Cookbooks

• Use the OpenAI SDK

  1. Install the SDK: pip install openai (Python) or npm i openai (Node.js) 2. Set base_url to https://api.onefast.ai/v1 3. Set api_key to your key…

• Use Claude Code

  Point Claude Code at the platform’s Anthropic-compatible endpoint: export ANTHROPIC_BASE_URL="https://api.onefast.ai/anthropic" export ANTHROPIC_AUTH_TOKEN="sk-your-api-key" claude Claude Code will then use the platform’s Claude models (claude-sonnet-4-6, claude-opus-4-6,…

• Configure Cursor

  Provider: OpenAI API Key: your key Base URL: https://api.onefast.ai/v1 Model: any model ID, e.g. gpt-4o or claude-sonnet-4-6 That’s it — Cursor will use the…

• Python Batch Calls

  from openai import OpenAI from concurrent.futures import ThreadPoolExecutor client = OpenAI(api_key="sk-...", base_url="https://api.onefast.ai/v1") def ask(text): r = client.chat.completions.create( model="gpt-4o-mini", messages=[{"role": "user", "content": text}], max_tokens=100, )…

• Cost Optimization

  Prefer -mini / -nano / -flash models for simple tasks Use a larger-context model for long documents, a cheaper one for short tasks Set…