Getting Started

Dashboard User Guide

How to use each dashboard section, choose modes, and keep costs predictable.

9 minUpdated 2026-02-15
Summary

How to use each dashboard section, choose modes, and keep costs predictable.

4 deep-dive sections0 code samples
Quick Start
  1. Create account and generate your first API key.
  2. Run first request in API Explorer.
  3. Use Chat mode for first production prompt.
  4. Track charges and latency in Usage.

Dashboard map

Primary product surfaces
Chat
Run prompts with mode controls
Usage
Charged credits, tokens, replay
Credits
Wallet top-up + auto top-up
Settings
BYOK and privacy policies

Mode behavior

ModeDefault chargeWhen to use
Chat1 creditDefault day-to-day prompting
Compare3 creditsChoose best model on the same prompt
Blend4 creditsMerge strengths of multiple models
Judge5 creditsStructured ranking and winner selection
Mesh1 creditFailover path for reliability

Suggested daily workflow

  1. Start in Chat with Auto and Balanced goal.
  2. For critical prompts, run Compare before standardizing.
  3. Use Blend/Judge only for high-value outputs.
  4. Add Mesh chain for reliability-sensitive flows.
  5. Check Usage daily and Replay weekly.

How to read Usage page correctly

  • Charged credits: what user wallet is billed.
  • Latency: request performance for user experience.
  • Tokens: workload profile for model selection decisions.
Trust and clarity

Use charged credits as the customer-facing billing source of truth. Keep provider-cost terms out of end-user billing copy.

Billing and creditsRate limits and reliabilityReplay Lab tutorial
Docs Assistant

ChatKit-style guided help

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

Sign in to ask implementation questions and get runnable snippets.

Sign in to use assistant
Previous
Quick Start Guide
Next
Authentication and API Keys