@blockrun/clawrouter 0.12.243 → 0.12.244

package/README.md

@@ -34,7 +34,7 @@ Agents can only sign transactions.<br><br>
 
 </div>
 
-> **ClawRouter** is an open-source smart LLM router that reduces AI API costs by up to <!-- br:savings.autoVsBaselinePct -->87<!-- /br:savings.autoVsBaselinePct -->%. It analyzes each request across <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions --> dimensions and routes to the cheapest capable model in under 1ms, entirely locally. ClawRouter is the only LLM router built for autonomous AI agents — it uses wallet signatures for authentication (no API keys) and USDC micropayments via the x402 protocol (no credit cards). <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models from OpenAI, Anthropic, Google, xAI, DeepSeek, and more. MIT licensed.
+> **ClawRouter** is an open-source smart LLM router that reduces AI API costs by up to <!-- br:savings.autoVsBaselinePct -->88<!-- /br:savings.autoVsBaselinePct -->%. It analyzes each request across <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions --> dimensions and routes to the cheapest capable model in under 1ms, entirely locally. ClawRouter is the only LLM router built for autonomous AI agents — it uses wallet signatures for authentication (no API keys) and USDC micropayments via the x402 protocol (no credit cards). <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models from OpenAI, Anthropic, Google, xAI, DeepSeek, and more. MIT licensed.
 
 ---
 
@@ -193,7 +193,7 @@ Choose your routing strategy with `/model <profile>`:
 | `/model free` | Free NVIDIA models | **100%**                                                                                                                                                                                                                                                                                          | $0 balance, learning |
 | `/model auto` | Balanced (default) | † Withheld from `/v1/models` — the router still calls it by direct ID, but you will not find it on the public pricing page. See [savings-mix.json](https://github.com/BlockRunAI/blockrun/blob/main/src/brand/savings-mix.json), which prices the published savings claim on visible models only. |
 
-**<!-- br:savings.autoVsBaselinePct -->87<!-- /br:savings.autoVsBaselinePct -->%** | General use |
+**<!-- br:savings.autoVsBaselinePct -->88<!-- /br:savings.autoVsBaselinePct -->%** | General use |
 | `/model eco` | Cheapest possible | **<!-- br:savings.ecoVsBaselinePct -->98<!-- /br:savings.ecoVsBaselinePct -->%** | Maximum savings |
 | `/model premium` | Best quality | 0% | Mission-critical |
 
@@ -205,8 +205,10 @@ Choose your routing strategy with `/model <profile>`:
 
 **100% local routing. <1ms latency. Zero external API calls.**
 
+The scorer weighs <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions --> dimensions of the request:
+
 ```
-Request → Weighted Scorer (<!-- br:clawrouter.dimensions -->14<!-- /br:clawrouter.dimensions --> dimensions) → Tier → Best Model → Response
+Request → Weighted Scorer → Tier → Best Model → Response
 ```
 
 | Tier      | ECO Model                               | AUTO Model                              | PREMIUM Model                |
@@ -216,7 +218,7 @@ Request → Weighted Scorer (<!-- br:clawrouter.dimensions -->14<!-- /br:clawrou
 | COMPLEX   | gemini-3.1-flash-lite ($0.25/$1.50)     | gemini-3.1-pro ($2/$12)                 | claude-fable-5 ($10/$50)     |
 | REASONING | grok-4-1-fast-reasoning † ($0.20/$0.50) | grok-4-1-fast-reasoning † ($0.20/$0.50) | claude-sonnet-4.6 ($3/$15)   |
 
-**<!-- br:savings.autoVsBaselinePct -->87<!-- /br:savings.autoVsBaselinePct -->% cheaper than pinning Claude Opus 5** for the same traffic, on `auto`; **<!-- br:savings.ecoVsBaselinePct -->98<!-- /br:savings.ecoVsBaselinePct -->%** on `eco`.
+**<!-- br:savings.autoVsBaselinePct -->88<!-- /br:savings.autoVsBaselinePct -->% cheaper than pinning Claude Opus 5** for the same traffic, on `auto`; **<!-- br:savings.ecoVsBaselinePct -->98<!-- /br:savings.ecoVsBaselinePct -->%** on `eco`.
 
 Not an "up to" figure. The baseline, the workload mix and the token ratio are
 published in [`savings-mix.json`](https://github.com/BlockRunAI/blockrun/blob/main/src/brand/savings-mix.json),
@@ -716,7 +718,7 @@ ClawRouter is an open-source (MIT licensed) smart LLM router built for autonomou
 
 ### How much can ClawRouter save on LLM costs?
 
-On the `auto` profile ClawRouter costs <!-- br:savings.autoVsBaselinePct -->87<!-- /br:savings.autoVsBaselinePct -->% less than pinning Claude Opus 5 for every request, and <!-- br:savings.ecoVsBaselinePct -->98<!-- /br:savings.ecoVsBaselinePct -->% less on `eco`. That is computed from a published workload mix rather than estimated — see [savings-mix.json](https://github.com/BlockRunAI/blockrun/blob/main/src/brand/savings-mix.json) for the baseline and assumptions. Actual savings depend on your workload — simple queries are routed to free models ($0/request), while complex tasks get premium models.
+On the `auto` profile ClawRouter costs <!-- br:savings.autoVsBaselinePct -->88<!-- /br:savings.autoVsBaselinePct -->% less than pinning Claude Opus 5 for every request, and <!-- br:savings.ecoVsBaselinePct -->98<!-- /br:savings.ecoVsBaselinePct -->% less on `eco`. That is computed from a published workload mix rather than estimated — see [savings-mix.json](https://github.com/BlockRunAI/blockrun/blob/main/src/brand/savings-mix.json) for the baseline and assumptions. Actual savings depend on your workload — simple queries are routed to free models ($0/request), while complex tasks get premium models.
 
 ### How does ClawRouter compare to OpenRouter?
 

package/dist/cli.js

@@ -37005,10 +37005,17 @@ var init_models = __esm({
       cogview: "zai/cogview-4",
       // Video generation
       "grok-video": "xai/grok-imagine-video",
+      // Bare `seedance` deliberately stays on 1.5-pro. It is the cheapest of the
+      // family ($0.070/s vs 2.5's $0.315/s) and `/videogen` documents it as
+      // "default — cheapest"; repointing it at the newest tier would 4.5x the
+      // quote for every caller who typed the short name expecting the default.
+      // Same reasoning that keeps `kimi` on K2.7. Pin 2.5 explicitly to opt in.
       seedance: "bytedance/seedance-1.5-pro",
       "seedance-1.5": "bytedance/seedance-1.5-pro",
       "seedance-2-fast": "bytedance/seedance-2.0-fast",
-      "seedance-2": "bytedance/seedance-2.0"
+      "seedance-2": "bytedance/seedance-2.0",
+      "seedance-2.5": "bytedance/seedance-2.5",
+      "seedance-2-5": "bytedance/seedance-2.5"
     };
     BLOCKRUN_MODELS = [
       // Smart routing meta-models — proxy replaces with actual model
@@ -92698,13 +92705,25 @@ var init_proxy = __esm({
     };
     VIDEO_PRICING = {
       "xai/grok-imagine-video": { pricePerSecond: 0.05, defaultDurationSeconds: 8 },
-      "bytedance/seedance-1.5-pro": { pricePerSecond: 0.0875, defaultDurationSeconds: 5 },
+      // Seedance rates re-synced 2026-08-08 from blockrun's models.ts after the
+      // family reprice (blockrun #351/#354). All three were carrying pre-reprice
+      // numbers, which only ever skewed the usage log — the charge comes from the
+      // x402 header, and estimateVideoCost is the fallback for when it is absent.
+      "bytedance/seedance-1.5-pro": { pricePerSecond: 0.07, defaultDurationSeconds: 5 },
       "bytedance/seedance-2.0-fast": {
-        pricePerSecond: 0.22687,
+        pricePerSecond: 0.165,
         defaultDurationSeconds: 5
       },
       "bytedance/seedance-2.0": {
-        pricePerSecond: 0.28358,
+        pricePerSecond: 0.227,
+        defaultDurationSeconds: 5
+      },
+      // Seedance 2.5: 720p with synced audio, up to 30s. Not a replacement for 2.0
+      // Pro — that is still the one for 1080p/4K. No OpenRouter failover exists for
+      // 2.5, so a token360 outage surfaces as an error instead of quietly rendering
+      // on another model.
+      "bytedance/seedance-2.5": {
+        pricePerSecond: 0.315,
         defaultDurationSeconds: 5
       },
       // Sora 2 via Azure AI Foundry — flat $0.10/s for both t2v and i2v.
@@ -226046,7 +226065,8 @@ function buildVideoGenerationProvider() {
       "xai/grok-imagine-video",
       "bytedance/seedance-1.5-pro",
       "bytedance/seedance-2.0-fast",
-      "bytedance/seedance-2.0"
+      "bytedance/seedance-2.0",
+      "bytedance/seedance-2.5"
     ],
     capabilities: {
       maxVideos: 1,
@@ -226599,7 +226619,7 @@ ${errText}`
             const parsed = parseGenArgs(ctx.args ?? "");
             if (!parsed.prompt) {
               return {
-                text: "Usage: `/videogen <prompt> [--model=<alias>] [--duration=5|8|10]`\n\nAliases: `seedance` (1.5-pro, default \u2014 cheapest), `seedance-2-fast`, `seedance-2`, `grok-video`.\n\n\u23F1\uFE0F  Generation takes 60\u2013180 seconds. Payment settles only on success."
+                text: "Usage: `/videogen <prompt> [--model=<alias>] [--duration=5|8|10]`\n\nAliases: `seedance` (1.5-pro, default \u2014 cheapest), `seedance-2-fast`, `seedance-2`, `seedance-2.5` (720p + synced audio, long-form), `grok-video`.\n\n\u23F1\uFE0F  Generation takes 60\u2013180 seconds. Payment settles only on success."
               };
             }
             const model = resolveModelAlias(parsed.model ?? "seedance");

package/dist/index.js

@@ -533,10 +533,17 @@ var init_models = __esm({
       cogview: "zai/cogview-4",
       // Video generation
       "grok-video": "xai/grok-imagine-video",
+      // Bare `seedance` deliberately stays on 1.5-pro. It is the cheapest of the
+      // family ($0.070/s vs 2.5's $0.315/s) and `/videogen` documents it as
+      // "default — cheapest"; repointing it at the newest tier would 4.5x the
+      // quote for every caller who typed the short name expecting the default.
+      // Same reasoning that keeps `kimi` on K2.7. Pin 2.5 explicitly to opt in.
       seedance: "bytedance/seedance-1.5-pro",
       "seedance-1.5": "bytedance/seedance-1.5-pro",
       "seedance-2-fast": "bytedance/seedance-2.0-fast",
-      "seedance-2": "bytedance/seedance-2.0"
+      "seedance-2": "bytedance/seedance-2.0",
+      "seedance-2.5": "bytedance/seedance-2.5",
+      "seedance-2-5": "bytedance/seedance-2.5"
     };
     BLOCKRUN_MODELS = [
       // Smart routing meta-models — proxy replaces with actual model
@@ -92518,13 +92525,25 @@ var init_proxy = __esm({
     };
     VIDEO_PRICING = {
       "xai/grok-imagine-video": { pricePerSecond: 0.05, defaultDurationSeconds: 8 },
-      "bytedance/seedance-1.5-pro": { pricePerSecond: 0.0875, defaultDurationSeconds: 5 },
+      // Seedance rates re-synced 2026-08-08 from blockrun's models.ts after the
+      // family reprice (blockrun #351/#354). All three were carrying pre-reprice
+      // numbers, which only ever skewed the usage log — the charge comes from the
+      // x402 header, and estimateVideoCost is the fallback for when it is absent.
+      "bytedance/seedance-1.5-pro": { pricePerSecond: 0.07, defaultDurationSeconds: 5 },
       "bytedance/seedance-2.0-fast": {
-        pricePerSecond: 0.22687,
+        pricePerSecond: 0.165,
         defaultDurationSeconds: 5
       },
       "bytedance/seedance-2.0": {
-        pricePerSecond: 0.28358,
+        pricePerSecond: 0.227,
+        defaultDurationSeconds: 5
+      },
+      // Seedance 2.5: 720p with synced audio, up to 30s. Not a replacement for 2.0
+      // Pro — that is still the one for 1080p/4K. No OpenRouter failover exists for
+      // 2.5, so a token360 outage surfaces as an error instead of quietly rendering
+      // on another model.
+      "bytedance/seedance-2.5": {
+        pricePerSecond: 0.315,
         defaultDurationSeconds: 5
       },
       // Sora 2 via Azure AI Foundry — flat $0.10/s for both t2v and i2v.
@@ -225799,7 +225818,8 @@ function buildVideoGenerationProvider() {
       "xai/grok-imagine-video",
       "bytedance/seedance-1.5-pro",
       "bytedance/seedance-2.0-fast",
-      "bytedance/seedance-2.0"
+      "bytedance/seedance-2.0",
+      "bytedance/seedance-2.5"
     ],
     capabilities: {
       maxVideos: 1,
@@ -226351,7 +226371,7 @@ ${errText}`
             const parsed = parseGenArgs(ctx.args ?? "");
             if (!parsed.prompt) {
               return {
-                text: "Usage: `/videogen <prompt> [--model=<alias>] [--duration=5|8|10]`\n\nAliases: `seedance` (1.5-pro, default \u2014 cheapest), `seedance-2-fast`, `seedance-2`, `grok-video`.\n\n\u23F1\uFE0F  Generation takes 60\u2013180 seconds. Payment settles only on success."
+                text: "Usage: `/videogen <prompt> [--model=<alias>] [--duration=5|8|10]`\n\nAliases: `seedance` (1.5-pro, default \u2014 cheapest), `seedance-2-fast`, `seedance-2`, `seedance-2.5` (720p + synced audio, long-form), `grok-video`.\n\n\u23F1\uFE0F  Generation takes 60\u2013180 seconds. Payment settles only on success."
               };
             }
             const model = resolveModelAlias(parsed.model ?? "seedance");

package/docs/anthropic-third-party-harness-changes.md

@@ -56,7 +56,7 @@ From 20,000+ production requests:
 | Free models (trivial tasks)      | 12.8%        | $0.00             |
 | Others                           | 13.8%        | varies            |
 
-**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.
+**Result: <!-- br:savings.autoVsBaselinePct -->88<!-- /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:
 

package/docs/clawrouter-vs-openrouter-llm-routing-comparison.md

@@ -271,7 +271,7 @@ No silent drops. No stale catalog. Models are benchmarked for speed, quality, an
 | **Model catalog**   | Laggy, silent drops              | Curated <!-- br:models.chatVisible -->71<!-- /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** |
+| **Average cost**    | $25/M tokens (Opus direct)       | auto-routed = **<!-- br:savings.autoVsBaselinePct -->88<!-- /br:savings.autoVsBaselinePct -->% savings** |
 
 ![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)
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@blockrun/clawrouter",
-  "version": "0.12.243",
-  "description": "Smart LLM router — save 87% on inference costs. 71 models (6 free), one wallet, x402 micropayments.",
+  "version": "0.12.244",
+  "description": "Smart LLM router — save 88% on inference costs. 71 models (6 free), one wallet, x402 micropayments.",
   "type": "module",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/skills/clawrouter/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: clawrouter
-description: Hosted-gateway LLM router — save 87% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 71 models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 6 free NVIDIA models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai), AND the Surf unified crypto data API (84 endpoints — CEX/DEX, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, prediction markets, social/CT mindshare, news, VC fund intel) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.
+description: Hosted-gateway LLM router — save 88% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 71 models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 6 free NVIDIA models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai), AND the Surf unified crypto data API (84 endpoints — CEX/DEX, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, prediction markets, social/CT mindshare, news, VC fund intel) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.
 triggers:
   - "clawrouter"
   - "claw router"
@@ -53,7 +53,7 @@ metadata:
 
 # ClawRouter
 
-Hosted-gateway LLM router that saves <!-- br:savings.autoVsBaselinePct -->87<!-- /br:savings.autoVsBaselinePct -->% on inference costs by forwarding each request to the blockrun.ai gateway, which picks the cheapest model capable of handling it across <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models from 9 providers (<!-- br:models.free -->6<!-- /br:models.free --> free NVIDIA models). All billing flows through one USDC wallet; you do not hold provider API keys.
+Hosted-gateway LLM router that saves <!-- br:savings.autoVsBaselinePct -->88<!-- /br:savings.autoVsBaselinePct -->% on inference costs by forwarding each request to the blockrun.ai gateway, which picks the cheapest model capable of handling it across <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models from 9 providers (<!-- br:models.free -->6<!-- /br:models.free --> free NVIDIA models). All billing flows through one USDC wallet; you do not hold provider API keys.
 
 **This is not a local-inference tool.** ClawRouter is a thin local proxy. Your prompts are sent over HTTPS to the blockrun.ai gateway for model execution. If your workload requires inference that never leaves your machine, use a local runtime like Ollama — ClawRouter is not the right tool for that use case.