TokenFin
See what your AI coding agents really cost, per prompt
Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.
This is 1 of 503 launches in developer tools for AI coding agents — see how it stacks up on momentum and crowding →
413 other launches read as similar to this one →
Details
- External ID
- 1269873
- Source
- PH
- Company
- —
- Product
- TokenFin
- Website domain
- producthunt.com
- Launched
- Oct. 5, 2026
- Cohort
- —
- Upvotes
- 1
- Upvotes percentile
- 0.3258772542988956
- Tags
- Open Source, Artificial Intelligence, GitHub, Tech
- Fetched at
- Oct. 6, 2026, 1:01 a.m.
- Updated at
- Oct. 6, 2026, 1:01 a.m.
Description
TokenFin shows what your team's AI usage really costs: per prompt, session, developer, model and project. One command (npx tokenfin setup) connects Claude Code, Cowork, OpenCode, Codex and Gemini (beta) through OpenTelemetry. No proxy, so we never touch your API keys. See full prompts and sessions, set per-model limits with alerts at 90%, find waste, and export chargeback or FOCUS CSVs. Subscription usage is shown separately from your real API bill. Free and unlimited.
Enrichment
- Niche
- developer tools for AI coding agents
- Vertical
- Horizontal
- Function
- Observability & eval
- Audience
- Developer
- AI stance
- Not AI
- Project type
- Commercial product
- Normalized one-liner
- token cost tracking for ai coding assistants
- Manually corrected
- False
Could you build this?
Partial While the dashboard is standard, creating an OpenTelemetry instrumentation collector that hooks into proprietary developer CLI tools (Claude Code, Codex, etc.) across environments requires non-trivial observability engineering.
What it would actually take: The system requires an OpenTelemetry (OTel) receiver backend paired with an auto-configuring CLI script that injects environment variables and exporter configs into various local CLI runtime environments. Ingestion requires a scalable timeseries/log storage (e.g., ClickHouse) and an engine that parses diverse token metrics, vendor-specific pricing models, and session traces. The primary complexity lies in standardizing disparate tracing spans across continuously mutating third-party AI CLIs.
Competitors
Other products that read as similar to this one — 413 launches clear the similarity bar, closest 8 shown.
Attention rank: #261 of 414 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 333 days after the earliest competitor.
- Know Your Tokens · ph · 2026-10-04 · 1 upvotes · similarity 0.58
- Tokenflow · ph · 2026-09-17 · 3 upvotes · similarity 0.58
- Tokmeter · ph · 2026-10-08 · 1 upvotes · similarity 0.50
- burn · github · 2026-09-26 · 11 upvotes · similarity 0.50
- TokenTrack · ph · 2026-10-02 · 2 upvotes · similarity 0.50
- claudebill · ph · 2026-09-18 · 63 upvotes · similarity 0.50
- Hydra · hn · 2026-04-21 · 9 upvotes · similarity 0.49
- Tokencap · hn · 2026-04-04 · 7 upvotes · similarity 0.48
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a observability & eval tool for Media & entertainment yet.