AI Orchestrator | Dashboard

-- Active Models

+12%

-- Healthy Circuits

100%

-- Avg Latency

-8ms

-- Avg Cost/M

-15%

Model Rankings

Top 10

Routing Profiles

Recent Activity

Model sync completed 2 min ago

New model added: gpt-4-turbo 15 min ago

Circuit breaker triggered for model #42 1 hour ago

All Models

Model	Provider	Quality	Latency	Cost/M	Context	Status

Profile Configuration

Weight Visualization

0 Total Requests

0 Total Tokens

$0.00 Estimated Cost

0ms Avg Latency

Request Volume

Usage data will appear here when requests are made

Model Distribution

gpt-4-turbo 42%

claude-3-sonnet 28%

llama-3-70b 18%

Other 12%

Requests by Profile

45%

balanced

25%

quality

20%

speed

10%

budget

Test Prompt

Routing Decision

Enter a prompt to see routing analysis

Checking Ollama...

Connecting to local Ollama service

No Local Models

Install models with Ollama to use local inference

ollama pull llama3.2

Popular Models

Quick Install

Budget Configuration

Advisory

Daily Limit ($) Set to 0 to disable daily limit

Weekly Limit ($) Set to 0 to disable weekly limit

Monthly Limit ($) Set to 0 to disable monthly limit

Alert Threshold (%)

50% 80% 100%

Show warning when spending reaches this percentage

Hard Limit (Block requests when exceeded) When enabled, requests will be rejected if budget is exceeded

Current Spending

Daily OK

$0.00 / $10.00

Weekly OK

$0.00 / $50.00

Monthly OK

$0.00 / $100.00