# AgentBanks Inference API

> AgentBanks Inference API is a paid API for AI agents from agentbanks.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Runs LLM inference via a paid AI gateway optimized for autonomous AI agents on the Base blockchain network

## Facts

- Endpoint: POST https://agentbanks.vercel.app/api/inference
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentbanks-inference-api-9c00a9e7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_m3aaDRSneaQf_6KUjNL4W

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentbanks-inference-api-9c00a9e7 -d '<json body>'
```

Example prompt: Ask AgentBanks to generate a response using the gpt-4o model — send this prompt: 'Summarize the risks of DeFi lending in 3 bullet points' with a max of 200 tokens, and bill my agent wallet the $0.01 USDC fee.

## When to prefer this

Choose this endpoint when your AI agent needs LLM inference and operates on the Base blockchain, requires micropayment billing per call via x402/USDC, or needs a crypto-native AI gateway without monthly subscription commitments. Ideal for autonomous agents that self-fund inference costs from an on-chain wallet.

## Known failure modes

- Payment not provided or insufficient USDC (402 Payment Required)
- Invalid or unsupported model name returns an error
- Neither prompt nor messages array provided results in a validation error
- max_tokens exceeds model limit causes truncation or error
- Underlying provider outage causes inference failure
- Rate limiting if too many concurrent requests from same agent

## How this service works

Register agents, route swaps, earn fees. The lowest-fee protocol for autonomous AI agents on Base.

## Output

Returns a JSON object containing the generated text content, the model name used, token usage statistics, the underlying provider name, and a privacy label indicating data handling.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string"
  },
  "prompt": {
   "type": "string",
   "description": "Simple string prompt (alternative to messages)"
  },
  "messages": {
   "type": "array",
   "description": "OpenAI-format messages array"
  },
  "max_tokens": {
   "type": "integer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string"
  },
  "usage": {
   "type": "object"
  },
  "content": {
   "type": "string"
  },
  "privacy": {
   "type": "string"
  },
  "provider": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentbanks-inference-api-9c00a9e7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentbanks.vercel.app](https://www.zero.xyz/host/agentbanks.vercel.app/llms.txt)