io.net

io.net is a decentralized GPU network for AI compute, built on Solana, that aggregates idle consumer and data-center GPUs (NVIDIA A100, H100, H200, and Blackwell-class) into on-demand, geo-distributed compute clusters orchestrated with the Ray framework. The platform exposes a Web3-native alternative to hyperscaler GPU cloud through several developer-facing surfaces: IO Intelligence (an OpenAI-compatible inference API for 15+ open-source models including Llama 3.3 70B), IO Cloud (Container-as-a-Service and VM-as-a-Service APIs for deploying GPU containers, Ray clusters, Kubernetes clusters, and bare-metal instances), IO Agents (agent and agentic-workflow APIs), IO Explorer (a network analytics API for devices, clusters, and block rewards), IO Worker (the supplier-side onboarding stack), IO ID (the account/wallet hub), and IO Staking. Confidential Compute on Intel TDX-enabled H100/H200/B200 GPUs and a remote attestation service for Intel TDX and NVIDIA H200 confidential VMs round out the security surface. The IO token is an SPL token on Solana used for settlement, staking, and rewards; fiat and USDC payments are accepted and converted to IO. io.net also publishes an MCP server at mcp.io.solutions for agent-driven cluster provisioning. The platform's tagline is "the open-source AI infrastructure platform" and its commercial pitch is AI compute at 50–70% below comparable hyperscaler rates.

io.net publishes 8 APIs on the APIs.io network. Tagged areas include Artificial Intelligence, GPU, Decentralized Compute, DePIN, and Web3.

io.net’s developer surface includes developer portal, documentation, getting-started guide, API reference, signup flow, developer console, engineering blog, and 28 more developer resources.

🌐 Visit website 📡 Source on GitHub

35.6/100 thin ▬ flat Agent 3/100 human only open core · MIT Full breakdown ↓
scored 2026-09-14 · rubric v0.22.0

8 APIs 17 Features

Artificial Intelligence GPU Decentralized Compute DePIN Web3 Solana Inference LLM Distributed Computing Ray Kubernetes ContainersConfidential ComputeAgents MCP

Kin Score

Kin Score How this is scored →
scored 2026-09-14 · rubric v0.22.0

Composite quality — 35.6/100 · thin

Contract Quality 0.0 / 23

Developer Ergonomics 10.3 / 18

Access Clarity 6.2 / 18

Operational Transparency 3.4 / 12

Contract Governance 0.0 / 11

Discoverability 5.8 / 9

Open Source Surface 10.0 / 10

Agent readiness — 3/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Open Source Surface applies to this provider. This product is open source and we read its repository directly, so Open Source Surface carries 10 points of the composite. It is scored from what the repository actually publishes — a security policy, a contribution guide, a release history, a code of conduct — read live from the provider rather than inferred from our own catalog pointers. This facet adds; nothing was taken away to make room for it. An open-source project is not excused from the commercial facets, because exemption would strip it of the points it does earn. If we have the wrong repository, or this product is not open source, say so on your provider repo and we will drop the facet rather than have you publish against it.

Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.

The six quality facets above are damped to 90 points between them, because the conditional facet above carries the other 10. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 90% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/io-net: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Standards implemented 1

Interfaces this provider implements that became standards by being copied rather than ratified. Each is profiled by the API Commons, and the evidence column says how the claim was established — not that it was made.

The OpenAI Interface

prose — states compatibility; nothing published to check it against

2 core of 338 operations graded · api-commons/models

APIs 8

Individual APIs this provider publishes, each with its own machine-readable definition.

IO Intelligence API

OpenAI-compatible inference API for open-source AI models hosted on io.net's decentralized GPU network. Exposes /v1/models and /v1/chat/completions over the base URL https://api...

IO Agents API

REST API for discovering, configuring, and running AI agents and agentic workflows on io.net's no-code workflow editor. Supports agent discovery, workflow execution, workflow-sc...

IO Cloud Container-as-a-Service API

Container-as-a-Service REST API for deploying GPU-backed containers across io.net's decentralized network. Operations include container deployment and termination, real-time log...

IO Cloud VM-as-a-Service API

VM-as-a-Service REST API for provisioning, extending, and terminating GPU virtual machines on io.net. Surfaces hardware availability and pricing, supports multi-VM cluster orche...

IO Explorer API

Network analytics API exposing device summaries and detailed metrics, block-reward analysis, proof-of-work challenge tracking, and device notifications. Powers the public IO Exp...

IO Sub-API Key Management API

Administrative API for creating scoped sub-API keys with per-model restrictions and per-key credit limits, tracking usage and aggregated spend, and revoking keys. Designed for t...

IO Cloud MCP Server

Hosted Model Context Protocol server at https://mcp.io.solutions/mcp that exposes IO Cloud provisioning and management tools to MCP-aware agents (Claude Desktop, Claude Code, Cu...

Confidential Compute Attestation Agent API

Open-source FastAPI remote attestation service for Intel TDX and NVIDIA H200 confidential VMs operating on the io.net network. Issues verifiable cryptographic attestations that ...

Scroll for all 8

Features 17

Notable capabilities this provider offers.

IO Intelligence — OpenAI-compatible inference API for 15+ open-source models including Llama 3.3 70B

IO Cloud — decentralized GPU compute spanning Container-as-a-Service, Ray clusters, Kubernetes clusters, and bare-metal

IO Agents — agentic workflow builder with no-code visual editor and Agents API

IO Explorer — network analytics, device and cluster metrics, block-reward tracking, proof-of-work transparency

IO Worker — supplier-side onboarding for GPU providers across Ubuntu, Windows, macOS, HiveOS

IO ID — unified user dashboard for wallets, credits, usage, and withdrawals

IO Staking — device-owner staking plus collaborative co-staking with reliability scoring

Confidential Compute on Intel TDX-enabled H100/H200/B200 GPUs with remote attestation

Confidential Inference with cryptographic proof of secure execution

MCP server at mcp.io.solutions for agent-driven IO Cloud provisioning

Built on Solana — IO is an SPL token; fiat and USDC payments accepted and converted to IO

Ray framework orchestration for distributed AI workloads

Sub-API keys with per-model restrictions and per-key credit limits

Vision (image upload) and reasoning content supported on IO Intelligence

OpenAI SDK drop-in compatibility (`openai` Python / Node) with custom base_url

Stripe / fiat credit-card billing alongside crypto settlement

Pitched at 50–70% below hyperscaler GPU pricing

Scroll for all 17

Security Posture 1

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Io Net Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

Portal

GettingStarted

Signup

Console

Documentation 4

Reference material describing how the API behaves

ContributionGuide

Documentation

Documentation

APIReference

Build 7

SDKs, sample code, and the tooling you integrate with

CodeOfConduct

CodeOfConduct

GitHubOrganization

SourceCode

SourceCode

SourceCode

SourceCode

SourceCode

Scroll for all 7

Access & Security 5

Authentication, authorization, and security posture

SecurityPolicy

DomainSecurity

APIKeys

Token

Tokenomics

Operate 3

Status, limits, changes, and where to get help

IssueTracker

IssueTracker

Releases

Releases

Discord

Discord

Commercial 3

Pricing, plans, and the legal terms of use

License

License

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 4

The organization behind the API

Website

Website

Blog

Blog

Twitter

Twitter

LinkedIn

Other 5

Properties that don't map to a standard resource type

Intelligence

Cloud

Explorer

Medium

Staking

Source (apis.yml)

aid: io-net
name: io.net
description: 'io.net is a decentralized GPU network for AI compute, built on Solana, that aggregates idle consumer and data-center
  GPUs (NVIDIA A100, H100, H200, and Blackwell-class) into on-demand, geo-distributed compute clusters orchestrated with the
  Ray framework. The platform exposes a Web3-native alternative to hyperscaler GPU cloud through several developer-facing
  surfaces: IO Intelligence (an OpenAI-compatible inference API for 15+ open-source models including Llama 3.3 70B), IO Cloud
  (Container-as-a-Service and VM-as-a-Service APIs for deploying GPU containers, Ray clusters, Kubernetes clusters, and bare-metal
  instances), IO Agents (agent and agentic-workflow APIs), IO Explorer (a network analytics API for devices, clusters, and
  block rewards), IO Worker (the supplier-side onboarding stack), IO ID (the account/wallet hub), and IO Staking. Confidential
  Compute on Intel TDX-enabled H100/H200/B200 GPUs and a remote attestation service for Intel TDX and NVIDIA H200 confidential
  VMs round out the security surface. The IO token is an SPL token on Solana used for settlement, staking, and rewards; fiat
  and USDC payments are accepted and converted to IO. io.net also publishes an MCP server at mcp.io.solutions for agent-driven
  cluster provisioning. The platform''s tagline is "the open-source AI infrastructure platform" and its commercial pitch is
  AI compute at 50–70% below comparable hyperscaler rates.'
url: https://raw.githubusercontent.com/api-evangelist/io-net/refs/heads/main/apis.yml
deliveryModel:
  model: open-core
  license: MIT
  open_source: true
  commercial: true
  callable_host: false
  label: Open core · an OSS project plus a commercial hosted product
  confidence: high
  source:
  - license
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source: []
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/io-net.png
tags:
- Artificial Intelligence
- GPU
- Decentralized Compute
- DePIN
- Web3
- Solana
- Inference
- LLM
- Distributed Computing
- Ray
- Kubernetes
- Containers
- Confidential Compute
- Agents
- MCP
tags_raw:
- AI
- Artificial Intelligence
- GPU
- Decentralized Compute
- DePIN
- Web3
- Solana
- Inference
- LLM
- Distributed Computing
- Ray
- Kubernetes
- Containers
- Confidential Compute
- Agents
- MCP
created: '2026-05-25'
modified: '2026-05-25'
specificationVersion: '0.23'
apis:
- aid: io-net:io-intelligence-api
  name: IO Intelligence API
  description: OpenAI-compatible inference API for open-source AI models hosted on io.net's decentralized GPU network. Exposes
    /v1/models and /v1/chat/completions over the base URL https://api.intelligence.io.solutions/api/v1, accepts Bearer-token
    authentication, and supports streaming, vision (image upload), reasoning content, and a shared usage pool across 15+ models
    including meta-llama/Llama-3.3-70B-Instruct. Designed as a drop-in replacement for the OpenAI SDK — install `openai` (Python
    or Node.js) and point base_url at api.intelligence.io.solutions.
  humanURL: https://io.net/docs/guides/intelligence/io-intelligence-apis
  baseURL: https://api.intelligence.io.solutions/api/v1
  tags:
  - Artificial Intelligence
  - Inference
  - LLM
  - OpenAI-Compatible
  - Chat Completions
  - Vision
  - Streaming
  tags_raw:
  - AI
  - Inference
  - LLM
  - OpenAI-compatible
  - Chat Completions
  - Vision
  - Streaming
  properties:
  - type: Documentation
    url: https://io.net/docs/guides/intelligence/io-intelligence-apis
  - type: Documentation
    url: https://io.net/docs/reference/ai-models/get-started-with-io-intelligence-api
  - type: Portal
    url: https://ai.io.net
  - type: Signup
    url: https://ai.io.net/ai/api-keys
  - type: Authentication
    url: https://io.net/docs/guides/intelligence/io-intelligence-apis
- aid: io-net:io-agents-api
  name: IO Agents API
  description: REST API for discovering, configuring, and running AI agents and agentic workflows on io.net's no-code workflow
    editor. Supports agent discovery, workflow execution, workflow-schema retrieval, and CRUD on per-agent secrets.
  humanURL: https://io.net/docs/guides/intelligence
  tags:
  - Artificial Intelligence
  - Agents
  - Workflows
  - Automation
  tags_raw:
  - AI
  - Agents
  - Workflows
  - Automation
  properties:
  - type: Documentation
    url: https://io.net/docs/guides/intelligence
  - type: Documentation
    url: https://io.net/docs/guides/clouds/agent-cloud
- aid: io-net:io-cloud-caas-api
  name: IO Cloud Container-as-a-Service API
  description: Container-as-a-Service REST API for deploying GPU-backed containers across io.net's decentralized network.
    Operations include container deployment and termination, real-time log streaming, replica availability and capacity checks
    per GPU hardware type, deployment configuration updates, and price estimation. Backed by the same orchestration layer
    that powers IO Cloud's Ray and Kubernetes options.
  humanURL: https://io.net/docs/guides/clouds/io-cloud
  tags:
  - GPU
  - Containers
  - CaaS
  - Deployment
  - Distributed Computing
  properties:
  - type: Documentation
    url: https://io.net/docs/guides/clouds/io-cloud
  - type: Documentation
    url: https://docs.io.net/docs/start-using-io-cloud
- aid: io-net:io-cloud-vmaas-api
  name: IO Cloud VM-as-a-Service API
  description: VM-as-a-Service REST API for provisioning, extending, and terminating GPU virtual machines on io.net. Surfaces
    hardware availability and pricing, supports multi-VM cluster orchestration, and exposes job history for billing and audit.
  humanURL: https://io.net/docs/guides/clouds/io-cloud
  tags:
  - GPU
  - VMs
  - Compute
  - Bare Metal
  - Cluster
  tags_raw:
  - GPU
  - VMs
  - Compute
  - Bare Metal
  - Clusters
  properties:
  - type: Documentation
    url: https://io.net/docs/guides/clouds/io-cloud
  - type: Documentation
    url: https://docs.io.net/docs/deploy-ray-cluster
- aid: io-net:io-explorer-api
  name: IO Explorer API
  description: Network analytics API exposing device summaries and detailed metrics, block-reward analysis, proof-of-work
    challenge tracking, and device notifications. Powers the public IO Explorer dashboard and is suitable for partner monitoring
    and on-chain reward attestation.
  humanURL: https://explorer.io.net
  tags:
  - Analytics
  - Monitoring
  - DePIN
  - Block Rewards
  - Proof of Work
  properties:
  - type: Documentation
    url: https://io.net/docs
  - type: Dashboard
    url: https://explorer.io.net
- aid: io-net:io-sub-api-key-api
  name: IO Sub-API Key Management API
  description: Administrative API for creating scoped sub-API keys with per-model restrictions and per-key credit limits,
    tracking usage and aggregated spend, and revoking keys. Designed for teams and partners reselling or proxying io.net inference.
  humanURL: https://ai.io.net/ai/api-keys
  tags:
  - Administrative
  - APIKeys
  - Access Control
  - FinOps
  tags_raw:
  - Administrative
  - API Keys
  - Access Control
  - FinOps
  properties:
  - type: Documentation
    url: https://io.net/docs/guides/intelligence/io-intelligence-apis
  - type: Portal
    url: https://ai.io.net/ai/api-keys
- aid: io-net:io-cloud-mcp-server
  name: IO Cloud MCP Server
  description: Hosted Model Context Protocol server at https://mcp.io.solutions/mcp that exposes IO Cloud provisioning and
    management tools to MCP-aware agents (Claude Desktop, Claude Code, Cursor, etc.). Authenticates via the `x-api-key` header
    using an io.net API key with io-cloud project scope.
  humanURL: https://io.net/docs/guides/clouds/agent-cloud
  baseURL: https://mcp.io.solutions/mcp
  tags:
  - MCP
  - Agents
  - GPU
  - Tool Use
  properties:
  - type: Documentation
    url: https://io.net/docs/guides/clouds/agent-cloud
- aid: io-net:cc-attestation-agent-api
  name: Confidential Compute Attestation Agent API
  description: Open-source FastAPI remote attestation service for Intel TDX and NVIDIA H200 confidential VMs operating on
    the io.net network. Issues verifiable cryptographic attestations that a workload is running inside a Trusted Execution
    Environment with the expected firmware and GPU state. Source published at github.com/ionet-official/cc-attestation-agent-api
    under MIT.
  humanURL: https://github.com/ionet-official/cc-attestation-agent-api
  tags:
  - Confidential Compute
  - Attestation
  - Security
  - Intel TDX
  - NVIDIA H200
  - TEE
  properties:
  - type: SourceCode
    url: https://github.com/ionet-official/cc-attestation-agent-api
  - type: Documentation
    url: https://io.net/docs
common:
- type: IssueTracker
  url: https://github.com/ionet-official/cc-attestation-agent-api/issues
- type: Releases
  url: https://github.com/ionet-official/cc-attestation-agent-api/releases
- type: SecurityPolicy
  url: https://github.com/ionet-official/cc-attestation-agent-api/blob/main/SECURITY.md
- type: CodeOfConduct
  url: https://github.com/ionet-official/cc-attestation-agent-api/blob/main/CODE_OF_CONDUCT.md
- type: ContributionGuide
  url: https://github.com/ionet-official/cc-attestation-agent-api/blob/main/CONTRIBUTING.md
- type: License
  name: MIT
  url: https://github.com/ionet-official/cc-attestation-agent-api/blob/main/LICENSE
- type: DomainSecurity
  url: security/io-net-domain-security.yml
- type: Website
  url: https://io.net
- type: Portal
  url: https://io.net
- type: Documentation
  url: https://io.net/docs
- type: Documentation
  url: https://docs.io.net
- type: GettingStarted
  url: https://io.net/docs
- type: APIReference
  url: https://io.net/docs/reference/ai-models/get-started-with-io-intelligence-api
- type: Intelligence
  url: https://io.net/intelligence
- type: Cloud
  url: https://io.net/cloud
- type: Explorer
  url: https://explorer.io.net
- type: Signup
  url: https://ai.io.net
- type: Console
  url: https://ai.io.net
- type: APIKeys
  url: https://ai.io.net/ai/api-keys
- type: GitHubOrganization
  url: https://github.com/ionet-official
- type: SourceCode
  url: https://github.com/ionet-official/cc-attestation-agent-api
- type: SourceCode
  url: https://github.com/ionet-official/io-net-official-setup-script
- type: SourceCode
  url: https://github.com/ionet-official/io_launch_binaries
- type: SourceCode
  url: https://github.com/ionet-official/docs
- type: SourceCode
  url: https://github.com/ionet-official/io-ray-serve-chat-demo
- type: Blog
  url: https://io.net/blog
- type: Twitter
  url: https://twitter.com/ionet
- type: LinkedIn
  url: https://www.linkedin.com/company/io-net
- type: Medium
  url: https://ionet.medium.com
- type: Discord
  url: https://discord.gg/ionet
- type: Token
  url: https://io.net/token
- type: Tokenomics
  url: https://io.net/token
- type: Staking
  url: https://io.net/staking
- type: TermsOfService
  url: https://io.net/terms
- type: PrivacyPolicy
  url: https://io.net/privacy
- type: Features
  data:
  - IO Intelligence — OpenAI-compatible inference API for 15+ open-source models including Llama 3.3 70B
  - IO Cloud — decentralized GPU compute spanning Container-as-a-Service, Ray clusters, Kubernetes clusters, and bare-metal
  - IO Agents — agentic workflow builder with no-code visual editor and Agents API
  - IO Explorer — network analytics, device and cluster metrics, block-reward tracking, proof-of-work transparency
  - IO Worker — supplier-side onboarding for GPU providers across Ubuntu, Windows, macOS, HiveOS
  - IO ID — unified user dashboard for wallets, credits, usage, and withdrawals
  - IO Staking — device-owner staking plus collaborative co-staking with reliability scoring
  - Confidential Compute on Intel TDX-enabled H100/H200/B200 GPUs with remote attestation
  - Confidential Inference with cryptographic proof of secure execution
  - MCP server at mcp.io.solutions for agent-driven IO Cloud provisioning
  - Built on Solana — IO is an SPL token; fiat and USDC payments accepted and converted to IO
  - Ray framework orchestration for distributed AI workloads
  - Sub-API keys with per-model restrictions and per-key credit limits
  - Vision (image upload) and reasoning content supported on IO Intelligence
  - OpenAI SDK drop-in compatibility (`openai` Python / Node) with custom base_url
  - Stripe / fiat credit-card billing alongside crypto settlement
  - Pitched at 50–70% below hyperscaler GPU pricing
  sources:
  - https://io.net/docs
  - https://io.net/docs/guides/intelligence/io-intelligence-apis
  - https://io.net/docs/guides/clouds/io-cloud
  - https://io.net/docs/guides/clouds/agent-cloud
  - https://io.net/intelligence
  - https://github.com/ionet-official
  updated: '2026-05-25'
position: Consuming
kind: contract
access: 3rd-Party
maintainers:
- FN: Kin Lane
  email: info@apievangelist.com
  X: apievangelist
  url: https://apievangelist.com

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/io-net"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/io-net/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/io-net/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.