待翻譯:Show HN: TokenSpend, the AI ROI Solution
AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Token router + receipts Route every model. Read every receipt. One endpoint for Claude, GPT, Gemini and open models. Routing is free. Usage and cost stay visible by engineer. Browse all modelsRead API docsNo provider ke…
AI 服務暫時不可用,以下為來源正文,待恢復後補全翻譯。
Token router + receipts Route every model. Read every receipt. One endpoint for Claude, GPT, Gemini and open models. Routing is free. Usage and cost stay visible by engineer. Browse all modelsRead API docsNo provider key needed to try Live registry Pick the model. Keep the receipt. Live Claude Sonnet 5anthropic/claude-sonnet-5$2/M in1,000K contextGPT-5.6 Lunaopenai/gpt-5.6-luna$0.2/M in1,050K contextGemini 3.5 Flashgoogle/gemini-3.5-flash$1.5/M in1,048K context Provider list price. No markup.52 models 52models live registry 14vendors one endpoint 1.1Mtokens routed observed receipts —p50 latency 0 requests · 24h Spend review See what the spend shipped. TokenSpend joins routed usage to Git branches, commits and pull requests. Shipped, in-flight and unmatched spend stay distinct. Aggregate by default, never an engineer leaderboard. Confidence stays visible on every attribution. Request history included. Zero data retention is one click away. See live demo How it works Spend review March 2026 · Acme Engineering $48.2K Claude spend Mixed confidence $28.4K became shipped code. $9.8K never tied to a merged PR. Shipped HIGH $28.4K 59% · Tied to a merged pull request In flight MED $7.1K 15% · Open PR or inside the attribution window Unmatched LOW $9.8K 20% · No merged PR after 30 days Other LOW $2.9K 6% · Other repositories or non-PR work Sample data. Quick Start produces correlation; the capture plugin upgrades selected teams to SHA-level attribution. How it works 1. Connect GitHub Securely link your repositories through the GitHub App to track what ships. 2. Track AI spend Capture Claude Code usage and cost across your fleet, automatically and zero-touch. 3. Reconcile ROI Match spend to merged pull requests and measure what your AI budget actually shipped. Enterprise features Team-level attribution Spend and shipped rate per team. Aggregate by default, never a per-engineer ranking. TeamSpendShipped Platform$12.4K61% Infrastructure$8.9K54% Growth$5.2K48% Mobile$3.1K57% Automatic PR linking Each captured session resolves to the pull request it shipped in, by branch and SHA. PR #128 Checkout retry logic Shipped PR #131 Dashboard charts In flight PR #126 Spike: vector search Unmatched Security Encrypted in transit and at rest. SSO on Enterprise. SOC-2 is on the roadmap. Privacy first Token counts, timestamps, and git refs leave the machine. Your prompts, code, and transcripts never do. Audit ready Export reconciliation logs for finance and FinOps. Full visibility into how AI spend maps to shipped work. Spend over time Watch the burn, by model See daily Claude spend broken out by model version, with the percent that shipped traced on its own axis. The same chart you get on your dashboard. Spend over time $60,840Last 30 days Daily AI spend (estimated + metered), by model version, against the spend that shipped. Period navigatorHover to scrub · click to pin Scrub the plot or navigator. Click to pin a period. Arrow keys supported Peak day$4,673Jun 18 Daily average$2,028 Shipped in range$27,42545% Spend ($, left)Yield (% shipped, right) Sample data. Start with one repo and one pilot team. View demoGet started