Use when you need an llm chat completion for summaries, extraction or classification from a cheap open model. Do not use for frontier models, tool calling or streaming. Returns JSON with a chat completion from IBM Granite 4.0 Micro on Workers AI, with token usage for 0.002 USDC per thousand tokens, up to 0.03 USDC per call (clients without upto pay the cap). Asynchronous: the paid call returns a jobId and a free pollUrl; typical job time 8000 ms (p95). Category: Inference.

Payment Options