@blockrun/clawrouter 0.12.74 → 0.12.75

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -222,7 +222,7 @@ OpenRouter doesn't always pass through provider-specific features correctly. Ima
222
222
 
223
223
  **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.
224
224
 
225
- ![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 46+ models with automatic legacy-to-modern redirects). Direct provider routing means no dropped payloads.](./assets/clawrouter-feature-parity-direct-connectivity.png)
225
+ ![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)
226
226
 
227
227
  ---
228
228
 
@@ -240,7 +240,7 @@ When new models launch, OpenRouter's catalog lags. Users configure a model that
240
240
 
241
241
  ### How ClawRouter Solves This
242
242
 
243
- ClawRouter maintains a curated catalog of 46+ models across 8 providers, updated with each release. Delisted models have automatic redirect aliases:
243
+ ClawRouter maintains a curated catalog of 55+ models across 9 providers (including 11 free NVIDIA models), updated with each release. Delisted models have automatic redirect aliases:
244
244
 
245
245
  ```typescript
246
246
  // Delisted models redirect automatically
@@ -2,7 +2,7 @@
2
2
 
3
3
  _March 20, 2026 | BlockRun Engineering_
4
4
 
5
- When you route AI requests across 46 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.
5
+ 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.
6
6
 
7
7
  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.
8
8
 
@@ -21,7 +21,7 @@ We needed a system that could classify any request and route it to the optimal m
21
21
 
22
22
  ## Step 1: Benchmarking the Fleet
23
23
 
24
- Before building the router, we needed ground truth. We benchmarked all 46 models through our production payment pipeline.
24
+ Before building the router, we needed ground truth. We benchmarked all 55+ models through our production payment pipeline.
25
25
 
26
26
  ### Methodology
27
27
 
@@ -312,7 +312,7 @@ We originally designed a two-stage system where low-confidence rules-based class
312
312
 
313
313
  ## Appendix: Full Benchmark Data
314
314
 
315
- Raw data (46 models, latency, throughput, IQ scores, pricing): [`benchmark-merged.json`](https://github.com/BlockRunAI/ClawRouter/blob/main/benchmark-merged.json)
315
+ Raw data (55+ models, latency, throughput, IQ scores, pricing): [`benchmark-merged.json`](https://github.com/BlockRunAI/ClawRouter/blob/main/benchmark-merged.json)
316
316
 
317
317
  Routing configuration: [`src/router/config.ts`](https://github.com/BlockRunAI/ClawRouter/blob/main/src/router/config.ts)
318
318
 
@@ -320,4 +320,4 @@ Scoring implementation: [`src/router/rules.ts`](https://github.com/BlockRunAI/Cl
320
320
 
321
321
  ---
322
322
 
323
- _BlockRun is the x402 micropayment gateway for AI. One wallet, 46+ models, pay-per-request with USDC. [blockrun.ai](https://blockrun.ai)_
323
+ _BlockRun is the x402 micropayment gateway for AI. One wallet, 55+ models, pay-per-request with USDC. [blockrun.ai](https://blockrun.ai)_
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@blockrun/clawrouter",
3
- "version": "0.12.74",
3
+ "version": "0.12.75",
4
4
  "description": "Smart LLM router — save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",