Getting Started

Quick Start Guide

From zero to first production request: free preview, Starter vs Teams, first API call, and token-settled billing.

8 minUpdated 2026-02-15

Summary

From zero to first production request: free preview, Starter vs Teams, first API call, and token-settled billing.

4 deep-dive sections1 code samples

Quick Start

Create account and generate your first API key.
Run first request in API Explorer.
Use Chat mode for first production prompt.
Track charges and latency in Usage.

What you get immediately

Every new account starts with the Free preview: 5 messages total. No credit card required. When you want ongoing usage, choose Starter for the Auto lane or Teams for manual premium-model access.

OpenAI-style messages format (role + content)
Chat with Auto as the default path
Teams unlocks Compare, Blend, Judge, and manual GPT, Claude, and Gemini Pro access
Unified usage, token visibility, and settled final cost
Optimization and replay workflows for policy tuning

Start simple

Use the free preview to see routing and response metadata. Move to Starter when you want real monthly usage, and only move to Teams when you need manual premium-model control.

Prompt lifecycle

Client

Sends OpenAI-style request

LLMWise API

Auth, validation, policy routing

Model path

Auto/fixed/mesh failover execution

Usage settlement

Plan tokens or add-on credits + latency log

10-minute setup

Create an account in /sign-up and use the 5-message free preview.
Choose Starter if you want ongoing Auto usage, or Teams if you need manual GPT, Claude, and Gemini Pro access.
Generate an API key in /keys.
Open /api-explorer and run your first request.
Open /usage to confirm tokens, resolved model, and settled billing.

First request

curl -X POST https://llmwise.ai/api/v1/chat \
  -H "Authorization: Bearer mm_sk_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "optimization_goal": "balanced",
    "messages": [
      {"role": "user", "content": "Give me a launch checklist for an AI API product."}
    ],
    "stream": true
  }'

What success looks like

In streaming mode, watch for a final done payload including:

finish_reason
resolved_model
prompt_tokens
completion_tokens
credits_charged when add-on or wallet billing applies

Activation path

Start with Chat on Auto, then move to Mesh and Replay once you have enough request history to optimize routing. Only move to Teams if you need premium manual selection or the advanced Compare/Blend/Judge workflows.

Chat API reference Billing and credits Mesh mode tutorial

Docs Assistant

ChatKit-style guided help

Product-scoped assistant for LLMWise docs and API usage. It does not answer unrelated topics.

Dashboard User Guide