start at $0.30 per million tokens, with the full lineup and rates below. TL;DR * Seven addit

November 4, 2026
6 min read
Chutes models are now on SayGM

Chutes models are now on SayGM

SayGM is an LLM gateway built on Bittensor subnet 28. The gateway itself runs inside an Intel TDX trusted execution environment and with one API key and one base URL you get access to  Claude, GPT, Gemini and a varied catalog of open-weight models. Chutes is happy to announce we are now one of the upstream providers powering access on SayGM. The open-weight models SayGM serves inside a TEE sit in its confidential tier, and you can spot them by the -tee suffix on the model ID. If you build on C

October 28, 2026
5 min read
Democratizing Intelligence: Building an Open Source AI Lab on a Decentralized Network

Democratizing Intelligence: Building an Open Source AI Lab on a Decentralized Network

Should intelligence be owned by the broligarchy? Intelligence has quickly become one of the most critical resources on earth, and unfortunately it has already turned into a race for unimaginable wealth and concentrated power. A small handful of companies own the frontier models, the data, the hardware, and the IP to produce these models. Those same companies are now pushing for regulatory capture and anti-trust wavers to further consolidate control. The durable solution isn't just another ope

October 22, 2026
8 min read
I let Hermes write its own Chutes config
#vince

I let Hermes write its own Chutes config

One prompt was enough for Hermes to draft its Chutes config. Here is the prompt, the config it wrote, and what the setup and attestation checks actually returned.

September 15, 2026
6 min read
A recurrent model trained decentralized, with no blocking and almost no quality loss
ParallaxDecentralized TrainingResearch

A recurrent model trained decentralized, with no blocking and almost no quality loss

We trained a pure recurrent model across distributed GPUs with fully non-blocking synchronization, and it landed within 0.6% of the centralized baseline at matched steps. As far as we know, that is the first time decentralized non-blocking training has held up on a recurrent architecture. The tradeoff we set out to break Training a model across many GPUs in different places forces a familiar choice. Either the GPUs stop and wait to synchronize with each other, which is slow and expensive, or

July 8, 2026
2 min read
Please excuse our absence from Proof of Talk in Paris

Please excuse our absence from Proof of Talk in Paris

TL;DR We've been focusing on powerful, significant, and fully quantifiable improvements to chutes' operating budget, security, intellectual property, etc. We very much have a GSD (GET SHIT DONE) philosophy, and sometimes that requires "all-hands-on-deck" work that precludes the possibility of attend

June 15, 2026
4 min read
Quick and Easy Serverless AI Model Deployment
Serverless AIAI Deployment

Quick and Easy Serverless AI Model Deployment

If you want to deploy an AI model without spending weeks on infrastructure, Chutes gives you a practical serverless route: package the model, deploy it on GPU-backed infrastructure, and pay for usage instead of permanent capacity. That shortens the path from experiment to endpoint. What serverless deployment helps with Most model teams do not struggle with the idea of deployment. They struggle with the surrounding work: provisioning hardware, handling dependencies, exposing an API, and scalin

May 18, 2026
1 min read
I built an open-source TEE stack for confidential GPU compute
#vince

I built an open-source TEE stack for confidential GPU compute

A first-hand look at how Chutes built an open-source TEE stack for confidential GPU compute, from attestation and GPU isolation to federation, workload policy, and encrypted upgrades.

May 11, 2026
13 min read
Private AI inference: what it means and how Chutes makes it verifiable
AI InfrastructureConfidential ComputeAI Security

Private AI inference: what it means and how Chutes makes it verifiable

Private AI inference comes down to runtime access. At Chutes, we pair OpenAI-compatible APIs with hardware-attested confidential compute and an optional end-to-end encrypted path.

May 7, 2026
5 min read
End-to-End Encrypted AI Inference with Post-Quantum Cryptography
AI APIsAI InfrastructureDecentralized AIAI SecurityEncryptionTEE

End-to-End Encrypted AI Inference with Post-Quantum Cryptography

How Chutes built verifiable, zero-knowledge AI inference using TEEs, ML-KEM-768, and hardware attestation – so not even we can see your data.

March 26, 2026
14 min read
From Volume to Value: Building a Sustainable AI Inference Platform
News

From Volume to Value: Building a Sustainable AI Inference Platform

We processed 45% fewer tokens over the last six weeks. On the surface, that may seem like pretty bad news, but the true story is one of massive increases in efficiency and future sustainability.

March 20, 2026
4 min read
Community Announcement - February 27th, 2026
News

Community Announcement - February 27th, 2026

An update about the coming changes to Chutes

February 27, 2026
3 min read
Confidential Compute for AI Inference: How Chutes Delivers Verifiable Privacy with Trusted Execution Environments
#vince

Confidential Compute for AI Inference: How Chutes Delivers Verifiable Privacy with Trusted Execution Environments

Your prompts. Your data. Hardware-protected from everyone—even us. Chutes TEEs: Confidential AI you can verify, not just trust The Chutes network is designed for an adversarial world: miners are anonymous and permissionless.  Given this new reality, security is no longer “just trust me” it must become “don’t trust, verify.” That’s the core idea behind Chutes’ security model: a defense‑in‑depth stack that verifies software integrity, attests to hardware properties, restricts runtime behavior

December 23, 2025
4 min read
Who are the founders of Chutes AI?
#vince

Who are the founders of Chutes AI?

Founders and Organizational Model Chutes AI was founded by a global, decentralized collective of engineers, researchers, and builders working under the umbrella of Chutes Global Corp. There is no CEO or central decision maker; responsibilities are shared across contributors through a collective gove

November 12, 2025
1 min read
Deploy AI Music Generation Tools in Minutes With Chutes
#vince

Deploy AI Music Generation Tools in Minutes With Chutes

Deploy AI music generation models with Chutes' serverless GPU compute and create new opportunities for creativity and personalization. This secure platform enables you to deploy and manage AI models at scale. Effortlessly move from experimentation to production in minutes and accelerate time-to-value with Chutes. Easily Deploy AI Music Models Whether you're training new models or running real-time inference, Chutes supports your music generation projects with reliable, flexible compute. Deplo

November 11, 2025
2 min read
AI Content Moderation Made Easy With Chutes
AI Performance

AI Content Moderation Made Easy With Chutes

Chutes enables large-scale AI content moderation that is fast, accurate and cost-efficient. Deploy and scale your own models or serverless AI code on a decentralized open-source network. Handle massive volumes of user-generated content in real time and integrate seamlessly into modern development environments with performance and flexibility at scale.  Effortlessly Intercept Content Risks With AI Moderation Chutes empowers you to deploy customized AI content moderation models — open-source or

November 4, 2025
2 min read
Why Does AI Need GPUs?
AI Infrastructure

Why Does AI Need GPUs?

Artificial intelligence (AI) requires processing enormous amounts of data and performing millions of calculations at once. Traditional central processing units (CPUs) are not optimized for this level of parallel processing. Instead, AI uses graphics processing units (GPUs), which are specifically designed to handle thousands of simultaneous computations — making them essential for modern AI applications.  Why Are GPUs Used for AI? GPUs are hardware components with thousands of smaller, specia

October 28, 2025
2 min read
Chutes: A Decentralized AI Platform
Decentralized AI

Chutes: A Decentralized AI Platform

Deploy any AI model in minutes with Chutes — serverless, decentralized, and built for scalable, GPU-free AI compute.

October 7, 2025
3 min read
New Chutes Landing Pages, Miner Dashboards & Pricing Updates
News#vince

New Chutes Landing Pages, Miner Dashboards & Pricing Updates

We've rebuilt the landing pages from scratch to reflect where we are as a subnet/product. They're now more fleshed out, with more pages targeted towards enterprise customers, pricing etc. (You'll notice our new pricing tiers, coming next Monday) We've also significantly fleshed out documentation for our SDK, API and integrated the miner docs directly, to one central hub which we now call Chutes Developers. We hope with this change we can encourage more developers to build, deploy and scale thei

July 31, 2025
1 min read
Chutes Usage Skyrockets: TPS & RPS Growth Over Time
data

Chutes Usage Skyrockets: TPS & RPS Growth Over Time

Impressive real-world adoption metrics highlight Chutes’ readiness to handle high-volume AI tasks on the Bittensor network.

February 13, 2025
5 min read
Chutes Achieves PMF: Billions of Tokens Flowing Through the Open Router Daily
milestone

Chutes Achieves PMF: Billions of Tokens Flowing Through the Open Router Daily

Chutes hits crucial PMF milestone, underscoring its staying power in the decentralized AI compute arena.

February 4, 2025
5 min read
DeepSeek-R1 Now Available on Chutes: Advanced Reasoning at Your Fingertips
release

DeepSeek-R1 Now Available on Chutes: Advanced Reasoning at Your Fingertips

DeepSeek-R1 joins the Chutes platform, bringing advanced reasoning capabilities to developers and users worldwide.

January 22, 2025
5 min read
Chutes Unveils Massive GPU Miner Pool: Run Any Model Instantly
release

Chutes Unveils Massive GPU Miner Pool: Run Any Model Instantly

Chutes expands its global GPU network, offering one-click access to training and inference for LLMs, images, audio, and beyond.

January 15, 2025
5 min read
Chutes Has Landed! 🪂 Just in time for Christmas, Permissionless AI Compute is Here
update

Chutes Has Landed! 🪂 Just in time for Christmas, Permissionless AI Compute is Here

A new era of decentralized AI compute arrives with Chutes, bringing GPU power and autonomous workflows to everyone.

December 24, 2024
5 min read

Join Our Community

Connect with us for real-time updates, discussions, and community support.