# Clervo AI Chat Completions

> Clervo AI Chat Completions 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).

Provides OpenAI-compatible chat completions via pay-per-use x402 micropayments, with no separate provider account or API key management required.

## Facts

- Endpoint: POST https://api.clervo.dev/v1/chat/completions
- 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-chat-completions-6275231e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YNfKpgi5TZg75KLAogEAn

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-chat-completions-6275231e -d '<json body>'
```

Example prompt: Ask the allam-2-7b model what idempotency means in the context of payments — I want a concise answer and I'm fine paying the per-call fee via my x402 wallet.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible chat completions with pay-per-use micropayments and no upfront API key or subscription setup. It is ideal for autonomous agents, serverless functions, or applications that want to pay fractionally per call in USDC via x402 rather than managing separate provider accounts. Prefer it over direct OpenAI or Anthropic APIs when you want a single aggregated gateway, minimal credential overhead, and crypto-native billing.

## Known failure modes

- Insufficient USDC balance or failed x402 payment — returns 402 Payment Required
- Invalid or missing messages array — returns 400 Bad Request
- Unsupported model identifier — returns 400 or 404
- Rate limiting or capacity issues — returns 429 Too Many Requests
- Model inference timeout — returns 504 or truncated response

## 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 conforming to the OpenAI chat completion format, including: a unique completion ID, the model used (e.g. clervo/allam-2-7b), the assistant's reply message, finish reason (e.g. 'stop'), and token usage breakdown (prompt, completion, and total tokens).

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "chatcmpl-example",
  "model": "clervo/allam-2-7b",
  "usage": {
   "total_tokens": 2,
   "prompt_tokens": 1,
   "completion_tokens": 1
  },
  "object": "chat.completion",
  "choices": [
   {
    "index": 0,
    "message": {
     "role": "assistant",
     "content": "Idempotency prevents a retry from becoming a second logical operation or charge.",
     "refusal": null
    },
    "logprobs": null,
    "finish_reason": "stop"
   }
  ],
  "created": 0
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/clervo-ai-chat-completions-6275231e/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)