Jimla

Cost Control Plane · Trailing 30 days

…

Total Spend

0 requests

…

Active Savings

projected

…

Cache Hits

no requests yet

…

Tokens Used

0 in / 0 out

Optimization

Savings Breakdown

Conservative estimate from historical patterns — updates as data accumulates

$0.0000

Semantic Cache

Repeated prompts served from cache

$0.0000

Model Routing

Simple requests routed to cheaper models

$0.0000

Compression

Projected

Visibility

Total AI Spend — Org Wide

◎

Connect billing APIs to see your full spend picture

Add OPENAI_BILLING_KEY, ANTHROPIC_BILLING_KEY, or GITHUB_TOKEN to your .env to track spend across all channels.

Proxied spend so far: $0.0000

Spend

Breakdown

No data yet.

Fingerprint	Hits	Total Cost
No repeated prompts yet.

Continuous Optimization

Per-Team Tuning

Reviews usage signals and adjusts optimization settings automatically per team.

No active teams in the selected window. Send some requests first.

Testing

Prompt Lab

Test compression and measure token savings against your chosen provider.

System promptUser prompt

Original promptOptimized prompt

Latest response

Run a test to see the response here.

Savings snapshot

Compression results will appear here.

Prompt comparison

Compare two prompts to measure savings.

Access

API Key Management

Issue team keys that map to upstream provider credentials. Keys are stored encrypted.

Team	User	Provider	Profile	Created
No active keys.

Jimla · jimla.ai · Cost Control Plane