Changelog
The scan runs on a schedule — every price checked, every score re-verified, every change detected. This page groups what it found by day, with the material changes first. It is written from the data by the scanner itself: it cannot say something happened that did not.
Some prices move constantly. OpenRouter blends a model’s price across whichever providers are serving it, so a figure can tick every hour; where that happened we show one line with the range and the number of moves rather than twenty near-identical rows. The untouched stream is at the bottom of this page.
17 Aug 2026 · 7 changes
dataRoundup article generated from 19 tested models, fact-checked (58 claims verified), published as a noindexed draft.
dataRoundup article generated from 19 tested models, fact-checked (39 claims verified), published as a noindexed draft.
dataRoundup article generated from 3 tested tools, fact-checked (48 claims verified), published as a noindexed draft.
dataRoundup article generated from 19 tested models, fact-checked (47 claims verified), published as a noindexed draft.
dataRoundup article generated from 19 tested models, fact-checked (48 claims verified), published as a noindexed draft.
watchclaude.com/pricing content changed per Wayback snapshot 20260814102934 — price extractors will verify on the next daily scan
watchcursor.com/pricing content changed per Wayback snapshot 20260815123334 — price extractors will verify on the next daily scan
16 Aug 2026 · 4 changes
dataJudging protocol judge-2026-08 -> judge-2026-08b: machine constraint caps moved into the harness (word limits, banned phrases, bullet counts, JSON validity), applied to fresh runs and retroactively to the archive.
datagemini · Writing: 89 -> 87/100 after retroactive machine constraint caps (1 breach machine-checked).
datacursor · Coding: 87 -> 85/100 after retroactive machine constraint caps (1 breach machine-checked).
dataclaude · Writing: 90 -> 87/100 after retroactive machine constraint caps (1 breach machine-checked).
14 Aug 2026 · 1 change
staleChatGPT: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6448311069) — value kept, marked stale
12 Aug 2026 · 12 changes
dataOtter.ai App Store rating up 0% — App Store rating 4.77 → 4.78 · Apple App Store (iTunes Lookup API)
dataFireflies.ai App Store rating down 0% — App Store rating 4.83 → 4.82 · Apple App Store (iTunes Lookup API)
11 Aug 2026 · 14 changes
stalen8n: github_stars could not be re-verified (GitHub API failed for n8n-io/n8n: fetch failed) — value kept, marked stale
staleMicrosoft Copilot: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6472538445) — value kept, marked stale
stalePerplexity: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 1668000334) — value kept, marked stale
staleGemini: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6477489729) — value kept, marked stale
staleClaude: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6473753684) — value kept, marked stale
staleNotebookLM: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6737527615) — value kept, marked stale
staleSuno: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6480136315) — value kept, marked stale
staleElevenLabs: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6743162587) — value kept, marked stale
staleFireflies.ai: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6463164203) — value kept, marked stale
staleOtter.ai: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 1276437113) — value kept, marked stale
staleGrammarly: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 1158877342) — value kept, marked stale
staleNotion AI: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 1232780281) — value kept, marked stale
staleCanva AI: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 897446215) — value kept, marked stale
staleReplit: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 1614022293) — value kept, marked stale
10 Aug 2026 · 2 changes
7 Aug 2026 · 6 changes
17 Jul 2026 · 1 change
Everything the scanner recorded, including model and API changes (250 events, unedited)
Every event exactly as the scanner wrote it — including the model and API-price changes kept out of the view above, and the micro-ticks collapsed into single rows there. An audit trail that has been tidied is not an audit trail, so this one is untouched.
2026-08-17 17:14:21price-changeGLM 5.2: api_price_out_per_1m changed 3.74 → 1.5356 (OpenRouter API)
2026-08-17 17:14:21price-changeGLM 5.2: api_price_in_per_1m changed 1.19 → 0.4886 (OpenRouter API)
2026-08-17 17:14:21price-changeGPT-5.6 Sol: api_price_out_per_1m changed 30 → 15 (OpenRouter API)
2026-08-17 17:14:21price-changeGPT-5.6 Sol: api_price_in_per_1m changed 5 → 2.5 (OpenRouter API)
2026-08-17 17:14:21scan21 tracked models checked against 414 listed
2026-08-17 15:15:04price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1652 → 0.1596 (OpenRouter API)
2026-08-17 15:15:04price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0826 → 0.0798 (OpenRouter API)
2026-08-17 15:15:04price-changeDeepSeek V4 Pro: api_price_out_per_1m changed 3.96 → 1.98 (OpenRouter API)
2026-08-17 15:15:04price-changeDeepSeek V4 Pro: api_price_in_per_1m changed 1.32 → 0.66 (OpenRouter API)
2026-08-17 15:15:04price-changeGPT-5.6 Luna: api_price_out_per_1m changed 0.6 → 1.2 (OpenRouter API)
2026-08-17 15:15:04price-changeGPT-5.6 Luna: api_price_in_per_1m changed 0.1 → 0.2 (OpenRouter API)
2026-08-17 15:15:04price-changeGPT-5.6 Terra: api_price_out_per_1m changed 6 → 12 (OpenRouter API)
2026-08-17 15:15:04price-changeGPT-5.6 Terra: api_price_in_per_1m changed 1 → 2 (OpenRouter API)
2026-08-17 14:39:22editorial_holdRoundup passed the fact-check but the confidence gate did not (too_close: Claude Opus 4.8 vs GPT-5.6 Terra: 1-0 with 11 ties (sign test p=1) — the top of this board is a tie-break, not a measured win) — held for human editorial sign-off.
2026-08-17 14:39:22roundup_publishedRoundup article generated from 19 tested models, fact-checked (58 claims verified), published as a noindexed draft.
2026-08-17 14:10:06editorial_holdRoundup passed the fact-check but the confidence gate did not (too_close: GPT-5.6 Sol vs GPT-5.5: 1-0 with 11 ties (sign test p=1) — the top of this board is a tie-break, not a measured win) — held for human editorial sign-off.
2026-08-17 14:10:06roundup_publishedRoundup article generated from 19 tested models, fact-checked (39 claims verified), published as a noindexed draft.
2026-08-17 13:46:55editorial_holdRoundup passed the fact-check but the confidence gate did not (edge: ChatGPT vs Claude: 5-5 with 8 ties (Wilcoxon p=0.7507) — the top of this board is a tie-break, not a measured win) — held for human editorial sign-off.
2026-08-17 13:46:55roundup_publishedRoundup article generated from 3 tested tools, fact-checked (48 claims verified), published as a noindexed draft.
2026-08-17 12:36:51editorial_holdRoundup passed the fact-check but the confidence gate did not (too_close: GPT-5.6 Sol vs GPT-5.5: 1-2 with 9 ties (sign test p=1) — the top of this board is a tie-break, not a measured win) — held for human editorial sign-off.
2026-08-17 12:36:51roundup_publishedRoundup article generated from 19 tested models, fact-checked (47 claims verified), published as a noindexed draft.
2026-08-17 11:15:54editorial_holdRoundup passed the fact-check but the confidence gate did not (too_close: GPT-5.6 Sol vs GPT-5.5: 1-1 with 10 ties (sign test p=1) — the top of this board is a tie-break, not a measured win) — held for human editorial sign-off.
2026-08-17 11:15:54roundup_publishedRoundup article generated from 19 tested models, fact-checked (48 claims verified), published as a noindexed draft.
2026-08-17 06:20:43scandownload reachable (HTTP 200) (no claims written — parser is Phase-3 work)
2026-08-17 06:20:43scanrepo alive, last push 2026-08-10 (no claims written — parser is Phase-3 work)
2026-08-17 06:20:43scanrepo alive, last push 2026-08-17 (no claims written — parser is Phase-3 work)
2026-08-17 06:20:43scan2 pricing pages checked against Wayback digests, 2 changed
2026-08-17 06:20:43page-changedclaude.com/pricing content changed per Wayback snapshot 20260814102934 — price extractors will verify on the next daily scan
2026-08-17 06:20:43page-changedcursor.com/pricing content changed per Wayback snapshot 20260815123334 — price extractors will verify on the next daily scan
2026-08-17 06:20:43scan6/6 dev tools' HN presence measured (90-day window)
2026-08-17 06:20:43scan1/1 plan prices verified, free tier confirmed
2026-08-17 06:20:43scan2/2 plan prices verified, free tier confirmed
2026-08-17 06:20:43scan3/3 plan prices verified, free tier confirmed
2026-08-17 06:20:43scan3/3 plan prices verified, free tier confirmed
2026-08-17 06:20:43scan2/2 plan prices verified, free tier confirmed
2026-08-17 06:20:43scan2/2 plan prices verified
2026-08-17 06:20:43scan4/4 plan prices verified
2026-08-17 06:20:43scan1/1 repos re-checked
2026-08-17 06:20:43scan5/5 Android apps checked
2026-08-17 06:20:43scan14/14 apps re-checked
2026-08-17 06:20:43scan10 models re-scored from 1000 leaderboard rows, 1 dropped → stale
2026-08-17 06:14:39price-changeDeepSeek V4 Pro: api_price_out_per_1m changed 1.98 → 3.96 (OpenRouter API)
2026-08-17 06:14:39price-changeDeepSeek V4 Pro: api_price_in_per_1m changed 0.66 → 1.32 (OpenRouter API)
2026-08-17 05:14:33price-changeDeepSeek V4 Pro: api_price_out_per_1m changed 3.96 → 1.98 (OpenRouter API)
2026-08-17 05:14:33price-changeDeepSeek V4 Pro: api_price_in_per_1m changed 1.32 → 0.66 (OpenRouter API)
2026-08-17 04:14:29price-changeGLM 5.2: api_price_out_per_1m changed 2.42 → 3.74 (OpenRouter API)
2026-08-17 04:14:29price-changeGLM 5.2: api_price_in_per_1m changed 0.76 → 1.19 (OpenRouter API)
2026-08-17 01:14:17price-changeDeepSeek V4 Pro: api_price_out_per_1m changed 1.98 → 3.96 (OpenRouter API)
2026-08-17 01:14:17price-changeDeepSeek V4 Pro: api_price_in_per_1m changed 0.66 → 1.32 (OpenRouter API)
2026-08-17 00:14:13price-changeGLM 5.2: api_price_out_per_1m changed 0.968 → 2.42 (OpenRouter API)
2026-08-17 00:14:13price-changeGLM 5.2: api_price_in_per_1m changed 0.308 → 0.76 (OpenRouter API)
2026-08-17 00:14:13price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1173 → 0.1677 (OpenRouter API)
2026-08-17 00:14:13price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0587 → 0.0839 (OpenRouter API)
2026-08-17 00:14:13price-changeDeepSeek V4 Pro: api_price_out_per_1m changed 2.336 → 1.98 (OpenRouter API)
2026-08-17 00:14:13price-changeDeepSeek V4 Pro: api_price_in_per_1m changed 1.168 → 0.66 (OpenRouter API)
2026-08-16 23:14:09model-observedNew on OpenRouter: z-ai/glm-5.2:free
2026-08-16 23:14:09price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1201 → 0.1173 (OpenRouter API)
2026-08-16 23:14:09price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0601 → 0.0587 (OpenRouter API)
2026-08-16 23:14:09scan21 tracked models checked against 414 listed
2026-08-16 22:14:05price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1229 → 0.1201 (OpenRouter API)
2026-08-16 22:14:05price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0615 → 0.0601 (OpenRouter API)
2026-08-16 21:15:01model-observedNew on OpenRouter: z-ai/glm-5.2:free
2026-08-16 21:15:01price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1201 → 0.1229 (OpenRouter API)
2026-08-16 21:15:01price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0601 → 0.0615 (OpenRouter API)
2026-08-16 20:14:58price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1229 → 0.1201 (OpenRouter API)
2026-08-16 20:14:58price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0615 → 0.0601 (OpenRouter API)
2026-08-16 09:43:52protocol_changeBase-rate tripwire published: any machine check firing on more than half the field (n>=6) is quarantined for review instead of capping; quarantine artifact published at /data/gate/check-quarantine.json and consumed by fresh runs.
2026-08-16 09:43:52protocol_changeDocumented the judge-flag clamp: a judge reporting a breach has its own score clamped to 5 before the median. Executed and published protocol now match.
2026-08-16 09:43:52protocol_changeJudging protocol judge-2026-08 -> judge-2026-08b: machine constraint caps moved into the harness (word limits, banned phrases, bullet counts, JSON validity), applied to fresh runs and retroactively to the archive.
2026-08-16 09:03:03score_recappedgpt-5-6-sol · Summarising: 94 -> 95/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 09:03:03score_recappedgemini-3-5-flash · Summarising: 88 -> 89/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedqwen3-7-max · Study notes: 84 -> 88/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedqwen3-7-max · Summarising: 83 -> 87/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedkimi-k3 · Study notes: 88 -> 91/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedkimi-k3 · Summarising: 88 -> 90/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgrok-4-5 · Study notes: 86 -> 88/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgrok-4-5 · Summarising: 89 -> 92/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgpt-5-6-sol · Summarising: 91 -> 94/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgpt-5-6-luna · Summarising: 93 -> 97/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgpt-5-3-codex · Study notes: 85 -> 88/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgpt-5-3-codex · Summarising: 92 -> 96/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedglm-5-2 · Study notes: 85 -> 89/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedglm-5-2 · Summarising: 88 -> 91/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgemini-3-5-flash · Study notes: 80 -> 83/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgemini-3-5-flash · Summarising: 85 -> 88/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgemini-3-1-pro · Study notes: 87 -> 89/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgemini-3-1-pro · Summarising: 88 -> 90/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgemini-3-1-flash-lite · Study notes: 78 -> 80/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedgemini-3-1-flash-lite · Summarising: 83 -> 85/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappeddeepseek-v4-pro · Summarising: 93 -> 95/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedclaude-sonnet-5 · Study notes: 78 -> 81/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedclaude-sonnet-5 · Summarising: 89 -> 93/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedclaude-opus-4-8 · Summarising: 95 -> 99/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedclaude-opus-4-6 · Study notes: 85 -> 88/100 after machine-check recalibration (1 breach machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedclaude-opus-4-6 · Summarising: 90 -> 93/100 after machine-check recalibration (0 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedclaude-fable-5 · Study notes: 78 -> 80/100 after machine-check recalibration (2 breaches machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:37:12score_recappedclaude-fable-5 · Summarising: 89 -> 93/100 after machine-check recalibration (1 breach machine-checked; a mis-specified check was corrected and wrongly capped scores restored).
2026-08-16 08:16:35score_recappedqwen3-7-max · Study notes: 88 -> 84/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedqwen3-7-max · Summarising: 87 -> 83/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedkimi-k3 · Study notes: 91 -> 88/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedkimi-k3 · Summarising: 90 -> 88/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedkimi-k3 · Best-value API: 91 -> 90/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgrok-4-5 · Study notes: 88 -> 86/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgrok-4-5 · Summarising: 92 -> 89/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgpt-5-6-sol · Summarising: 95 -> 91/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgpt-5-6-luna · Summarising: 97 -> 93/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgpt-5-3-codex · Study notes: 88 -> 85/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgpt-5-3-codex · Summarising: 96 -> 92/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedglm-5-2 · Study notes: 89 -> 85/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedglm-5-2 · Summarising: 91 -> 88/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini-3-5-flash · Study notes: 83 -> 80/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini-3-5-flash · Summarising: 89 -> 85/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini-3-1-pro · Study notes: 89 -> 87/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini-3-1-pro · Summarising: 90 -> 88/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini-3-1-pro · Best-value API: 88 -> 86/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini-3-1-flash-lite · Study notes: 80 -> 78/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini-3-1-flash-lite · Emails: 88 -> 86/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini-3-1-flash-lite · Summarising: 85 -> 83/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedgemini · Writing: 89 -> 87/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappeddeepseek-v4-pro · Summarising: 95 -> 93/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedcursor · Coding: 87 -> 85/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedclaude-sonnet-5 · Study notes: 81 -> 78/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedclaude-sonnet-5 · Summarising: 93 -> 89/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedclaude-opus-4-8 · Summarising: 99 -> 95/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedclaude-opus-4-8 · Essays: 83 -> 79/100 after retroactive machine constraint caps (2 breaches machine-checked).
2026-08-16 08:16:35score_recappedclaude-opus-4-6 · Study notes: 91 -> 85/100 after retroactive machine constraint caps (2 breaches machine-checked).
2026-08-16 08:16:35score_recappedclaude-opus-4-6 · Summarising: 93 -> 90/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedclaude-opus-4-6 · Best-value API: 85 -> 83/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 08:16:35score_recappedclaude-fable-5 · Study notes: 83 -> 78/100 after retroactive machine constraint caps (3 breaches machine-checked).
2026-08-16 08:16:35score_recappedclaude-fable-5 · Customer replies: 91 -> 88/100 after retroactive machine constraint caps (3 breaches machine-checked).
2026-08-16 08:16:35score_recappedclaude-fable-5 · Summarising: 96 -> 89/100 after retroactive machine constraint caps (2 breaches machine-checked).
2026-08-16 08:16:35score_recappedclaude · Writing: 90 -> 87/100 after retroactive machine constraint caps (1 breach machine-checked).
2026-08-16 07:14:02price-changeGLM 5.2: api_price_in_per_1m changed 0.3248 → 0.308 (OpenRouter API)
2026-08-16 06:15:00price-changeGLM 5.2: api_price_in_per_1m changed 0.462 → 0.308 (OpenRouter API)
2026-08-16 06:15:00price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1257 → 0.1229 (OpenRouter API)
2026-08-16 06:15:00price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0629 → 0.0615 (OpenRouter API)
2026-08-16 05:40:56scan1/1 plan prices verified, free tier confirmed
2026-08-16 05:40:56scan2/2 plan prices verified, free tier confirmed
2026-08-16 05:40:56scan3/3 plan prices verified, free tier confirmed
2026-08-16 05:40:56scan3/3 plan prices verified, free tier confirmed
2026-08-16 05:40:56scan1/1 plan prices verified, free tier confirmed
2026-08-16 05:40:56scan2/2 plan prices verified, free tier confirmed
2026-08-16 05:40:56scan2/2 plan prices verified
2026-08-16 05:40:56scan4/4 plan prices verified
2026-08-16 05:40:56scan1/1 repos re-checked
2026-08-16 05:40:56scan5/5 Android apps checked
2026-08-16 05:40:56scan14/14 apps re-checked
2026-08-16 05:40:56scan10 models re-scored from 1000 leaderboard rows, 1 dropped → stale
2026-08-16 05:40:56price-changeGLM 5.2: api_price_in_per_1m changed 0.462 → 0.308 (OpenRouter API)
2026-08-16 05:14:56price-changeGLM 5.2: api_price_out_per_1m changed 1.0208 → 0.968 (OpenRouter API)
2026-08-16 05:14:56price-changeGLM 5.2: api_price_in_per_1m changed 0.462 → 0.308 (OpenRouter API)
2026-08-16 05:14:56price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1285 → 0.1257 (OpenRouter API)
2026-08-16 05:14:56price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0643 → 0.0629 (OpenRouter API)
2026-08-16 04:14:49price-changeGLM 5.2: api_price_out_per_1m changed 1.452 → 1.0208 (OpenRouter API)
2026-08-16 04:14:49price-changeGLM 5.2: api_price_in_per_1m changed 0.462 → 0.3248 (OpenRouter API)
2026-08-15 23:14:55scan21 tracked models checked against 413 listed
2026-08-15 16:14:50price-changeGLM 5.2: api_price_in_per_1m changed 0.49 → 0.462 (OpenRouter API)
2026-08-15 15:14:38price-changeGLM 5.2: api_price_in_per_1m changed 0.49 → 0.462 (OpenRouter API)
2026-08-15 14:15:04price-changeGLM 5.2: api_price_in_per_1m changed 0.49 → 0.462 (OpenRouter API)
2026-08-15 13:15:00price-changeGLM 5.2: api_price_out_per_1m changed 1.54 → 1.452 (OpenRouter API)
2026-08-15 13:15:00price-changeGLM 5.2: api_price_in_per_1m changed 0.49 → 0.462 (OpenRouter API)
2026-08-15 13:15:00price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1313 → 0.1285 (OpenRouter API)
2026-08-15 13:15:00price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0657 → 0.0643 (OpenRouter API)
2026-08-15 12:15:39price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1341 → 0.1313 (OpenRouter API)
2026-08-15 12:15:39price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0671 → 0.0657 (OpenRouter API)
2026-08-15 11:14:57price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1369 → 0.1341 (OpenRouter API)
2026-08-15 11:14:57price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0685 → 0.0671 (OpenRouter API)
2026-08-15 10:14:50price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1397 → 0.1369 (OpenRouter API)
2026-08-15 10:14:50price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0699 → 0.0685 (OpenRouter API)
2026-08-15 08:15:17price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.1481 → 0.1397 (OpenRouter API)
2026-08-15 08:15:17price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.0741 → 0.0699 (OpenRouter API)
2026-08-15 05:42:16scan1/1 plan prices verified, free tier confirmed
2026-08-15 05:42:16scan2/2 plan prices verified, free tier confirmed
2026-08-15 05:42:16scan3/3 plan prices verified, free tier confirmed
2026-08-15 05:42:16scan3/3 plan prices verified, free tier confirmed
2026-08-15 05:42:16scan1/1 plan prices verified, free tier confirmed
2026-08-15 05:42:16scan2/2 plan prices verified, free tier confirmed
2026-08-15 05:42:16scan2/2 plan prices verified
2026-08-15 05:42:16scan4/4 plan prices verified
2026-08-15 05:42:16scan1/1 repos re-checked
2026-08-15 05:42:16scan5/5 Android apps checked
2026-08-15 05:42:16value-changePerplexity: playstore_rating changed 4.58 → 4.59 (Google Play (google-play-scraper))
2026-08-15 05:42:16scan14/14 apps re-checked
2026-08-15 05:42:16scan10 models re-scored from 1000 leaderboard rows, 1 dropped → stale
2026-08-15 05:42:16model-observedNew on OpenRouter: dots-studio/dots-3-note-preview:free
2026-08-15 04:15:52price-changeGLM 5.2: api_price_in_per_1m changed 1.19 → 0.49 (OpenRouter API)
2026-08-15 03:15:30price-changeGLM 5.2: api_price_in_per_1m changed 1.19 → 0.49 (OpenRouter API)
2026-08-15 02:15:22model-observedNew on OpenRouter: openai/gpt-oss-20b:free, qwen/qwen3.8-27b
2026-08-15 02:15:22price-changeGLM 5.2: api_price_in_per_1m changed 1.19 → 0.49 (OpenRouter API)
2026-08-15 01:14:07price-changeGLM 5.2: api_price_out_per_1m changed 3.74 → 1.54 (OpenRouter API)
2026-08-15 01:14:07price-changeGLM 5.2: api_price_in_per_1m changed 1.19 → 0.49 (OpenRouter API)
2026-08-15 00:15:05price-changeDeepSeek V4 Flash: api_price_out_per_1m changed 0.28 → 0.1649 (OpenRouter API)
2026-08-15 00:15:05price-changeDeepSeek V4 Flash: api_price_in_per_1m changed 0.14 → 0.0825 (OpenRouter API)
2026-08-14 23:15:03scan21 tracked models checked against 411 listed
2026-08-14 18:15:13price-changeGLM 5.2: api_price_in_per_1m changed 0.63 → 1.19 (OpenRouter API)
2026-08-14 17:15:09price-changeGLM 5.2: api_price_in_per_1m changed 0.63 → 1.19 (OpenRouter API)
2026-08-14 16:14:36price-changeGLM 5.2: api_price_in_per_1m changed 0.63 → 1.19 (OpenRouter API)
2026-08-14 15:14:42price-changeGLM 5.2: api_price_out_per_1m changed 1.98 → 3.74 (OpenRouter API)
2026-08-14 15:14:42price-changeGLM 5.2: api_price_in_per_1m changed 0.63 → 1.19 (OpenRouter API)
2026-08-14 08:15:31price-changeGLM 5.2: api_price_in_per_1m changed 0.5 → 0.63 (OpenRouter API)
2026-08-14 07:15:22price-changeGLM 5.2: api_price_in_per_1m changed 0.5 → 0.63 (OpenRouter API)
2026-08-14 06:59:29model-observedNew on OpenRouter: google/gemini-3.7-flash, google/gemini-3.7-flash:batch
2026-08-14 06:59:29price-changeGLM 5.2: api_price_in_per_1m changed 0.5 → 0.63 (OpenRouter API)
2026-08-14 05:45:15source-degradedOpenRouter API check failed (fetch failed) — 0 claim(s) marked stale, values kept visible with a stale badge
2026-08-14 05:45:15scan1/1 plan prices verified, free tier confirmed
2026-08-14 05:45:15scan2/2 plan prices verified, free tier confirmed
2026-08-14 05:45:15scan3/3 plan prices verified, free tier confirmed
2026-08-14 05:45:15scan3/3 plan prices verified, free tier confirmed
2026-08-14 05:45:15scan1/1 plan prices verified, free tier confirmed
2026-08-14 05:45:15scan2/2 plan prices verified, free tier confirmed
2026-08-14 05:45:15scan2/2 plan prices verified
2026-08-14 05:45:15scan4/4 plan prices verified
2026-08-14 05:45:15scan1/1 repos re-checked
2026-08-14 05:45:15scan5/5 Android apps checked
2026-08-14 05:45:15scan13/14 apps re-checked, 1 without ratings → stale
2026-08-14 05:45:15claim-staleChatGPT: app_version_date could not be re-verified (iTunes lookup returned no rating for app id 6448311069) — value kept, marked stale
2026-08-14 05:45:15claim-staleChatGPT: appstore_rating_count could not be re-verified (iTunes lookup returned no rating for app id 6448311069) — value kept, marked stale
2026-08-14 05:45:15claim-staleChatGPT: appstore_rating could not be re-verified (iTunes lookup returned no rating for app id 6448311069) — value kept, marked stale
2026-08-14 05:45:15source-degradedLMArena leaderboard (HF) check failed (fetch failed) — 30 claim(s) marked stale, values kept visible with a stale badge
2026-08-14 05:45:15source-degradedOpenRouter API check failed (fetch failed) — 0 claim(s) marked stale, values kept visible with a stale badge
2026-08-13 13:14:48source-degradedOpenRouter API check failed (fetch failed) — 0 claim(s) marked stale, values kept visible with a stale badge
2026-08-13 12:54:53source-degradedOpenRouter API check failed (fetch failed) — 63 claim(s) marked stale, values kept visible with a stale badge
2026-08-13 10:14:14price-changeGLM 5.2: api_price_out_per_1m changed 3.15 → 1.98 (OpenRouter API)
2026-08-13 10:14:14price-changeGLM 5.2: api_price_in_per_1m changed 0.5 → 0.63 (OpenRouter API)
2026-08-13 10:14:14scan21 tracked models checked against 409 listed
2026-08-13 09:20:10source-degradedOpenRouter API check failed (fetch failed) — 66 claim(s) marked stale, values kept visible with a stale badge
2026-08-13 07:14:59price-changeGLM 5.2: api_price_in_per_1m changed 0.49 → 0.5 (OpenRouter API)
2026-08-13 06:14:40price-changeGLM 5.2: api_price_in_per_1m changed 0.49 → 0.5 (OpenRouter API)
2026-08-13 05:40:56scan1/1 plan prices verified, free tier confirmed
2026-08-13 05:40:56scan2/2 plan prices verified, free tier confirmed
2026-08-13 05:40:56scan3/3 plan prices verified, free tier confirmed
2026-08-13 05:40:56scan3/3 plan prices verified, free tier confirmed
2026-08-13 05:40:56scan1/1 plan prices verified, free tier confirmed
2026-08-13 05:40:56scan2/2 plan prices verified, free tier confirmed
2026-08-13 05:40:56scan2/2 plan prices verified
2026-08-13 05:40:56scan4/4 plan prices verified
2026-08-13 05:40:56scan1/1 repos re-checked
2026-08-13 05:40:56scan5/5 Android apps checked
2026-08-13 05:40:56value-changePerplexity: playstore_rating changed 4.59 → 4.58 (Google Play (google-play-scraper))
2026-08-13 05:40:56scan14/14 apps re-checked
2026-08-13 05:40:56scan10 models re-scored from 1000 leaderboard rows, 1 dropped → stale
2026-08-13 05:40:56value-changeQwen3.7 Max: arena_rank_text changed 16 → 17 (LMArena leaderboard (CC-BY-4.0))
2026-08-13 05:40:56value-changeQwen3.7 Max: arena_elo_text changed 1475 → 1474 (LMArena leaderboard (CC-BY-4.0))
2026-08-13 05:40:56value-changeDeepSeek V4 Flash: arena_rank_text changed 74 → 75 (LMArena leaderboard (CC-BY-4.0))
2026-08-13 05:40:56value-changeDeepSeek V4 Flash: arena_elo_text changed 1432 → 1431 (LMArena leaderboard (CC-BY-4.0))
2026-08-13 05:40:56value-changeDeepSeek V4 Pro: arena_rank_text changed 39 → 36 (LMArena leaderboard (CC-BY-4.0))
2026-08-13 05:40:56value-changeDeepSeek V4 Pro: arena_elo_text changed 1450 → 1451 (LMArena leaderboard (CC-BY-4.0))
2026-08-13 05:40:56value-changeGrok 4.5: arena_rank_text changed 37 → 38 (LMArena leaderboard (CC-BY-4.0))
2026-08-13 05:40:56value-changeGemini 3.5 Flash: arena_elo_text changed 1480 → 1482 (LMArena leaderboard (CC-BY-4.0))
2026-08-13 05:40:56value-changeGPT-5.5: arena_rank_text changed 24 → 23 (LMArena leaderboard (CC-BY-4.0))