HeyPuter/puter

Investigate & possible fix metering for gemini models search and caching

Open

#3132 opened on May 19, 2026

View on GitHub
 (1 comment) (0 reactions) (1 assignee)JavaScript (41,281 stars) (3,752 forks)batch import
AIBackendTypeScriptenhancementhelp wanted

Description

Newer gemini models support things like grounded searches and timed caching. However openai compatible api might not expose these costs in the input/output tokens the way claude api does.

verify that metering for this is valid, and fix if not

Contributor guide

Tech stack
javascriptnodejs
Domain
backendapi
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
blocked
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Familiarity with Puter's codebaseUnderstanding of OpenAI compatible API meteringKnowledge of Gemini models features
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25
Research direction
Start by examining the existing metering implementation for OpenAI compatible API endpoints, likely in the backend's API handling code. Look for how token counts are calculated for Gemini models and whether search and caching costs are included. Check the Gemini SDK's response for any custom usage fields and compare with Claude's approach mentioned in the issue. If needed, adjust the metering logic to account for these additional costs.