# AgentServices Inference API

> AgentServices Inference API is a paid API for AI agents from agentservices.to, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-14).

Provides access to GPT-5.x language models via a pay-per-call OpenAI-compatible chat completion API, billed via x402 micropayments on Base.

## Facts

- Endpoint: POST https://agentservices.to/v1/inference
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentservices-inference-api-0fb8c474
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ub-UhvqsXxHY6Q4C-PPnA

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 agentservices-inference-api-0fb8c474 -d '<json body>'
```

Example prompt: Send these messages to gpt-5.4-mini and return the response: system says 'You are a helpful assistant' and user says 'Summarize the key risks of DeFi yield farming in 3 bullet points' — keep it under 300 tokens.

## When to prefer this

Choose this endpoint when your agent needs access to GPT-5-class language models without a direct OpenAI API key or subscription, especially in a crypto-native context where you want per-call billing via USDC micropayments on Base rather than a monthly quota. It is well-suited for autonomous agents that need sporadic, budget-controlled LLM inference without vendor lock-in to OpenAI billing.

## Known failure modes

- Missing or malformed 'messages' array returns a 400 validation error
- Invalid model name not in {gpt-5.4, gpt-5.4-mini, gpt-5.5} causes rejection
- Insufficient USDC balance or failed x402 micropayment returns a 402 Payment Required
- Max tokens exceeded for the selected model returns a context length error
- High temperature values may produce incoherent or unpredictable outputs
- Rate limiting may occur under high concurrency with repeated rapid calls

## How this service works

Paid data APIs for AI agents. Crypto market data, DeFi yields, IP geolocation, dispute resolution, marketing intelligence. Powered by x402 micropayments on Base.

## Output

Returns a chat completion object in OpenAI response format containing the model's generated assistant message, token usage statistics, finish reason, and model identifier used.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "messages"
 ],
 "properties": {
  "model": {
   "type": "string",
   "description": "gpt-5.4, gpt-5.4-mini, or gpt-5.5"
  },
  "messages": {
   "type": "array",
   "description": "Chat messages in OpenAI format [{role, content}]"
  },
  "max_tokens": {
   "type": "integer"
  },
  "temperature": {
   "type": "number"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentservices-inference-api-0fb8c474/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentservices.to](https://www.zero.xyz/host/agentservices.to/llms.txt)