← All endpoints
agent402.tools api llm
https://agent402.tools/api/llm
answers 402
LLM inference proxy - send an OpenAI-format chat/completions request and get a response from GPT-4o-mini. Supports vision (up to 2 image URLs, low detail) and structured output (response_format: json_object or json_schema). No API key needed; pay per call via x402. Input capped at 16k chars, output at 4096 tokens.
We sent a real
POST request to this endpoint and it
answered 402 with payment requirements we could parse.
- Price
- $0.01
- Network
- base
- Pay to
- 0xaBF4FAbd7c416fB67202E5f9002389Fc75e2a9D0
- Spec dialect
- v2 (declares x402Version 2)
- Transport
- PAYMENT-REQUIRED header
- HTTP method
- POST
- Response latency
- 112 ms
- Payment options
- 13 usable of 13
- Last checked
- 2026-09-06T01:11:32.509Z (19d ago)
- Category
- finance-crypto
Re-check it yourself:
curl "https://api.the402.dev/validate?url=https%3A%2F%2Fagent402.tools%2Fapi%2Fllm"