# Clervo AI Messages API

> Clervo AI Messages API is a paid API for AI agents from api.clervo.dev, paid per call via x402, $0.001/call, status down (last checked 2026-09-15).

Send a chat message to an AI language model via pay-per-use x402 micropayment, without managing provider accounts or API keys

## Facts

- Endpoint: POST https://api.clervo.dev/v1/messages
- Price: $0.001/call
- Payment: x402
- Status: down
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/clervo-ai-messages-api-93ad19b3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_1iPRQBv65hVOL8QZeSpSk

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 clervo-ai-messages-api-93ad19b3 -d '<json body>'
```

Example prompt: Use Clervo to send this message to the allam-2-7b model: 'Explain idempotency in one sentence' — it'll charge per call via x402 so no API key needed.

## When to prefer this

Choose this endpoint when you need LLM inference without managing provider API keys or subscriptions, especially in agent or software contexts where pay-per-use x402 micropayments (USDC) are preferable to flat-rate billing. Ideal for lightweight agent pipelines, prototypes, or multi-tenant systems where provisioning separate provider accounts per user is impractical.

## Known failure modes

- Payment failure: x402 payment not provided or insufficient USDC balance — request rejected before inference
- Invalid model identifier: unrecognized model string returns an error
- Malformed message body: missing required fields returns a 4xx validation error
- Rate limiting: too many concurrent requests may be throttled
- Context length exceeded: prompt too long for selected model
- Network timeout: inference takes too long and connection drops

## How this service works

Clervo lets software use AI models and agent tools with pay-per-use x402 payments, without managing separate provider accounts or API keys.

## Output

Returns a JSON object with a message ID, the assistant role, the model used, the generated text content as an array of text blocks, token usage counts for input and output, and a stop reason indicating why generation ended.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "msg_example",
  "role": "assistant",
  "type": "message",
  "model": "clervo/allam-2-7b",
  "usage": {
   "input_tokens": 1,
   "output_tokens": 1
  },
  "content": [
   {
    "text": "Idempotency keeps retries from becoming a second logical operation or charge.",
    "type": "text"
   }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/clervo-ai-messages-api-93ad19b3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.clervo.dev](https://www.zero.xyz/host/api.clervo.dev/llms.txt)