docs: correct the evergreen posts, date-stamp the ones that are measurements - #225
Merged
Conversation
…rements The docs/ directory is two different things and had been treated as one. Evergreen pages — comparisons, feature tables, the Anthropic cost posts — carry live claims that a reader takes as current. Those were stale: 55+ and 41+ models against a catalog of 66, and three savings figures (92%, 89%, a hand-computed "$2.05/M vs $25/M") that predate the published one. Bound to the artifact. Dated engineering posts are measurements. "We Benchmarked 39 AI Models" ran 39 models on March 16; rewriting that to 66 would misrepresent what was measured, not update it. Those keep their numbers and gain a note saying so, pointing at the current figures. 9-free-ai-models-zero-cost-blockrun.md is the awkward case: the count is in the title and the URL. The free tier is 8 now, not 9. Renaming breaks every existing link, so it takes the same note, which also explains WHY the number moved — models get withheld when a provider's terms change. Deliberately left: "up to 97%" is observation-compression ratio, not cost; "3 models per request" is the fallback attempt cap; "2 chains" is L1/L2; the 30% is Anthropic's own promo credit. Same words, different subjects.
|
Note Currently processing new changes in this PR. This may take a few minutes, please wait... ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (7)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/9-free-ai-models-zero-cost-blockrun.md`:
- Line 89: The Opus savings baseline is inconsistent across the two
documentation pages. In docs/9-free-ai-models-zero-cost-blockrun.md lines 89-89,
align the ECO comparison table and pricing calculations with the documented
Claude Opus 5 baseline; in docs/anthropic-third-party-harness-changes.md lines
59-59, update the workload examples and displayed prices to use the same Opus 5
baseline and matching calculations.
- Around line 3-8: Update the historical-count disclaimer in the article
containing the “9 free models” claims so it applies to the entire page,
including the lineup and related prose. Either clearly mark all such references
as historical or revise them to the current count of 8, while preserving the
existing URL slug.
In `@docs/anthropic-cost-savings.md`:
- Line 53: Update the adjacent diagram label from “41+ AI Models” to match the
sentence’s current 66-model count, keeping the rest of the diagram unchanged.
In `@docs/clawrouter-vs-openrouter-llm-routing-comparison.md`:
- Around line 259-274: Synchronize the cost-comparison image referenced near
this comparison table with the current 87% savings claim: regenerate or replace
the asset as needed, and update its alt text to remove the outdated 92% savings
and $2.05/M values. Keep the image and alt text consistent with the table’s
current pricing data.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: b7293fdc-fd5b-4a3b-a6ad-43a2c9ffc45e
📒 Files selected for processing (7)
docs/9-free-ai-models-zero-cost-blockrun.mddocs/anthropic-cost-savings.mddocs/anthropic-third-party-harness-changes.mddocs/clawrouter-cuts-llm-api-costs-500x.mddocs/clawrouter-vs-openrouter-llm-routing-comparison.mddocs/llm-router-benchmark-46-models-sub-1ms-routing.mddocs/smart-llm-router-14-dimension-classifier.md
Comment on lines
+3
to
+8
| > **The count in this title is a snapshot.** It was 9 when this was written; the | ||
| > published free tier is now 8 — models are withheld from `/v1/models` when a | ||
| > provider's terms change, most recently over NVIDIA's prompt-retention policy. | ||
| > The URL keeps its original slug so existing links do not break. Current figures: | ||
| > [blockrun.ai/brand/numbers.json](https://blockrun.ai/brand/numbers.json). | ||
|
|
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | 🏗️ Heavy lift
Scope the snapshot disclaimer to the whole article.
The note qualifies only the title, but the page continues to present “9 models” and “9 free models” as current claims. Mark the lineup and related prose as historical too, or update current claims to 8.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/9-free-ai-models-zero-cost-blockrun.md` around lines 3 - 8, Update the
historical-count disclaimer in the article containing the “9 free models” claims
so it applies to the entire page, including the lineup and related prose. Either
clearly mark all such references as historical or revise them to the current
count of 8, while preserving the existing URL slug.
| | Manual free model selection | **$0** | | ||
|
|
||
| **ECO mode saves 92%+ compared to Claude Opus alone.** | ||
| **ECO mode is <!-- br:savings.ecoVsBaselinePct -->98<!-- /br:savings.ecoVsBaselinePct -->% cheaper than pinning Claude Opus 5 for every request.** |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | 🏗️ Heavy lift
Make the Opus savings baseline consistent across both pages.
Both updated claims use Claude Opus 5, while their surrounding pricing/examples reference older Opus versions. Use one documented baseline and matching calculations at every affected site.
docs/9-free-ai-models-zero-cost-blockrun.md#L89-L89: align the ECO comparison table and pricing with the Opus 5 baseline.docs/anthropic-third-party-harness-changes.md#L59-L59: align the workload examples and displayed prices with the Opus 5 baseline.
📍 Affects 2 files
docs/9-free-ai-models-zero-cost-blockrun.md#L89-L89(this comment)docs/anthropic-third-party-harness-changes.md#L59-L59
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/9-free-ai-models-zero-cost-blockrun.md` at line 89, The Opus savings
baseline is inconsistent across the two documentation pages. In
docs/9-free-ai-models-zero-cost-blockrun.md lines 89-89, align the ECO
comparison table and pricing calculations with the documented Claude Opus 5
baseline; in docs/anthropic-third-party-harness-changes.md lines 59-59, update
the workload examples and displayed prices to use the same Opus 5 baseline and
matching calculations.
| ## The Solution: ClawRouter | ||
|
|
||
| [ClawRouter](https://github.com/BlockRunAI/ClawRouter) is an open-source local proxy that sits between your app and 41+ AI models. It saves you money in three ways: **smart routing**, **token optimization**, and **response caching**. | ||
| [ClawRouter](https://github.com/BlockRunAI/ClawRouter) is an open-source local proxy that sits between your app and <!-- br:models.chatVisible -->66<!-- /br:models.chatVisible --> AI models. It saves you money in three ways: **smart routing**, **token optimization**, and **response caching**. |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
Update the adjacent diagram’s stale model count.
This sentence now says 66 AI models, but the same page’s diagram still displays “41+ AI Models” at Line 57. Update the diagram label so the page presents one consistent model-count claim.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/anthropic-cost-savings.md` at line 53, Update the adjacent diagram label
from “41+ AI Models” to match the sentence’s current 66-model count, keeping the
rest of the diagram unchanged.
Comment on lines
+259
to
+274
| | | OpenRouter | ClawRouter | | ||
| | ------------------- | -------------------------------- | -------------------------------------------------------------------------------------------------------- | | ||
| | **Authentication** | API key (leak risk) | Wallet signature (no keys) | | ||
| | **Payment** | Prepaid balance (custodial) | Per-request USDC (non-custodial) | | ||
| | **Routing** | Server-side black box | Local 14-dim classifier, <1ms | | ||
| | **Fallback** | Often broken (20+ issues) | 8-deep chains, per-model isolation | | ||
| | **Model IDs** | Nested prefixes, mangling bugs | Clean aliases, single format | | ||
| | **Cost visibility** | None per-request | Headers + JSONL logs + `/stats` | | ||
| | **Empty wallet** | Request fails | Auto-fallback to free tier | | ||
| | **Rate limits** | Per-key, shared | Per-wallet, independent | | ||
| | **Vision support** | Images sometimes dropped | Auto-detected, vision-only fallback | | ||
| | **Tool calling** | Silent failures with some models | Flag-based filtering, guaranteed support | | ||
| | **Model catalog** | Laggy, silent drops | Curated <!-- br:models.chatVisible -->66<!-- /br:models.chatVisible --> models, redirect aliases | | ||
| | **Budget control** | Monthly invoice | Per-session cap (`maxCostPerRun`) | | ||
| | **Setup** | Create account, paste key | Agent generates wallet, auto-configured | | ||
| | **Average cost** | $25/M tokens (Opus direct) | auto-routed = **<!-- br:savings.autoVsBaselinePct -->87<!-- /br:savings.autoVsBaselinePct -->% savings** | |
There was a problem hiding this comment.
🗄️ Data Integrity & Integration | 🟠 Major | 🏗️ Heavy lift
Synchronize the comparison image with the new 87% claim.
The table now shows 87% savings, but the adjacent clawrouter-cost-transparency-nexus-92-savings.png alt text still advertises 92% savings and $2.05/M. Update or regenerate the asset and its alt text together.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/clawrouter-vs-openrouter-llm-routing-comparison.md` around lines 259 -
274, Synchronize the cost-comparison image referenced near this comparison table
with the current 87% savings claim: regenerate or replace the asset as needed,
and update its alt text to remove the outdated 92% savings and $2.05/M values.
Keep the image and alt text consistent with the table’s current pricing data.
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.
docs/is two different things and had been treated as one.Evergreen pages — corrected
Comparisons, feature tables, the Anthropic cost posts. A reader takes these as current, and they were not:
55+/41+$2.05/M vs $25/M = 92%89% vs Opus-for-everything92%+Dated posts — left alone, and now say so
"We Benchmarked 39 AI Models Through Our Payment Gateway" ran 39 models on March 16. Rewriting that to 66 would misrepresent what was measured, not update it.
Those keep their numbers and gain a note:
The awkward one
9-free-ai-models-zero-cost-blockrun.mdhas the count in its title and its URL. The free tier is 8 now, not 9. Renaming breaks every existing link, so it takes the same note — which also explains why it moved: models get withheld when a provider's terms change, most recently NVIDIA's prompt-retention policy.Deliberately not "fixed"
The sweep flagged these; all are different subjects wearing the same words:
up to 97%— observation compression ratio, not cost3 models per request— the fallback attempt cap2 chains— L1/L2, not RPCup to 30%— Anthropic's own promo creditVerification
tscclean · prettier clean · 724 tests pass ·sync-brand-numbers --checkcleanSummary by CodeRabbit