# model-api.xyz Chat Completions

> model-api.xyz Chat Completions is a paid API for AI agents from model-api.xyz, paid per call via x402, $0.001/call, status down (last checked 2026-09-15).

Provides a chat completions endpoint for generating AI language model responses, accessible via micropayment (x402 protocol).

## Facts

- Endpoint: POST https://model-api.xyz/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/model-api-xyz-fe8685b4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wxqGVCsE9hmGQ8NHOWL-q

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 model-api-xyz-fe8685b4 -d '<json body>'
```

Example prompt: Send this conversation to model-api.xyz's chat completions endpoint and get a response: system says 'You are a helpful assistant', user says 'What are the three laws of thermodynamics?'

## When to prefer this

Prefer this endpoint when you need a pay-per-call AI chat completions API with no subscription, using the x402 micropayment protocol and USDC. Suitable for agents that need lightweight, on-demand LLM access without committing to a monthly plan or managing API keys from major providers.

## Known failure modes

- Payment not included or invalid x402 payment header — returns 402 Payment Required
- Malformed request body or missing required fields (e.g. 'model', 'messages') — returns 400 Bad Request
- Model name not recognized or unavailable — returns 404 or 400
- Rate limit exceeded — returns 429 Too Many Requests
- Service unavailable or overloaded — returns 503
- Insufficient USDC balance to cover the $0.001 per-call fee

## Output

Returns an AI-generated assistant message completing the conversation, along with metadata such as token usage counts and finish reason, following the standard OpenAI-compatible chat completions response format.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/model-api-xyz-fe8685b4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from model-api.xyz](https://www.zero.xyz/host/model-api.xyz/llms.txt)