Chutes is the leading open-source, decentralized compute provider for deploying, scaling and running open-source models in production.
SN 64. Rank 5 of 32 by emission
Chutes
Emission5.9%of the block reward · rank 5 of 32
Participants15 miners · 14 validators
Registration0.0005 TAO
Verified2026-09-09links checked and scores merged
The programinference · github.com@3b5609f · read 2026-09-19
The work
Compute time. A miner runs a Kubernetes cluster of GPU servers inside confidential virtual machines and hosts chutes, the platform's word for a deployable model or workload. What is paid for is the seconds an instance is live and serving, weighted by the GPU class it runs on. The index lists the SDK repository; the validator lives in chutes-api.
own docs · chutes.ai
The goal of mining on chutes is to provide as much compute as possible, optimizing for cold start times
How it is scored
A miner's score is the sum, over the last day, of the seconds each of its instances was live times that instance's compute multiplier, which folds in GPU class, bounties, urgency, and the confidential-compute and private-chute bonuses. Only instances with at least one successful invocation count. The sums are normalized to a distribution and set as weights.
code · raw.githubusercontent.com · metasync/constants.py
SCORING_INTERVAL = "1 day"; sum (overlap_seconds * multiplier) across all history intervals
Sources disagree The docs scoring page fetched 2026-09-19 describes four weighted metrics, compute units 55 percent, invocations 25, unique chutes 15, bounties 5, over a default 7-day window; the code at the pinned commit scores instance compute units alone over one day, per the spec dated 2026-04-13 in docs/specs/scoring-window.md.
How the pay splits
Proportional. Every eligible miner is paid its share of the day's compute units, with no winner bonus and no floor. The split is the score vector itself, normalized to sum to one and submitted as weights.
code · raw.githubusercontent.com · docs/specs/scoring-window.md
normalizes to a distribution, and the result is set as on-chain weights
Who judges
Fourteen validators were active on the 2026-09-09 chain snapshot. Commit-reveal is off. The judge is the platform: the scoring query runs against the API's own billing database, and other validators run a lite auditor package against exported audit data. The judges verify the platform's accounting rather than re-run the work. Weights are set at the top of each UTC hour.
chain · hyperparams-2026-09-19.json
commit_reveal_weights_enabled False, weights_rate_limit 100; chain-2026-09-09.json active_validators 14
How often it turns
Emission settles every 360 blocks, about 72 minutes. The score is recomputed hourly at :00 UTC over a rolling one-day window, so a new miner reaches full parity in a day and a misbehaving one phases out in a day. A new registration is immune from deregistration for 5,000 blocks, about 16 hours.
chain · hyperparams-2026-09-19.json
tempo 360, immunity_period 5000
Who buys
Developers and resellers paying per million tokens or per GPU hour. The pricing page lists per-model rates from $0.0245 per million input tokens and confidential GPU time from $1.80 an hour with a one-time deploy fee. The front page shows OpenRouter, Kilo, Fetch.AI, Phala and Pax Historia as logos and claims trillions of tokens a month, undated.
own docs · chutes.ai
Pay per token. No subscription, no minimum, no markup.
What has been gamed
Many hotkeys under one owner: only the top scorer per coldkey is paid, the rest get zero. Manipulated step and token times: resisted with medians over two days. Inflated GPU counts: checked against chute history. Invocations reported as faulty are excluded. In April 2026 the scoring window was cut from seven days to one so that misbehaviour phases out in a day rather than a week.
own docs · chutes.ai
For each coldkey, only the highest-scoring hotkey receives rewards All other hotkeys sharing the same coldkey receive zero score
4 of 7 fields rest on the chain or the code. A manifest is the site's reading of the subnet's program, not a review; each field links its source. All programs · What a field means · Correct a field
What it says
The subnet in its own words: the line the index took from its front door, and what the team has said on the record. All 15 quotes in the map.
Their subnet
Chutes describes itself as serverless, permissionless compute for everyone, a cloud with a fleet of GPUs that must earn its keep.
Chutes is a new subnet coming to bittensor 🚀
Chutes has officially arrived—bringing permissionless AI compute to everyone, right in time for the holidays. Leveraging the same Bittensor network that powers many AI subnets, Chutes opens the door for anyone to run any AI model with minimal setup.
Developers are embracing Chutes for everything from training custom models to real-time inference. Meanwhile, miners benefit from streamlined validation tasks and consistent TAO rewards.
With fundamentals in place and an ever-growing node network, Chutes is on track to redefine decentralized compute at scale.
2,779 GPUs on https://t.co/eYYRnXjXfW with 892 of those being H200s. 5.6 billion tokens per day, not including non-LLM apps. ~40 requests per second sustained. 53 unique apps. Only 64 days online... #bittensor
Bittensor, in their words
Bittensor is described in its own words as a decentralised AI network and an ecosystem of specialised AI systems, closer to the foundation's language than to Steeves's market framing.
Chutes has officially arrived—bringing permissionless AI compute to everyone, right in time for the holidays. Leveraging the same Bittensor network that powers many AI subnets, Chutes opens the door for anyone to run any AI model with minimal setup.
Chutes harnesses the Bittensor ecosystem—a decentralized network of specialized AI systems—to deliver aggregate performance and diversity of capabilities that are difficult to match with traditional centralized approaches.
Chutes is powered by Bittensor, a decentralized AI network - we are Subnet 64.
Chutes broke that cycle and unleashed the power of bittensor in a pretty huge way,
Frames collective revolution cloud door ecosystem fleet
What is said about it
By other voices in the map, verbatim and dated.
Chutes (sn64) is (currently) the top ranked #1 subnet on Bittensor with a $50M~ valuation. If Chutes were a startup, 100% of VCs would price it at a valuation somewhere between 10-20X higher.
Bittensor $TAO has its first $100M subnet, just 9 weeks after dTAO launch. Congrats Chutes (SN64)! Chutes is 'serverless AI' providing 'instant on' AI model hosting (DeepSeek, Mistral, etc.) for 85% less cost than AWS.
What it shows
Explained from zero by the index, from the subnet's own materials, for someone who has never heard of Bittensor.
SN64 Chutes rents out AI model computing power by the request, the way a cloud provider does, except the machines belong to strangers who are paid in the subnet's token.
The commodity, explained from zero
The commodity is inference: asking an already trained AI model a question and getting an answer, sold by the million tokens, the word-pieces those models count, in and out. Chutes hosts open-source models, ones whose files anyone may download, and lets a developer send a request to one web address and get a reply, the same way they would with a big cloud provider. The docs put it in one line: "Chutes is a decentralized, serverless inference platform for open-source AI models." Serverless means the customer never rents or manages a machine; they pay per use.
It has a price because running these models needs expensive graphics processors. The pricing page lists per-model rates, from $0.0245 per million input tokens for a small model to $3.00 in and $15.00 out for a large one, and private GPU time from $1.80 an hour. The stated principle is "No subscription, no minimum, no markup."
Who buys today: the front page claims "Powering Trillions of Tokens per Month," undated, and shows logos for OpenRouter, Kilo, Fetch.AI, Phala and Pax Historia. No customer is quoted.
Why it is on Bittensor at all
The machines are not Chutes' own. They belong to miners, who plug their GPU clusters into the network and are paid in the subnet's token according to how much work they do. Its own comparison, in a file written for AI agents, is that rivals "all rely on centralized cloud providers" while Chutes runs on "a globally distributed GPU pool with no single-cloud dependency." Here the comparison breaks: a cloud provider owns its hardware and signs contracts for the rest, while Chutes only scores strangers and lets the token do the hiring. Whether that is cheaper for the buyer is not stated in dollars anywhere.
How the work gets done
Miners run GPU servers arranged as a Kubernetes cluster, software for running many containers across machines, and host "chutes," the platform's word for a deployable model or workload. The docs say the goal of mining "is to provide as much compute as possible, optimizing for cold start times," the seconds a model takes to wake up. Validators score each miner over a rolling seven days on four weighted measures: compute units 55 percent, successful invocations 25 percent, how many distinct chutes it keeps running 15 percent, and bounties 5 percent. The subnet's emission, its slice of newly minted TAO, is split by those scores, with a rule that a miner running many identities is punished rather than paid more.
How you would know it works
The live model catalog with prices at https://chutes.ai/models and the status page with daily uptime history at https://status.chutes.ai are both public. The endpoint on the front page, https://llm.chutes.ai/v1/chat/completions, can be called with an API key.
What is missing
There is no dated usage number; "trillions of tokens" carries no month. The miner docs disagree with each other: the docs overview still describes GraVal while the miner README says GraVal is no longer supported. No page is written for stakers. The only comparison with rivals sits in llms.txt, a file meant for machines.
Go deeper
- Front door with live endpoint: https://chutes.ai
- Pricing by model and hour: https://chutes.ai/pricing
- Miner scoring weights and anti-gaming: https://chutes.ai/docs/miner-resources/scoring
Sources for this explainer
- https://chutes.ai
- https://chutes.ai/docs
- https://chutes.ai/llms.txt
- https://chutes.ai/pricing
- https://chutes.ai/models
- https://chutes.ai/docs/miner-resources/scoring
- https://chutes.ai/docs/miner-resources/overview
- https://chutes.ai/docs/api-reference/overview
- https://status.chutes.ai
- https://raw.githubusercontent.com/chutesai/chutes-miner/main/README.md
- https://raw.githubusercontent.com/chutesai/chutes-api/main/README.md
Metaphor: a cloud provider whose machines belong to strangers. Every claim is drawn from the evidence set or the subnet's own materials; "(inferred)" marks a conclusion rather than a quote. Corrections.
How legible it is
Four audiences, four questions each, rated on what a first-time reader can find in five minutes. The scale measures findability, not quality.
On-chain identity 7/7- subnet_name
- Chutes
- github_repo
- github.com
- subnet_contact
- support@chutes.ai
- subnet_url
- chutes.ai
- discord
- discord.gg
- description
- Breakthrough Serverless Compute for AI, At Scale.
- additional
- Chutes is a subnet operated by Chutes Global Corp, an International Business Corporation registered in Nevis with registration number C 61974
Stakers and validators●●●●● 4.3
Should I allocate here? · rank 1 of 32 for this audience
Q1What it is●●●●● 5
Chutes is the leading open-source, decentralized compute provider for deploying, scaling and running open-source models in production.
per 1M token and per GPU hour prices on the pricing page
Q2Who it is for●●●●● 4
Powering Trillions of Tokens per Month
undated, logos for OpenRouter, Kilo, FetchAI, Phala and Pax Historia on the front page, no dated figure and no usage dashboard
Q3How it resists gaming or fails●●●●● 4
scoring page with four weighted metrics, a 7 day window and an Anti-Gaming Mechanisms section (multi UID punishment, median rates), two clicks from the docs root, written for miners
Q4Identity and documentation●●●●● 4
identity 7 of 7, github, url and discord resolve, support address matches the help page, no staker page, the chutes-api README tells validators to use a child hotkey rather than run one
Miners●●●●● 3.3
Can I compete, and what wins? · rank 18 of 32 for this audience
Q1What it is●●●●● 3
The goal of mining on chutes is to provide as much compute as possible, optimizing for cold start times
miners host GPU nodes in a kubernetes cluster, no request or response schema
Q2Who it is for●●●●● 3
if you are using a server with 4x a40 GPUs (48GB VRAM), the server must have >= 48 4 = 192 GB of RAM
chutes-miner README requires Intel TDX VMs, no hardware table, registration cost not stated
Q3How it resists gaming or fails●●●●● 4
weights in prose, compute units 55 percent, invocations 25, unique chutes 15, bounties 5, 7 day window, one rewarded hotkey per coldkey, no example numbers, no immunity or deregistration policy
Q4Identity and documentation●●●●● 3
step by step ansible and sek8s guide, repo pushed 2026-08-30, no tagged releases, the docs site overview still describes GraVal and Wireguard while this README says GraVal is no longer supported
Buyers and enterprises●●●●● 4.8
Can I use this today? · rank 1 of 32 for this audience
Q1What it is●●●●● 5
Get your first chute deployed in under 10 minutes!
with a curl example, the front page posts to https://llm.chutes.ai/v1/chat/completions in Python, model catalog at chutes.ai/models
Q2Who it is for●●●●● 5
Pay per token. No subscription, no minimum, no markup.
per model prices per 1M tokens, GPU rates from $1.80 per hour, Plus $10 and Pro $20 plans, Enterprise with contact sales
Q3How it resists gaming or fails●●●●● 4
All services are online
with daily uptime history for website and API, help page lists docs, Discord, support@chutes.ai and a sales form, no SLA or response time
Q4Identity and documentation●●●●● 5
REST reference index with endpoint counts per area, base URL https://api.chutes.ai in llms.txt, support@chutes.ai on the help page matches the chain subnet_contact
Newcomers●●●●● 3.8
What is this and why does it matter? · rank 9 of 32 for this audience
Q1What it is●●●●● 4
Chutes is a decentralized, serverless inference platform for open-source AI models.
one click from the front page, consistent with the chain description, serverless and inference unexplained
Q2Who it is for●●●●● 3
unlike Replicate, Modal, RunPod, fal.ai, or Baseten, which all rely on centralized cloud providers
the only comparison lives in the machine facing llms.txt
Q3How it resists gaming or fails●●●●● 4
live catalog with per token prices, status page with daily uptime, chat app needs sign in, the usage figure on the front page is undated, no dated benchmark
Q4Identity and documentation●●●●● 4
subnet_name matches the site, url resolves, team and docs pages serve as about and learn pages, the description Breakthrough Serverless Compute for AI, At Scale is a headline phrase without a verb
Provenance
How this rating came to be. Verified means the scorer fetched the page and the words are on it; secondhand means concluded from code, absence, or a third party. The link badge is a separate automated check made before publication.
scored by agent a 2026-09-09, rubric v1.0merged 2026-09-09links verified 2026-09-09: 36 live, 1 unreachable, 2 manual
Something wrong? Corrections of fact are applied as they arrive during the window; rating disputes are batched at its close. How to file one · GitHub issue · email.