# CortexCloud AI Gateway (x402/v1/responses)

> CortexCloud AI Gateway (x402/v1/responses) is a paid API for AI agents from api.cortexcloud.org, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

OpenAI-compatible AI responses endpoint that routes calls to any model or data source, billed per-call in USDC on Base via x402 micropayments — no API keys or subscriptions required.

## Facts

- Endpoint: GET https://api.cortexcloud.org/x402/v1/responses
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cortexcloud-ai-gateway-x402-v1-responses-d9b06cbe
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_kjhLcP7zJdZsyCLbwwyxN

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 cortexcloud-ai-gateway-x402-v1-responses-d9b06cbe
```

Example prompt: Send this prompt to CortexCloud using gpt-4o and pay per-call in USDC — no keys needed: 'Summarize the following product reviews in three bullet points: [reviews text]'.

## When to prefer this

Choose CortexCloud when building AI agents that need to call LLMs without managing API keys, rotating credentials, or paying for subscriptions — especially when the agent should autonomously pay for its own inference using USDC on Base via the x402 protocol. Ideal for multi-tenant agent fleets, serverless AI pipelines, or prototyping scenarios where per-call crypto billing is preferable to flat-rate subscriptions. Prefer this over direct OpenAI/Anthropic APIs when you need a single OpenAI-compatible endpoint that abstracts across multiple models and handles billing via stablecoin micropayments.

## Known failure modes

- Insufficient USDC balance — payment rejected before inference runs
- Invalid or unsupported model name — returns 400 or model-not-found error
- Malformed messages array — OpenAI-compatible validation error
- x402 payment protocol not implemented by caller — payment handshake fails
- Rate limiting or quota exceeded — 429 response
- Model provider downstream outage — 502 or 503 from upstream LLM

## How this service works

OpenAI-compatible AI and data API for agents. Pay per call in USDC on Base via x402 — no API keys, no subscriptions, no lock-in.

## Output

An OpenAI-compatible response object containing the model's generated text completion, including fields like choices, message content, finish_reason, and usage token counts — identical in structure to OpenAI's /v1/responses or /v1/chat/completions output.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string"
  },
  "model": {
   "type": "string"
  },
  "stream": {
   "type": "boolean"
  },
  "instructions": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "format": "application/json",
 "example": {
  "id": "resp_abc",
  "object": "response",
  "output": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cortexcloud-ai-gateway-x402-v1-responses-d9b06cbe/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.cortexcloud.org](https://www.zero.xyz/host/api.cortexcloud.org/llms.txt)