AI Coding Field Notes
Open dataset of what AI coding agents cost: token pricing, per-million rates, and every published figure (prices, percentages, multiples, token counts and durations) as JSON and CSV. Figures are one row each, carrying the sentence they came from. Plus the field notes behind the numbers.
Ce que coûtent réellement les agents de code IA : 335 chiffres, chacun avec sa phrase et sa date
English · 中文 · Español · 日本語 · 한국어 · Tiếng Việt · Français · Deutsch · Русский · Bahasa Indonesia
Un jeu de données ouvert. Chaque chiffre publié dans 32 notes de terrain — prix, pourcentages, multiples, nombres de tokens et durées — extrait en une ligne, avec la phrase entière dont il provient et sa date de publication.
Les chiffres d’abord
Les lignes ci-dessous sont en anglais, recopiées telles quelles, sans traduction : un chiffre séparé de sa phrase n’est pas vérifiable — $1.43 peut être par million de tokens, par mois ou par utilisateur.
| Figure | The sentence it came from | Write-up |
|---|---|---|
$1.43 |
The $1.43 and the $9.05 are both frontier models doing a job they were not specifically built for. | The Two Best AI Code Reviewers Score the Same. One Costs $1.43 a Run, the Other $9.05. |
$29 |
Before writing a contract-comparison tool, one builder handled three to ten comparisons by hand at $29 a document, and only turned the routine into software once the same people kept coming back and paying for it. | Debunking the Myth of Overnight Success in Micro-SaaS |
90% |
90% of developers still rely on manual prompt writing, while top performers use Skill Package to automate 80% of repetitive tasks, saving hours weekly. | Best Practices for AI Agent Skill Management |
80% |
When the Claude Code team decided to slash 80% of their system prompts, most developers expected the model to lose its edge in complex engineering tasks. | Why Stripping 80% of System Prompts Actually Improved Claude Code’s Performance |
$30 |
With a budget as low as $30 per day, developers have reached an effective lead cost of $3 to $4. | Stop Reading SimilarWeb Like a Traffic Dashboard — Read It Like a Feasibility Test |
$1,000 |
Instead of chasing a 2.5% consumer conversion rate across unpredictable social channels, you sell a single $1,000 to $5,000 service package directly to one business owner — no massive ad campaigns, no hundreds of low-tier support tickets. | How Indie Developers Are Building AI-Powered “Digital Landlords” and Renting Them Out for Monthly Cash Flow |
40-second |
When an independent developer uses Agency Agents to set up a 40-second response cycle for e-commerce listings, they are building a feedback loop that reads market conditions and adjusts, which is what separates a timed automation from a script on a timer. | Stop Chatting With AI: How I Use /loop and /hook to Automate My Indie Dev Workflow |
9.1% |
One reported case moved entry-group conversion from 9.1% to 55.1% by rebuilding an automated onboarding flow around what the funnel data actually showed, rather than around what the team assumed users were doing. | Boosting AI Bot Conversion: A Deep Dive into Funnel Data |
$1.25 |
Meta priced Muse Spark 1.1 at $1.25 per million input and $4.25 per million output, roughly 75% and 83% below Anthropic’s Opus, and the tradeoff is visible in the benchmarks, since it leads on MCP Atlas and JobBench while trailing on SWE-Bench Pro and DeepSWE 1.1. | 1.6 Billion Free Tokens Is a Compression Ratio, Not a Strategy |
9x |
Open Code Review reports roughly 9x lower token consumption than general-purpose agents while holding accuracy, which suggests that a specialized agent aimed at one job often beats a heavy generalist on the only axis an indie developer can afford to optimize. | Token Optimization for Indie Developers’ AI API Bills |
87 percent |
The 87 percent figure and those two cases are measuring the same thing from different angles, which is time spent moving data by hand between a system that knows the answer and a system that needs it. | The 5 AI Features That Separated 27 Profitable Solopreneurs From the Rest |
40 seconds |
By using an AI agent to automate responses, negotiation, and price adjustment, the average response time can be reduced to within 40 seconds. | From AI Demo to Product: Loop Engineering for Indie Devs |
curl -s https://cdn.jsdelivr.net/gh/xyzs996/ai-coding-field-notes@main/data/figures.json
curl -s https://cdn.jsdelivr.net/gh/xyzs996/ai-coding-field-notes@main/data/figures.csv
Le champ published est le jour où cette note est parue, pas le jour où ce prix était en vigueur. Les prix bougent : lisez chaque ligne à sa propre date.
Les textes
Les textes sont en anglais, ici : https://xyzs996.github.io/ai-coding-field-notes/ — avec le tableau des chiffres, les pages par thème et les pages par fournisseur. Si vous ne voulez que les données, les deux curl ci-dessus suffisent.
Dites quelque chose
- Mettez une étoile pour suivre les mises à jour. Les données sont en CC BY : l’étoile ne change rien à ce que vous pouvez en faire.
- Un chiffre est faux ? Si un prix a changé, ou si votre propre mesure donne autre chose — ouvrez un issue. Ce dépôt est fait pour ça. (issue)
- Un chiffre manque ? Dites quelle métrique, quel fournisseur, quelle unité — en une ligne. Le formulaire a un seul champ obligatoire ; les demandes deviennent des lignes. (form)
CC BY 4.0 : copiez, republiez, dérivez, vendez. Une seule condition : dire d’où cela vient, un lien vers https://xyzs996.github.io/ai-coding-field-notes/ suffit.