Skip to content

docs: correct the evergreen posts, date-stamp the ones that are measurements #225

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
VickyXAI merged 1 commit into from
Jul 27, 2026
Merged

docs: correct the evergreen posts, date-stamp the ones that are measurements #225

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion docs/9-free-ai-models-zero-cost-blockrun.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,11 @@
# 9 Free AI Models, Zero Cost: How BlockRun Gives Developers Top-Tier LLMs for Nothing

> **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).

Comment on lines +3 to +8

@coderabbitai coderabbitai Bot Jul 27, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🎯 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.

## The Cost Problem Nobody Talks About

It's 2026. Large language models are table stakes for developers. But here's the uncomfortable truth — **the models you can afford aren't good enough, and the good ones aren't affordable.**
Expand Down Expand Up @@ -80,7 +86,7 @@ Assume 100 requests per day, distributed roughly as:
| ClawRouter ECO mode | ~$1–3 |
| 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.**

@coderabbitai coderabbitai Bot Jul 27, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🎯 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.


---

Expand Down
2 changes: 1 addition & 1 deletion docs/anthropic-cost-savings.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ This is where you're paying for real value:

## 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**.

@coderabbitai coderabbitai Bot Jul 27, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🎯 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.


```
┌─────────────┐ ┌──────────────────────────────┐ ┌──────────────────┐
Expand Down
6 changes: 3 additions & 3 deletions docs/anthropic-third-party-harness-changes.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ This is exactly the problem [ClawRouter](https://github.com/BlockRunAI/ClawRoute

## ClawRouter: Smart Routing for Agents

ClawRouter is an open-source local proxy that sits between your agent and 55+ LLM models across 9 providers. It analyzes every request across 15 dimensions and routes it to the cheapest model that can handle it — in under 1ms, entirely locally.
ClawRouter is an open-source local proxy that sits between your agent and <!-- br:models.chatVisible -->66<!-- /br:models.chatVisible --> LLM models across 9 providers. It analyzes every request across 15 dimensions and routes it to the cheapest model that can handle it — in under 1ms, entirely locally.

```
Your Agent → ClawRouter (localhost:8402) → Best model for the job
Expand All @@ -56,7 +56,7 @@ From 20,000+ production requests:
| Free models (trivial tasks) | 12.8% | $0.00 |
| Others | 13.8% | varies |

**Result: 81% savings vs. Sonnet-for-everything, 89% vs. Opus-for-everything.**
**Result: <!-- br:savings.autoVsBaselinePct -->87<!-- /br:savings.autoVsBaselinePct -->% cheaper than pinning Claude Opus 5 for every request** — the published figure, priced on a stated workload mix rather than estimated.

A typical user running 10K mixed requests/month:

Expand All @@ -74,7 +74,7 @@ Then point your agent at `http://localhost:8402/v1/` with any OpenAI-compatible

- **No API keys to manage** — wallet-based cryptographic auth
- **No subscriptions** — pay per request in USDC (Base or Solana)
- **No vendor lock-in** — 55+ models, switch anytime
- **No vendor lock-in** — <!-- br:models.chatVisible -->66<!-- /br:models.chatVisible --> models, switch anytime
- **You control your wallet** — non-custodial, funds never held by a third party
- **Budget caps** — set a max spend per session, ClawRouter gracefully downgrades when budget runs low
- **Token compression** — 7-layer pipeline reduces token costs by 7–40% before they hit any provider
Expand Down
4 changes: 2 additions & 2 deletions docs/clawrouter-cuts-llm-api-costs-500x.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,7 +135,7 @@ Less context repeated = fewer tokens = lower cost. Agents that need to recall ea

### 7. x402 Micropayments — Wallet-Based Budget Control

<p align="center"><img src="assets/blockrun-clawrouter-x402-usdc-micropayment-wallet-budget-control.png" alt="Budget limits enforced by physical construction — wallet loaded via Base/Solana, pay per call across 41+ models, balance hits zero and the valve shuts cleanly" width="720"></p>
<p align="center"><img src="assets/blockrun-clawrouter-x402-usdc-micropayment-wallet-budget-control.png" alt="Budget limits enforced by physical construction — wallet loaded via Base/Solana, pay per call across <!-- br:models.chatVisible -->66<!-- /br:models.chatVisible --> models, balance hits zero and the valve shuts cleanly" width="720"></p>

ClawRouter pays for inference via [x402](https://x402.org/) USDC micropayments (Base or Solana). You load a wallet. Each inference call costs exactly what it costs. When the wallet runs low, requests stop cleanly.

Expand All @@ -144,7 +144,7 @@ There is no monthly invoice. There is no 3am email. There is a wallet balance, a
**`maxCostPerRun`** — a per-session cost ceiling that stops or downgrades requests once a session exceeds a configured threshold (e.g., `$0.50`). This closes the remaining gap ([#3181](https://github.com/openclaw/openclaw/issues/3181)) where a wallet with sufficient funds can still accumulate within a single run. Two modes: `graceful` (downgrade to cheaper models) and `strict` (hard 429 once the cap is hit).

```
41+ models. One wallet. Pay per call.
<!-- br:models.chatVisible -->66<!-- /br:models.chatVisible --> models. One wallet. Pay per call.
```

---
Expand Down
36 changes: 18 additions & 18 deletions docs/clawrouter-vs-openrouter-llm-routing-comparison.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,7 +222,7 @@ OpenRouter doesn't always pass through provider-specific features correctly. Ima

**Direct provider routing.** ClawRouter routes through BlockRun's API directly to providers — not through a second aggregator. One hop, not two. Provider-specific features work because there's no middleman translating them.

![Guaranteed Feature Parity & Direct Connectivity — Three-panel diagram: Vision (image_url auto-detected → vision-capable models only), Tool Calling (toolCalling flag → agentic models only), Catalog (curated 55+ models with automatic legacy-to-modern redirects). Direct provider routing means no dropped payloads.](./assets/clawrouter-feature-parity-direct-connectivity.png)
![Guaranteed Feature Parity & Direct Connectivity — Three-panel diagram: Vision (image_url auto-detected → vision-capable models only), Tool Calling (toolCalling flag → agentic models only), Catalog (curated <!-- br:models.chatVisible -->66<!-- /br:models.chatVisible --> models with automatic legacy-to-modern redirects). Direct provider routing means no dropped payloads.](./assets/clawrouter-feature-parity-direct-connectivity.png)

---

Expand All @@ -240,7 +240,7 @@ When new models launch, OpenRouter's catalog lags. Users configure a model that

### How ClawRouter Solves This

ClawRouter maintains a curated catalog of 55+ models across 9 providers (including 9 free models), updated with each release. Delisted models have automatic redirect aliases:
ClawRouter maintains a curated catalog of <!-- br:models.chatVisible -->66<!-- /br:models.chatVisible --> models across 9 providers (including 9 free models), updated with each release. Delisted models have automatic redirect aliases:

```typescript
// Delisted models redirect automatically
Expand All @@ -256,22 +256,22 @@ No silent drops. No stale catalog. Models are benchmarked for speed, quality, an

## The Full Comparison

| | 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 55+ 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) | $2.05/M tokens (auto-routed) = **92% savings** |
| | 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** |
Comment on lines +259 to +274

@coderabbitai coderabbitai Bot Jul 27, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🗄️ 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.


![The Engineering Matrix — Side-by-side feature comparison: OpenRouter vs ClawRouter across Routing, Authentication, Payment, Fallback, Model IDs, Empty Wallet, Vision/Tools, and Average Cost. ClawRouter wins on every dimension.](./assets/clawrouter-engineering-matrix-comparison.png)

Expand Down
5 changes: 5 additions & 0 deletions docs/llm-router-benchmark-46-models-sub-1ms-routing.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,11 @@

_March 16, 2026 | BlockRun Engineering_

> **Numbers in this post are a snapshot from the date above.** They record what was
> measured then and are deliberately not updated — rewriting them would misrepresent
> the benchmark. For current figures see
> [blockrun.ai/brand/numbers.json](https://blockrun.ai/brand/numbers.json).

Last week we ran every model on BlockRun through a real-world latency benchmark — 39 models, same prompts, same payment pipeline, same hardware. No cherry-picked results. No synthetic lab conditions. Just cold, hard numbers from production infrastructure.

The results changed how we route requests.
Expand Down
5 changes: 5 additions & 0 deletions docs/smart-llm-router-14-dimension-classifier.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,11 @@

_March 20, 2026 | BlockRun Engineering_

> **Numbers in this post are a snapshot from the date above.** They record what was
> measured then and are deliberately not updated — rewriting them would misrepresent
> the benchmark. For current figures see
> [blockrun.ai/brand/numbers.json](https://blockrun.ai/brand/numbers.json).

When you route AI requests across 55+ models from 8 providers, you can't just pick the cheapest one. You can't just pick the fastest one either. We learned this the hard way.

This is the technical story of how we benchmarked every model on our platform, discovered that speed and intelligence are poorly correlated, and built a production routing system that classifies requests in under 1ms using 14 weighted dimensions with sigmoid confidence calibration.
Expand Down
Loading