# Clervo AI Responses API

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

Runs AI model inference and agent tool calls on-demand via x402 micropayments, without requiring separate provider accounts or API keys

## Facts

- Endpoint: POST https://api.clervo.dev/v1/responses
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/clervo-ai-responses-api-f7fea95e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_aDc5xWdBWNftEDAM14MQK

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-responses-api-f7fea95e -d '<json body>'
```

Example prompt: Using Clervo, send the message 'Explain what idempotency means in distributed systems' to the clervo/allam-2-7b model and give me the response — pay per call, no API key setup needed.

## When to prefer this

Choose Clervo when your software or agent needs to call AI models without managing separate API keys or provider accounts, and when per-call micropayment billing via x402/USDC is preferred over monthly subscriptions. Ideal for autonomous agents that need to pay for LLM calls programmatically, serverless functions making occasional AI calls, or multi-tenant applications where billing per inference is more suitable than flat-rate plans.

## Known failure modes

- Payment failure: insufficient USDC balance or x402 payment not accepted, resulting in 402 status
- Model not found: invalid model name returns an error in the error field
- Rate limiting or quota exceeded on the underlying model provider
- Malformed request body causing validation errors
- Max output tokens reached, returning incomplete_details in the response
- Tool invocation failure if tool definitions are misconfigured

## 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

A JSON response object containing the generated text output, the model used, token usage breakdown (input, output, cached, reasoning tokens), response status, output message array with role and content, tool call results if tools were invoked, and metadata like response ID and timestamps.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "resp_example",
  "text": {
   "format": {
    "type": "text"
   }
  },
  "error": null,
  "model": "clervo/allam-2-7b",
  "store": false,
  "tools": [],
  "top_p": 1,
  "usage": {
   "input_tokens": 1,
   "total_tokens": 2,
   "output_tokens": 1,
   "input_tokens_details": {
    "cached_tokens": 0
   },
   "output_tokens_details": {
    "reasoning_tokens": 0
   }
  },
  "object": "response",
  "output": [
   {
    "id": "msg_example",
    "role": "assistant",
    "type": "message",
    "status": "completed",
    "content": [
     {
      "text": "Idempotency keeps retries from becoming a second logical operation or charge.",
      "type": "output_text",
      "annotations": []
     }
    ]
   }
  ],
  "status": "completed",
  "metadata": {},
  "reasoning": {
   "effort": null,
   "summary": null
  },
  "created_at": 0,
  "truncation": "disabled",
  "temperature": 1,
  "tool_choice": "auto",
  "completed_at": 0,
  "instructions": null,
  "max_output_tokens": 64,
  "incomplete_details": null,
  "parallel_tool_calls": true,
  "previous_response_id": null
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/clervo-ai-responses-api-f7fea95e/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)