Flat-rate LLM
llm_completionLLM inference at a flat $0.001 per call - no token metering, no surge. POST a prompt, get the completion. Same price for 10 tokens or 4000, while metered gateways scale with usage. Automatic failover across several large models; typical response under 1s. Flat $0.001 per call, paid over x402 (USDC).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The request for the model. Up to 24000 characters. | |
| sistema | No | Optional system instruction. | |
| maxTokens | No | Output token cap, up to 4000. Does not change the price. |