The most secure AI inference on earth. Powering your next AI App.
Bittensor
Joined November 2024
- Tweets814
- Following12
- Followers11.8K
- Likes520
Chutes is very excited to be working with METANOVA LABS as they develop their Hit-to-Lead optimization agent! We fully intend to assist and support to this project in any way we can as it develops.
NOVA Hit-to-Lead Optimization Agent
In collaboration with @chutes_ai and @onepot_ai
We're developing a Hit-to-Lead optimization agent that integrates an algorithm developed by a NOVA Blueprint winner, extending NOVA's capabilities beyond hit discovery and into the iterative optimization of small molecules.
The system combines a domain-specialized AI agent with proprietary combinatorial chemical databases supplied by our partner Onepot AI, spanning billions of possible compounds, that are delivered within 5-7 business days.
Researchers will be able to guide the agent in developing, comparing and refining optimization strategies, exploring chemical modifications and prioritizing candidates based on predicted affinity, selectivity, physicochemical properties and specific binding interactions.
Confidentiality is a central design requirement. Pharmaceutical R&D involves valuable intellectual property, including compound structures, targets, emerging chemical series and optimization strategies that cannot be exposed publicly.
The Chutes team integrated domain specific models so that we can run inference in their verified Trusted Execution Environments (TEEs), with encrypted communication and controlled access to proprietary databases and project records. This architecture is intended to support confidential inference on external infrastructure while preserving organizational control over sensitive research data.
Finding a molecule with promising predicted affinity is only the beginning. Hit-to-Lead optimization involves balancing multiple, often competing objectives, including potency, selectivity, physicochemical properties and synthesizability, before progressing toward experimental activity and ADME validation.
The next step is to integrate the agent into our own Hit-to-Lead development program.
For NOVA, this represents an important step toward translating algorithms developed through open competition into tools for proprietary drug discovery programs, including our own asset-development pipeline and those of external research partners.
Chutes is now live on @say_gm_
SayGM gives you one API key for Claude, GPT, Gemini and open-source models.
When you pick one of SayGM’s private models, it can now run on Chutes, inside secure hardware where no one can read your prompts. Not even us.
See the full article here: chutes.ai/news/chutes-models…
Chutes retweeted
Here's a very crude simplified chutes roadmap/plan, for near term:
- move the most unprofitable things off of the subnet, including today's announcement of some (not all) additional inference options (not paid via emissions)
- this allows us to scale the things we want and need to avoid capacity issues/better direct incentive - this includes models we use to build data pipelines and relationships to other teams/networks/etc
- add options that are completely revenue positive (hourly pricing/rentals/simple docker based jobs/etc), TEE, private, secure, priced above cost, more extensive version of private chutes we have today basically
- expand the hourly compute offerings to also include CPU only (e.g. to run agents, web browsers, sandboxes, non-GPU work of any kind)
- use some of the incentive for ideally non-datacenter based model training and serving
- build a non-extractable product on chutes from the models we build, via dynamic edge nodes, possibly from the epigenesis work (smaller faster cheaper faster than lora customizations from the sparse sections of pretrained model, participant supplied)
- models and pipeline etc. will be open source, the customization and ensemble thereof will live only in chutes, inc. the continuously evolving set of served variations/RL/etc.
We'd like, to the extent we can, attract participants who want to build and have no obligation to pay datacenters or any particular hardware vendor, to keep the value inside the subnet at all times by attacking sell pressure at the source (DC commitments, chip purchases, etc).
We will continue to have secure TEE inference and GPUs; not elimating anything wholesale, just focusing more on a commodity that doesn't have to flow out to DCs and single hardware vendors.
NVIDIA reportedly has 75% profit margins, revenue for the sake of revenue fueling GPU reselling goes straight to one place, basically. Fine, I guess, but I'd rather work together as individuals with whatever hardware we can bring, to a reasonable degree.
We've expanded the Chutes catalog.
As demand for inference has grown, we've added capacity so our users around the world can get the models they need every day, paid for in crypto or fiat. Starting today, alongside our confidential TEE models, Chutes now offers a set of non-TEE models.
First up are the following models, live now on chutes.ai with the same API key and billing you already use.
DeepSeek V4 Pro: chutes.ai/app/chute/chutes-d…
Qwen3.8 Max: chutes.ai/app/chute/chutes-q…
GLM-5.2-Fast: chutes.ai/app/chute/chutes-z…
Qwen3.8-2.4T-A95B: chutes.ai/app/chute/chutes-q…
GLM-5.3: chutes.ai/app/chute/chutes-z…
DeepSeek-V4.1-Flash-1017: chutes.ai/app/chute/chutes-d…
Kimi-K2.7-Code: chutes.ai/app/chute/chutes-m…
More models are coming.
Chutes Inference at a glance
• OpenAI compatible: point any OpenAI SDK or existing tool at Chutes with your current API key. No new account, no new integration.
• One account, one bill: non-TEE and TEE models share the same API key, credits and usage dashboard (and are clearly labelled which category they fall into).
• Pay your way: crypto or fiat, available to users worldwide.
• Serverless: pay per token, nothing to deploy, no capacity to manage.
• Built for agents: tool calling and long-context workloads supported out of the box.
• Your choice of privacy tier: need end-to-end encryption? Run on our TEE models instead.
We've started rolling out additional models/capacity to the chutes platform, namely Qwen3.8 Max and DeepSeek V4.1 Pro (with more to follow soon, along with additional details). They are currently in beta mode, please test and give us feedback!
Unfortunately, due to the mechanics of these new model offerings and current general GPU/compute market dynamics, subscriptions are no longer feasible. Your subscriptions will automatically sunset/not renew at the end of the current subscription period.
If you have an active subscription it will continue to work normally until the end of the billing period. The two new models listed above are not available with subscriptions and are PayGo only, and they are not currently supported in TEE/confidential compute/E2EE mode.
Please reach out at [email protected] with any questions or concerns.
When you send a prompt to Chutes with E2EE, it runs inside a hardware-attested TEE with end-to-end encryption. We can't read it, and neither can anyone who asks us for it.
Even holding the TLS certificate for chutes.ai, we don't see prompts or responses. If we were ever ordered to hand them over, all anyone would get is ciphertext.
The whole stack is open source, so you don't have to take our word for it.
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, and the hardware.
We at Chutes have strong feelings about that. Read our thoughts on a different vision for the world and path forward here: chutes.ai/news/democratizing…
Most AI has an off switch. It looks like a building: one datacenter, one provider, one cloud account that can be closed, one government that can say no. If the thing you depend on lives in one place, someone else decides whether it stays on.
Parallax is our attempt to train models that don’t have that switch.
The name is the trick your eyes do. Hold a finger in front of your face and close one eye, then the other. It jumps. Many viewpoints make depth. Parallax trains one model from many machines’ viewpoints at once, and Jon’s claim on stage is that this is where the quality comes from.
If you are not an engineer, the whole thing comes down to one sentence: a model nobody can switch off, built on hardware anyone can rent.
The full talk: youtube.com/watch?v=4FOxXT66…
Jon's talk at Exploit was an hour on how Parallax works. Here's the part that matters if you never plan to read a paper.
Most AI today lives in a building someone else owns. They set the price, they keep the logs, they decide what you're allowed to ask, and they can switch it off. Parallax is us building the other version. Models small enough to run on a phone (an 8B model did about 60 tokens a second on a Snapdragon, CPU only) and cheap enough to train without a datacenter (about $6,500 for the whole 8B run). Spread across enough ordinary machines that nobody gets to switch it off.
That's the whole project. The maths is in the talk.
parallax.chutes.ai
14 open models, one endpoint, every one of them running inside a hardware-attested TEE.
That's the Chutes catalog today: Kimi K3 and GLM-5.2 with 1M context, DeepSeek V4 Flash, Qwen3.8-27B, Gemma 4 31B, and Nemotron-3-Nano from $0.0245 per million input tokens. The list changes often.
Any OpenAI-compatible client works. Set the base URL to llm.chutes.ai/v1 and keep the rest of your code.
Pretraining a model used to mean a datacenter and a nine-figure budget. Jon did it on rented RTX 5090s over the open internet for $11.27 per billion tokens.
The whole 8B run came to about $6,500. Retail hourly GPU prices, 574B tokens, 52 hours. The syncers were four CPU VMs with no GPU in them, and there was no object store anywhere in the system.
If a model costs about what a used car costs, a lot more people get to own one. That's the point of Parallax.
Jon's comparison from the same slide, his estimate from a published report: Llama 3.2 1B at about 370,000 H100 hours and retail H100 rental of $2 to $4 per GPU-hour works out to $92 to $184 per billion tokens.
The live training register: parallax.chutes.ai
