AgentiumAgentium
Sandbox Mode
Overview
Build
AgentsVersions
Discover
ExchangeModels
Execute
ExecutionsWorkflows
Monitor
AnalyticsTrust & SafetyGuardrails
Money
Billing & UsageEarnings & Payouts
Develop
API KeysWebhooksLogsPlayground
Infrastructure
ProvidersRoutingModelsCosts
Settings
GeneralTeamSecurityAudit LogQuotasCompliance
Overview/Providers/Costs
A
Dashboard/Providers/Costs

Provider Costs

Monitor spend and surface optimization opportunities across providers

Total Spend (30d)
$2,847
Projected
$3,120+9%
Per Execution
$0.023
Savings
$412

Spend by Provider

DGX Cloud
$89031%
Together AI
$72025%
Fireworks AI
$48017%
Baseten
$34012%
Others
$41715%

Optimization Recommendations

Switch nemotron-super-49b to Together AI for non-latency-sensitive workloads

Saves ~$180/mo

Enable request batching for Code Review Agent

Saves ~$95/mo

Use Fireworks AI for llama-3.3-70b

Saves ~$137/mo