LLM API

LLM API offers pay per call inference on a curated set of frontier models. OpenAI compatible chat completions, Anthropic native messages, the Responses API, and embeddings, billed by exact token usage. Responses are non streaming; set stream to false. The full model catalog is available with an LLM API account at llmapi.ai. This server is a transparent proxy in front of LLM API's own API that sells access on plans (credit or subscription) rather than per call: call the upstream API's paths here and the proxy handles identity, payment, and proxying. Agents can purchase autonomously or with their human's approval. No seller API operations have been verified for this document; consult the upstream API reference. The live catalog at /manifest.json is authoritative for prices and any free included units (prices[].includedUnits).