docs(benchmark): add Claude Haiku + Sonnet cost savings; verify per-Mtok pricing#434
Merged
Merged
Conversation
…tok pricing (closes #433) Quality benchmark now reports API input-cost savings for GPT-4o, Claude Sonnet, and Claude Haiku (was GPT-4o only). Pricing verified 2026-07: GPT-4o $2.50, Claude Sonnet 5/4.6 $3.00, Claude Haiku 4.5 $1.00 per 1M input tokens. - scripts/run-quality-benchmark.mjs: add Claude Haiku to PRICING; per-model savings aggregate + a "cost savings by model" markdown table. - src/tracking/pricing.js: correct stale Claude rates (Haiku 0.80→1.00, Opus 15.0→5.00) to current published pricing. - docs-vp/guide/quality-benchmark.md: cost table + headline + frontmatter now show all three models ($9,900+ GPT-4o · $11,900+ Sonnet · $3,900+ Haiku/mo). Rebuilt bundle; regenerated quality.json.
This was referenced Jul 5, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #433.
Summary
The quality benchmark reported API input-cost savings for GPT-4o only. This adds Claude Sonnet and Claude Haiku, and corrects stale hardcoded Claude pricing — all against current, verified 2026-07 per-1M-token rates.
Pricing verified
Changes
scripts/run-quality-benchmark.mjs: add Claude Haiku toPRICING; per-model aggregate + a "cost savings by model" table.src/tracking/pricing.js: Haiku $0.80→$1.00, Opus $15→$5 (current published rates).docs-vp/guide/quality-benchmark.md: cost table, headline, and frontmatter now show all three models.Real numbers (this run, 10 calls/day across 21 repos)
GPT-4o $9,949/mo · Claude Sonnet $11,939/mo · Claude Haiku $3,980/mo (doc uses conservative rounded-down "+" figures).
Test plan
node scripts/run-quality-benchmark.mjs --save→ 3-model tablenode test/integration/all.js— 104 passed, 0 failedsrc/; supply-chain gate clean🤖 Generated with Claude Code