Catch AI API cost regressions before they ship
SpendLint keeps one verified dataset of official LLM API prices, computes what your workload costs from it, and lets your repository declare a budget that CI enforces on every pull request.
A model swap from Claude Sonnet 5 to Claude Opus 5 on 1,000 requests a day (3,000 input, 600 output tokens each) moves the bill from $360.00 to $900.00 per month. A SpendLint budget contract turns that into a failed CI check with the exact delta.
Flagship model prices today
| Model | Input / 1M | Output / 1M | Verified | Page |
|---|---|---|---|---|
| Claude Sonnet 5 | $2.00 | $10.00 | 2026-09-05 | All anthropic prices |
| GPT-5.4 | $2.50 | $15.00 | 2026-09-05 | All openai prices |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 2026-09-05 | All google prices |
| GPT-5 | $1.25 | $10.00 | 2026-09-05 | All azure-openai prices |
Cheapest current models for a 3,000 in / 600 out workload
| Model | Per request | Per month at 1,000 req/day |
|---|---|---|
| GPT-5 nano azure-openai | $0.000390 | $11.70 |
| GPT-5 nano openai | $0.000390 | $11.70 |
| GPT-4.1 nano azure-openai | $0.000540 | $16.20 |
| Gemini 2.5 Flash-Lite google | $0.000540 | $16.20 |
| GPT-4.1 nano openai | $0.000540 | $16.20 |
| GPT-4o mini azure-openai | $0.000810 | $24.30 |
| GPT-4o mini openai | $0.000810 | $24.30 |
| GPT-5.6 Luna openai | $0.001320 | $39.60 |
Compare every model side by side or run your own workload.
Budget contracts
Add a spendlint.yaml to your repository, describe the workload, and the GitHub Action reports PASS, WARN or FAIL with the projected before and after cost and the rule that broke.
version: 1
rules:
max_monthly_usd: 500
max_cost_per_request_usd: 0.02
max_regression_pct: 20npx spendlint check --contract spendlint.yaml --workload workload.json --baseline workload.baseline.jsonOutput for the Sonnet 5 to Opus 5 swap above: FAIL, delta +$540.00/month (+150.00%), rules max_monthly_usd, max_cost_per_request_usd and max_regression_pct violated, five cheaper compliant models listed. Try a contract in the browser or read the setup guide.
What SpendLint does not do
- It does not read your provider invoices or API keys. Every number is a projection from list prices and your declared workload.
- It does not track spend after the fact. It stops the regression in review, where it is cheap to fix.
- It does not guess prices. Every row carries the official source URL and the date it was checked, and stale rows raise a warning instead of quietly staying live.
Reference pages
Claude API pricing
Every Claude model with input, output, cache and batch prices.
OpenAI API pricing
GPT-5.x, o-series and mini models, cached input and batch.
Gemini API pricing
Gemini 3.x and 2.5 with long-context tiers and promotional periods.
Azure OpenAI pricing
Global Standard list prices from the Azure Retail Prices API.
Claude Code cost
What a developer seat costs per day and month, with Anthropic's own figures.
JSON API
The same dataset as machine-readable JSON with provenance on every row.