Tool detail
LLM inference
LLM inference proxy to GPT-4o-mini: chat completion with optional vision input and structured JSON output.
Categories: LLM inference
Use when
- get a GPT-4o-mini chat completion without an OpenAI API key
- ask a question about up to 2 image URLs (low-detail vision)
- request a structured JSON response via response_format
Not for
- not a model picker — gpt-4o-mini only
- input capped at 16k chars, output at 4096 tokens
Inputs
POST JSON body: model (string, required, gpt-4o-mini), messages (array, required), max_tokens/temperature/top_p/stop/response_format optional
Inputs undocumented: array without items
Endpoint
- Method
POST- URL
https://agent402.tools/api/llm
Payment
- Protocol
- x402
- Listed price
- $0.01 USDC per call on Base
- Payment method
- exact
- Network
- eip155:8453
- Asset
- 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
Listed terms are catalog metadata. The caller supplies inputs and calls the tool outside Onelayer. If payment is required, the caller uses a compatible wallet to pay.
Source
- Directory
- Coinbase x402 Bazaar
- Record
- POST https://agent402.tools/api/llm
- Retrieved
- 2026-09-30T20:37:07.382Z
- Catalog file SHA-256
6837ccddf886f0007cf3727ea9d27faaa5047b51b4f425345c554ce1c271a524- Catalog built
- 2026-09-30T22:31:58.034Z