io.net

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
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- 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: '0.20'
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:
  - 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:
  - 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
  - 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
  - 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: 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