Chutes

Open coreServerless

Breakthrough Serverless Compute for AI, at Scale.

Homepage Docs Pricing Repository

Scanned 14 Oct 2026 · Schema v5 · features v21

From: $3/mo
Pay-as-you-go token inference and GPU-second custom deployments, plus optional monthly request bundles.
Free tier: No
No card required.
Isolation: Container
shares the host kernel
Regions: 1
worldwide, permissionless miners
Capabilities: 13 / 61
8 partial · 25 fail · 0 not assessed
Agent readiness: 10/11 · 10/11
read · drive, pre-login surface

Advertised for

LLM inference · Custom AI apps (FastAPI chutes) · Image/diffusion models · Speech/video models · Embeddings · Background/batch jobs

Built for

Developers, then technical

· API/SDK/CLI-first (pip install chutes; chutes deploy; OpenAI-compatible base_url) — no GUI builder
· Deep infra vocabulary: GPUs, Docker images, NodeSelector, TEE/TDX attestation, Bittensor/SS58, vLLM/SGLang
· Usage/compute pricing (per-token, per-GPU-second) + crypto top-up

01 Pricing Pay-as-you-go token inference and GPU-second custom deployments, plus optional monthly request bundles.

Tier	EntryPay-as-you-go	Base	Plus	Pro	TopEnterprise
Price	Usage-based	$3/month	$10/month	$20/month	Custom pricing

per token (inference) + per GPU-second/hour (deployed chutes) + per-deploy fee·Card required: No·chutes.ai

Overages: PAYG per-model token rates beyond bundled quotas; Plus discount 6%, Pro 10%; private GPU deployments billed separately.

02 Website design Desktop public website · assessed 14 Oct 2026

Complete assessment.

Dark, spacious AI infrastructure site with oversized pale sans-serif headings, mint pill actions, a rainbow abstract landing visual, terminal-style pricing panels and dense documentation navigation.

Technical illustration
Corporate

Landing page: captured
Pricing: captured
Docs: captured

03 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Containershares the host kernel

Persistence

Ephemeral by default — serverless GPU compute, 'pay only for GPU time actually used', autoscaling (incl. scale-to-zero). Chutes are stateless FastAPI apps; durable state is the user's responsibility (no documented first-class persistent volume on the public surface).

Snapshots / forks

fail

Resources & limits

Storage

Model weights/images handled by the platform; no user-facing object store or persistent volume documented. Inference is stateless; deployed chutes are ephemeral.

Limits & quotas

Per-user quotas; optional monthly request bundles; subscribed usage caps documented in API.

GPU

Yes

Access

Deploy interface

clisdkapicontainer-image

SDK languages

Python

Network & secrets

Egress controls

partial

Secrets

pass

Bring your own cloud

Placement & use

Jurisdiction

Advertised workloads

LLM inferenceCustom AI apps (FastAPI chutes)Image/diffusion modelsSpeech/video modelsEmbeddingsBackground/batch jobs

04 Capabilities 13 pass · 8 partial · 25 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 3/9

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Not supported

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not supported

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Not supported

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Not supported

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Supported

GPU computeGPU-backed instances available.

Supported

Multi-regionCompute placeable in more than one geographic region.

Partially supported

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Supported

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Not applicable

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Not applicable

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not supported

Networking & delivery 1/5

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Supported

Built-in reverse proxyPlatform routes external traffic to workload services.

Partially supported

Custom domainsBring-your-own domain via CNAME/DNS.

Not supported

Public preview URLsShareable per-deploy / per-branch URLs.

Not supported

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not applicable

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Partially supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Not applicable

Email send / receiveSend and/or receive email from the workload.

Not applicable

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not applicable

Developer access 4/7

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Supported

SSH accessDirect SSH into workloads.

Not applicable

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Not applicable

Git deployDeploy from a Git repo / push-to-deploy.

Not supported

Private container registryHosted private image registry.

Not supported

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not supported

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Not applicable

AI & agents 3/11

Built-in coding agentShips a first-party AI coding agent in the product.

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Not supported

MCP serverExposes a Model Context Protocol server for agents.

Supported

MCP clientActs as an MCP client / consumes MCP tools.

Not supported

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Not supported

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Not supported

BYOK for LLMsBring-your-own LLM provider keys.

Not supported

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Supported

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not applicable

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Not supported

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Not supported

Data 0/1

First-party databasePlatform-provided managed database.

Not supported

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Not applicable

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Not applicable

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not applicable

Platform & operations 0/4

Scheduled tasksCron / scheduled job primitive.

Not supported

Durable workflowsDurable execution / long-running workflow primitive.

Partially supported

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Not applicable

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Partially supported

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not applicable

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Partially supported

Organisation & security 2/9

Built-in authPlatform-provided authentication / IAM for workloads.

Partially supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Not supported

SharingShare a running workload/resource via link (optionally gated).

Partially supported

BYOCRuns inside the customer's own cloud account.

Not supported

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not supported

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not supported

Self-host / OSS coreOpen-source core that can be self-hosted.

Supported

Proposed, not verified

Capabilities the scan saw but the registry does not track yet. A key is admitted only once two distinct products exhibit it. These are not scored.

Confidential compute / TEE (Intel TDX + NVIDIA confidential GPUs; hardware-isolated, attestable, operator-blind inference; E2E-encrypted + post-quantum)confidential-compute
“Current public catalogue is all TEE-backed; private deployments use tee=True. Intel TDX and NVIDIA confidential compute with hardware attestation; no new taxonomy key admitted.” chutes.ai
Decentralized compute (permissionless Bittensor miner GPU network — the substrate)decentralized-compute
“Decentralized serverless compute powered by Bittensor; permissionless miner GPU supply. Proposed only; no registry mutation.” chutes.ai
Crypto-native payments (top up balance in $TAO / Bittensor alpha tokens to a per-account SS58 address, on-chain, auto-converted to USD)crypto-payments
“Pay from a Bittensor wallet in TAO; balances converted to USD. Proposed only; no registry mutation.” chutes.ai
Model failover/quality routing on the inference endpoint (default:latency / default:throughput / inline multi-model failover)model-failover-routing
“Toolkit chutes-routing documents model pools, aliases and intra-catalogue routing; this is not a multi-provider gateway.” chutes.ai

05 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

10/11

8 full · 2 partial · 91% of applicable checks

llms.txt
Supported
“Fresh /llms.txt links models, pricing, agent setup, full docs, auth and legal pages.”
llms-full.txt
Supported
“HTTP 200 comprehensive llms-full.txt export; 1247193 bytes, retained via pointer.”
robots.txt AI policy
Supported
“Fresh robots.txt explicitly allows GPTBot, OAI-SearchBot, ClaudeBot and other crawlers, excluding private routes.”
JSON-LD
Partially supported
“Homepage contains one WebSite JSON-LD with Organization publisher, not a rich Product/SoftwareApplication.”
Sitemap
Supported
“Fresh sitemap.xml HTTP 200; 209 URL locations.”
Meta tags
Supported
“Descriptive <title> + meta description + 10 OG tags.”
Markdown negotiation
Not supported
“Docs requested with Accept: text/markdown still returns text/html; no clean negotiation established.”
Content efficiency
Partially supported
“Readable homepage text / HTML bytes = 2.10%, using extracted non-script/style HTML text.”
Docs discoverable
Supported
“First-class docs (chutes.ai/docs) + Swagger (api.chutes.ai/docs) + a knowledge base, all linked.”
Machine-readable pricing
Supported
“GET /pricing returns structured per-GPU JSON; GET /v1/models returns per-token pricing (USD+TAO) — genuinely machine-readable, better than most.”
No anti-bot wall
Supported
“Anonymous public landing, docs, pricing, robots, exports and spec fetched without challenge.”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

10/11

8 full · 2 partial · 91% of applicable checks

Public API
Supported
“Documented REST API (api.chutes.ai) + Swagger UI — full control plane.”
OpenAPI spec
Supported
“Fresh HTTP 200 API OpenAPI JSON, 293083 bytes.”
MCP server
Supported
“Official /agents/mcp documents uv tool install chutes-mcp-server --from local toolkit directory, stdio client configuration and read tools; writes/deploy are BETA.”
SDK packages
Partially supported
“One official deployment SDK language: Python pip install chutes. Generic OpenAI clients are compatible, not multiple official Chutes SDKs.”
Auth documented
Supported
“Authentication API reference and llms.txt document Bearer key authentication and OAuth identity provider.”
Self-serve credentials
Supported
“Fresh OpenAPI lists POST /users/register and /api_keys/; toolkit documents autonomous agent registration. Documentation only, no registration performed.”
Webhooks
Not supported
“Inspected fresh OpenAPI/docs show no signed public webhook integration.”
CLI tool
Supported
“Official `chutes` CLI (deploy/register).”
Error model
Supported
“OpenAPI defines HTTPValidationError and documented 422 JSON validation responses.”
Rate limits documented
Partially supported
“Quota endpoints and request bundles documented, but no comprehensive response-header contract established.”
Agent config files
Supported
“Official agent hub publishes skills, scripts and MCP installation with multiple agent-specific guides.”

06 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 9

Claude Code Anthropic
Supported
“Claude Code and Cowork: setup, plus Claude recipes”
Source chutes.ai
Codex CLI OpenAI
Supported
“Codex: guide-only setup, plus Codex recipes”
Source chutes.ai
Cursor Anysphere
Supported
“Cursor, Cline, Aider: editor agents”
Source chutes.ai
Cline Cline
Supported
“Cursor, Cline, Aider: editor agents”
Source chutes.ai
Aider Aider
Supported
“Cursor, Cline, Aider: editor agents”
Source chutes.ai
Kilo Code Kilo
Supported
“Confirmed live integrations: LiteLLM, Vercel AI SDK, LangChain, Cline, Kilo Code, Roo Code, Cursor, Aider, MCP.”
Source chutes.ai
Roo code
Supported
“Confirmed live integrations: LiteLLM, Vercel AI SDK, LangChain, Cline, Kilo Code, Roo Code, Cursor, Aider, MCP.”
Source chutes.ai
Hermes Agent Nous Research
Supported
“Hermes: setup, plus Hermes recipes”
Source chutes.ai
OpenClaw Peter Steinberger
Supported
“OpenClaw: provider setup [BETA], doc-derived. Compatibility documented, not exercised in this scan.”
Source chutes.ai

Plausible compatibility 0

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

No general shell access documented, so nothing is derived. Absence is not unsupported.

07 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 1

GDPR
self-attestedhosted
“This agreement ensures compliance with applicable data protection laws, including the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA).”
Source chutes.ai

Regions 1

worldwide, permissionless minersDecentralized global miner network (Bittensor)

Compute is supplied by a globally-distributed, permissionless miner network — inherently multi-region but with NO user-facing region selection or data-residency control (a trade-off of the decentralized model; live node/utilization data at chutes.ai/app/research/nodes). The hosted control plane (api.chutes.ai / llm.chutes.ai) is centralized; the GPU execution is decentralized.

Legal

Privacy notice Terms of service

08 Open source MIT · fetched by machine, not quoted from marketing

Licence & repository

Licence: MITOSI
Primary language: Python
Stars: 28
Forks: 18
Created: 6 Nov 2024
Archived: No

Activity

Last commit: 3 Sep 2026
Latest release: —
Issues open / closed: 9 / 2 · 18% closed

No GitHub releases returned; main last pushed 2026-09-03T16:07:10Z

Fetched via gh on 14 Oct 2026.

Self-hosting

Methods: dockercomposekuberneteshelmansible
You operate: postgreskubernetesgpu

MIT backend API, SDK and miner components are public. README documents docker-compose local development and Helm/Kubernetes deployment; requires platform dependencies and GPU infrastructure. Self-hosting does not provide hosted network GPU capacity. Security architecture identifies private components whose source is not public. Free under MIT plus operator infrastructure; not a turnkey replica of the hosted service. README warns of expensive extensive infrastructure, miner server allocation per validator, and SDK domains defaulting to chutes.ai requiring overrides or a fork.

Documentation signals 8/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
SupportedChangelog
SupportedOpenAPI
Supportedllms.txt
SupportedExamples
SupportedArchitecture doc

09 Company & presence Facts only, not scored

Company

Headquarters: Distributed / decentralized (no central HQ)
Founded: 2024 (under Chutes Global Corp; a Bittensor-subnet-native platform)
Team size: 8 named people on current team page; not a total employee headcount.
Hiring: Hiring (actively, via careers)

Notable people

Jon Durbin (backend; known open-source AI/dataset contributor)
Cxmplex (backend)

Activity

Last release: No GitHub releases; main pushed 2026-09-03T16:07:10Z github.com
Last blog post: I let Hermes write its own Chutes config — September 15, 2026 chutes.ai

Presence 7

Links found on the public surface scanned; not an exhaustive search.

10 Sources & method How this entry was produced

Public surface only

Everything here was read from chutes.ai's unauthenticated pages, docs, pricing and repository on 14 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v21
Keys tracked today: 61
Assessed on this entry: 61

Something wrong on this page?

Nearby in the atlas

All Serverless products →