chat-completions-workflow

Calls this project's OpenAI-compatible chat-completions endpoint, the Cloudflare Pages function at functions/cerebras-chat.ts, through a five-step workflow that covers choosing among the seven served models by context window, speed and rate limits, token and batch budgeting, verifying route, authentication and deployment before sending, writing explicit system prompts, and validating replies including truncation and JSON checks. Use when a task must send text to a served model, pick a model from the catalogue, or push a batch of items through the endpoint in one session. Not for running models locally, generating images or audio, or calling endpoints run by other providers.

Version

v1.0.0

Size

17 KB

Updated

2026-10-12

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.