canonical: https://jentic.com/apis/aex402.com/aex402

# Aex402 rpc.aex402.com

The AEX402 API is a multi-chain RPC proxy and an OpenAI-compatible AI inference proxy, both paid with x402 micropayments. It routes JSON-RPC calls to Solana and many EVM chains, including Ethereum, Base, and HyperEVM, through per-chain endpoints you can point a wallet at, and it serves OpenAI-style chat completions and a models list. It also manages wallet-signed API keys and can spawn autonomous trading agents backed by their own burner wallets.

## For AI agents

Proxy JSON-RPC to Solana and EVM chains and run OpenAI-compatible inference, paid per call with x402, with wallet-signed key management.

## Scope

Does not custody long-term funds, run a wallet interface, or settle fiat payments. Use for proxying multi-chain RPC and AI inference with x402 micropayments only.

## Capabilities

- Proxy JSON-RPC calls to Solana and EVM chains through per-chain endpoints
- Create OpenAI-compatible chat completions and list available models
- Generate, list, and revoke wallet-signed API keys
- Check prepaid credit balance and top up from a confirmed payment
- Spawn and list autonomous trading agents backed by burner wallets
- Read backend status and x402 payment requirements

## Use cases

### Agent-Paid Multi-Chain RPC

An on-chain agent needs RPC access to several networks without holding accounts at each node provider. The AEX402 API routes JSON-RPC to Solana and EVM chains such as Ethereum and Base through per-chain endpoints, settling per call with x402, so the agent points a wallet at one proxy and reaches many chains on prepaid credit.

Example prompt: Send a JSON-RPC balance query to the Base endpoint through the proxy and return the result

### Pay-Per-Call AI Inference

A developer wants OpenAI-compatible inference billed per call instead of a monthly plan. The AEX402 API serves chat completions and a models list on an OpenAI-compatible surface, paid with x402 micropayments, so an agent can run inference against it with the same client it already uses for OpenAI-style APIs.

Example prompt: List the available models, then create a chat completion against the chosen model

### Wallet-Signed Key Management

A team provisions API keys tied to a wallet rather than an account. The AEX402 API generates wallet-signed keys, lists their prefixes, and revokes them, and reports the prepaid credit balance, so an agent can rotate keys and watch spend without a traditional login.

Example prompt: Generate a wallet-signed API key, then check the prepaid credit balance tied to the wallet

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/v1/chat/completions` | Create an OpenAI-compatible chat completion |
| GET | `/v1/models` | List available AI models |
| POST | `/eth` | Ethereum mainnet JSON-RPC proxy |
| POST | `/base` | Base mainnet JSON-RPC proxy |
| POST | `/v1/api-keys` | Generate a wallet-signed API key |
| GET | `/credits` | Check prepaid credit balance |
| POST | `/agents` | Spawn an autonomous trading agent |

## Key resources

- **RPC proxy** — Route JSON-RPC to Solana and EVM chains through per-chain endpoints
- **AI proxy** — Create OpenAI-compatible chat completions and list models
- **API keys** — Generate, list, and revoke wallet-signed API keys
- **Credits** — Check prepaid credit balance and top up from a confirmed payment
- **Agents** — Spawn and list autonomous trading agents with burner wallets

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 55 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 47 / 100
  - Developer Experience & Jentic Compatibility: 55 / 100
  - AI-Readiness & Agent Experience: 46 / 100
  - Agent Usability: 94 / 100
  - Security: 45 / 100
  - AI Discoverability: 62 / 100
- **View full report:** https://jentic.com/apis/aex402.com/aex402/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring AEX402 by hand means handling x402 micropayments, wallet-signed key generation, and per-chain RPC routing yourself. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** You choose which AEX402 operations your agent may call, so it can proxy RPC and run inference while the trading-agent and key-revocation operations stay out of the set unless you add them.
- **Credential handling:** Your AEX402 key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'proxy an RPC call to an EVM chain' or 'create a chat completion', and Jentic returns the matching AEX402 operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Alchemy** — Alchemy is a hosted multi-chain node and RPC provider; AEX402 is a per-call RPC proxy paid with x402 micropayments.
- **QuickNode** — QuickNode sells managed RPC endpoints per chain; AEX402 proxies many chains behind one endpoint on prepaid credit.
- **OpenRouter** — OpenRouter routes OpenAI-compatible inference across many model providers; AEX402 adds chain RPC alongside its inference proxy.

## FAQ

### What authentication does the AEX402 API use?

The AEX402 API accepts a bearer token in the Authorization header and session or wallet API-key headers, per its OpenAPI spec. Several endpoints, such as health, credit balance, and the chain RPC proxies, are described as free. Paid operations settle with x402 micropayments. Through Jentic the credential is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's context.

### Can I use AEX402 for both RPC and AI inference?

Yes. The API routes JSON-RPC to Solana and EVM chains through per-chain endpoints you can point a wallet at, and it serves OpenAI-compatible chat completions and a models list from the same service. An agent can reach both the chain proxies and the inference proxy through one integration.

### What are the rate limits for the AEX402 API?

The OpenAPI spec does not state fixed numeric rate limits, and it exposes a status endpoint reporting the current pricing and limit configuration. Check the AEX402 documentation at https://rpc.aex402.com/llms.txt for the current limits.

### How do I proxy an RPC call through Jentic?

Import the AEX402 API from the Jentic directory and give your agent an intent such as 'proxy an RPC call to an EVM chain'. Jentic returns the matching proxy operation with its input schema, your agent sends the JSON-RPC request, and your stored key is injected at execution time. To run it on your own infrastructure, install Jentic One from its GitHub repo.

### Can I limit what my agent is allowed to do with the AEX402 API?

Yes. Write a rule that allows only the RPC-proxy and inference operations, so your agent can query chains and run completions while the trading-agent and key-revocation operations stay out of the set unless you add them, and every call it makes is logged.

### Is there an AEX402 MCP server?

You don't need an MCP server to give your agent the AEX402 API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it, so no extra server's tool definitions sit in the agent's context.