OpenAI-compatible access
Use a single OpenAI-compatible base URL and API key to call supported models through standard chat-completions style requests.
JellyNet
JellyNet is an agentic API marketplace for buying and selling AI and API access. Buyers use an OpenAI-compatible interface and agent payment flows, while suppliers can earn from unused keys or spare resources.
Overview
JellyNet is an agentic API marketplace for buying and selling access to AI and API resources. Its homepage positions the product as a way for buyers to access LLMs at lower per-token cost while suppliers earn from idle keys or other spare resources.
The public site emphasizes OpenAI-compatible requests, x402-based payment settlement, and a marketplace model that supports both human checkout via Stripe and agent checkout via USDC on Solana. The result is a single interface for request-by-request access to multiple providers and protocols, with usage shown in a ledger-style dashboard.
Key features
Per-call agent payments
Submit requests with x402 payment headers, receive a 402 response, pay in USDC on Solana, and retry with payment proof.
Ledger and budget visibility
See request-level activity in a live ledger with balances, recent requests, and budget tracking shown in the dashboard preview.
Multi-provider marketplace
Work across a broad model and protocol catalog that the site summarizes as 40 protocols across text, image, audio, and embedding.
Tooling compatibility
Connect through common developer tools and SDKs, including the OpenAI SDK, Anthropic SDK, Vercel AI SDK, Cursor, Claude Code, and other OpenAI-compatible clients.
Supplier monetization flow
Let sellers list unused API keys, IP addresses, or spare compute and receive per-request earnings from marketplace usage.
Common use cases
Buyers integrating LLM access
An app or agent can call supported models through a standard OpenAI-compatible endpoint without changing its existing client stack.
Agent-native payment workflows
A builder can send a request, receive a 402 payment-required response, pay with x402, and retry automatically in a single round trip.
Suppliers monetizing idle capacity
A resource owner can list an unused API key or spare compute, set a price in the dashboard, and earn from per-request usage.
Budget tracking and request review
A team can monitor request spend, remaining balance, and recent usage from the dashboard-style ledger view while controlling a budget.
Multi-provider API routing
A developer can access multiple providers and protocols from one marketplace instead of wiring each vendor separately.
Pros and Cons
Pros
- OpenAI-compatible access reduces the need for SDK rewrites in common client workflows.
- Supports both buyer and supplier flows, so the marketplace serves consumption and monetization in one product.
- Per-request settlement and on-chain verification make pricing and payment flow explicit at the request level.
- The site shows compatibility with several popular SDKs and clients, which broadens adoption options.
Cons
- The public pricing page currently returns 404, so plan-level pricing and limits are not clearly published there.
- Some capability details are shown in marketing copy and dashboard screenshots rather than full documentation, so edge cases and operational limits are not fully specified.
- The site mentions 40 protocols and several provider names, but the exact list and any provider-specific constraints are not fully documented in the provided sources.
FAQ
How does JellyNet work for buyers?
JellyNet provides an agentic API marketplace where buyers can access LLMs and other APIs through a single OpenAI-compatible interface and pay per request. The site says agents can use x402 payment flows, while buyers can also use Stripe.
How does JellyNet work for suppliers?
The site describes sellers listing unused API keys, IP addresses, or spare compute in the marketplace. Buyers or agents then consume those resources per request, and suppliers earn from consumed usage.
Do agents need a separate account or SDK rewrite?
The homepage shows an x402 flow where a client receives an HTTP 402 response, pays the exact USDC amount on Solana, and retries the request with payment proof. This suggests agent workflows are supported without a separate account setup in that flow.
What integrations are supported?
The public page says JellyNet works with OpenAI SDK, Anthropic SDK, Vercel AI SDK, Cursor, Claude Code, and any OpenAI-compatible client.
Is there a separate pricing page or published plan list?
The site includes a pricing section on the homepage and a separate pricing URL that currently returns 404, so the available public evidence only confirms per-request settlement and that buyers can start with $1 free credit.
Quick Facts
- Category
- Agentic API marketplace
- Primary users
- API buyers, AI agents, and suppliers with unused API keys or compute
- Payment flow
- Stripe for humans; x402 with USDC on Solana for agents
- API style
- OpenAI-compatible
- Source domain
- jellynet.net
- Marketplace scope
- 40 protocols across text, image, audio, and embedding
Alternatives à JellyNet
AakarDev AI
AakarDev AI helps teams manage AI provider access, project-level setups, logs, and analytics from one dashboard. It supports BYOK workflows and lists providers including OpenAI, Google Gemini, Anthropic, Groq, Mistral AI, and Perplexity AI.
AgentMail
AgentMail is an email inbox API for AI agents that lets developers create, send, receive, and search messages through REST APIs and SDKs. It supports agent workflows such as threaded replies, verification, customer support, scheduling, and inbox-based approvals.
Arduino VENTUNO Q
Arduino VENTUNO Q is an edge AI computer for AI and robotics applications. It combines AI inference and deterministic control on a single board and is designed to work with Arduino App Lab.
Devin
Devin is an AI coding agent and software engineer that helps developers and engineering teams plan and execute complex software tasks. It is available through desktop, cloud, JetBrains, and CLI surfaces, with plans for individuals, teams, and enterprises.
Open Computer Use
Open Computer Use is an open-source Computer Use service wrapped as MCP for macOS, Linux, and Windows. It helps AI agents and MCP clients run desktop automation workflows through client setup commands or manual MCP configuration.
Lasso
Lasso is an ecommerce product data platform for enriching catalog records, processing supplier files, generating product content, and monitoring competitors. It combines a web app with a REST API, SDK, and MCP server for teams and developers.