-
Notifications
You must be signed in to change notification settings - Fork 2
Open
Labels
Complexity: M1-8 hours1-8 hoursPriority: Medium1-3 days1-3 daysType: EnhancementNew feature or requestNew feature or request
Description
Description
vCache should give a cost estimate.
Impact
- Who: End user
- What: Cost estimate
- Why: Value add
Proposed Solution
Stats engine should output approx cost savings based on model and input/output.
Acceptance Criteria
- Followed coding conventions
- Implemented or updated tests
- Input: Model, token input/output
- Output: Cost without cache, Cost with cache,...
Risks & Dependencies
That this works across models
Additional Context
--
Metadata
Metadata
Assignees
Labels
Complexity: M1-8 hours1-8 hoursPriority: Medium1-3 days1-3 daysType: EnhancementNew feature or requestNew feature or request