@blockrun/clawrouter 0.12.245 → 0.12.246

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 -->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 -->70<!-- /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.
 
 ---
 
@@ -61,7 +61,7 @@ This is the stack that lets agents operate autonomously: **x402 + USDC + local r
 
 |                  | OpenRouter        | LiteLLM          | Martian           | Portkey           | **ClawRouter**                                                         |
 | ---------------- | ----------------- | ---------------- | ----------------- | ----------------- | ---------------------------------------------------------------------- |
-| **Models**       | 200+              | 100+             | Smart routing     | Gateway           | **<!-- br:models.chatVisible -->70<!-- /br:models.chatVisible -->**    |
+| **Models**       | 200+              | 100+             | Smart routing     | Gateway           | **<!-- br:models.chatVisible -->71<!-- /br:models.chatVisible -->**    |
 | **Free tier**    | Rate-limited      | BYO keys         | No                | No                | **<!-- br:models.free -->5<!-- /br:models.free --> models, no signup** |
 | **Routing**      | Manual selection  | Manual selection | Smart (closed)    | Observability     | **Smart (open source)**                                                |
 | **Auth**         | Account + API key | Your API keys    | Account + API key | Account + API key | **Wallet signature**                                                   |
@@ -107,7 +107,7 @@ openclaw gateway restart
 
 > **Using Claude Code?** Check out [BRCC](https://blockrun.ai/brcc.md) — it's purpose-built for Claude Code with the same smart routing and x402 payments.
 >
-> **Using NousResearch Hermes?** See [ClawRouter-Hermes](https://github.com/BlockRunAI/ClawRouter-Hermes) — a Python plugin that wires Hermes into the ClawRouter proxy. Same wallet, same <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> models, same x402 USDC settlement on Base & Solana.
+> **Using NousResearch Hermes?** See [ClawRouter-Hermes](https://github.com/BlockRunAI/ClawRouter-Hermes) — a Python plugin that wires Hermes into the ClawRouter proxy. Same wallet, same <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models, same x402 USDC settlement on Base & Solana.
 
 No OpenClaw required. ClawRouter runs as a local proxy on port 8402.
 
@@ -213,7 +213,7 @@ Request → Weighted Scorer → Tier → Best Model → Response
 
 | Tier      | ECO Model                               | AUTO Model                              | PREMIUM Model                |
 | --------- | --------------------------------------- | --------------------------------------- | ---------------------------- |
-| SIMPLE    | free/gpt-oss-120b † (**FREE**)          | gemini-2.5-flash ($0.30/$2.50)          | kimi-k2.7 † ($0.95/$4.00)    |
+| SIMPLE    | step-3.7-flash (**FREE**)               | gemini-2.5-flash ($0.30/$2.50)          | kimi-k2.7 † ($0.95/$4.00)    |
 | MEDIUM    | gemini-3.1-flash-lite ($0.25/$1.50)     | kimi-k2.7 ($0.95/$4.00)                 | gpt-5.3-codex ($1.75/$14.00) |
 | 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)   |
@@ -393,7 +393,7 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 
 ## Models & Pricing
 
-<!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> models across 9 providers, one wallet. **<!-- br:models.free -->5<!-- /br:models.free --> models are $0 — paid models start at fractions of a cent.**
+<!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models across 9 providers, one wallet. **<!-- br:models.free -->5<!-- /br:models.free --> models are $0 — paid models start at fractions of a cent.**
 
 > **💡 "Cost per request"** = estimated cost for a typical chat message (~500 input + 500 output tokens). Paid requests also carry a flat **$0.001/tx settlement fee** (covers on-chain gas; already included in the price the gateway quotes). Free models never pay it.
 
@@ -498,15 +498,14 @@ Request → 402 (price: $0.003) → wallet signs USDC → retry → response
 
 USDC stays in your wallet until spent — non-custodial. Price is visible in the 402 header before signing.
 
-**Dual-chain support:** Pay with **USDC** on **Base (EVM)** or **USDC on Solana**. Both wallets are derived from a single BIP-39 mnemonic on first run.
+**Dual-chain support:** Pay with **USDC** on **Base (EVM)** or **USDC on Solana**. Both wallets are derived from a single BIP-39 mnemonic on first run. New installs default to **Solana**; existing installs stay on **Base** unless switched with `/wallet solana`.
 
 ```bash
 /wallet              # Check balance and address (both chains)
 /wallet export       # Export mnemonic + keys for backup
 /wallet recover      # Restore wallet from mnemonic on a new machine
 /wallet solana       # Switch to Solana USDC payments
-/wallet base         # Switch back to Base (EVM) USDC payments
-/chain solana        # Alias for /wallet solana
+/wallet base         # Switch to Base (EVM) USDC payments
 /stats               # View usage and savings
 /stats clear         # Reset usage statistics
 /exclude             # Show excluded models
@@ -654,7 +653,7 @@ npm test
 
 **The LLM router built for autonomous agents**
 
-You're here. <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> models, local smart routing, x402 USDC payments — the only stack that lets agents operate independently.
+You're here. <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models, local smart routing, x402 USDC payments — the only stack that lets agents operate independently.
 
 `curl -fsSL https://blockrun.ai/ClawRouter-update | bash`
 
@@ -665,7 +664,7 @@ You're here. <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> mod
 
 **BlockRun for Claude Code**
 
-Run Claude Code with <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> models, no rate limits, no Anthropic account, no phone verification. Pay per request with USDC — your wallet is your identity.
+Run Claude Code with <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models, no rate limits, no Anthropic account, no phone verification. Pay per request with USDC — your wallet is your identity.
 
 `curl -fsSL https://blockrun.ai/brcc-install | bash`
 
@@ -678,7 +677,7 @@ Run Claude Code with <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible
 
 **ClawRouter for NousResearch Hermes**
 
-Python plugin that wraps the ClawRouter proxy for `hermes-agent`. Same <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> models, same x402 USDC payments on Base & Solana, native Hermes ergonomics.
+Python plugin that wraps the ClawRouter proxy for `hermes-agent`. Same <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models, same x402 USDC payments on Base & Solana, native Hermes ergonomics.
 
 `pip install hermes-plugin-clawrouter`
 

package/dist/cli.js

@@ -33594,6 +33594,21 @@ function applyPromotions(tierConfigs, promotions, profile, now2 = /* @__PURE__ *
   }
   return result;
 }
+function applyUnavailableModels(tierConfigs, unavailableModels) {
+  if (!unavailableModels || unavailableModels.length === 0) return tierConfigs;
+  const dead = new Set(unavailableModels);
+  let result = tierConfigs;
+  for (const tier of Object.keys(tierConfigs)) {
+    const config = tierConfigs[tier];
+    const alive = [config.primary, ...config.fallback].filter((model) => !dead.has(model));
+    if (alive.length === 0 || alive[0] === config.primary && alive.length === config.fallback.length + 1) {
+      continue;
+    }
+    if (result === tierConfigs) result = { ...tierConfigs };
+    result[tier] = { primary: alive[0], fallback: alive.slice(1) };
+  }
+  return result;
+}
 function getStrategy(name) {
   const strategy = registry.get(name);
   if (!strategy) {
@@ -34291,6 +34306,7 @@ ${value.slice(-(scanLimit - prefixLength))}`;
           profile = useAgenticTiers ? "agentic" : "auto";
         }
         tierConfigs = applyPromotions(tierConfigs, config.promotions, profile, options.now);
+        tierConfigs = applyUnavailableModels(tierConfigs, options.unavailableModels);
         const agenticScoreValue = ruleResult.agenticScore;
         if (estimatedTokens > config.overrides.maxTokensForceComplex) {
           const decision2 = selectModel(
@@ -34419,18 +34435,6 @@ ${value.slice(-(scanLimit - prefixLength))}`;
         supportsTools: false,
         supportsVision: false
       },
-      "free/gpt-oss-120b": {
-        contextWindow: 128e3,
-        maxOutputTokens: 16384,
-        supportsTools: false,
-        supportsVision: false
-      },
-      "free/gpt-oss-20b": {
-        contextWindow: 128e3,
-        maxOutputTokens: 16384,
-        supportsTools: false,
-        supportsVision: false
-      },
       "free/seed-oss-36b": {
         contextWindow: 131072,
         maxOutputTokens: 16384,
@@ -34503,6 +34507,18 @@ ${value.slice(-(scanLimit - prefixLength))}`;
         supportsTools: true,
         supportsVision: true
       },
+      "nvidia/nemotron-nano-9b-v2": {
+        contextWindow: 131072,
+        maxOutputTokens: 16384,
+        supportsTools: false,
+        supportsVision: false
+      },
+      "nvidia/step-3.7-flash": {
+        contextWindow: 131072,
+        maxOutputTokens: 16384,
+        supportsTools: false,
+        supportsVision: false
+      },
       "openai/gpt-4.1": {
         contextWindow: 128e3,
         maxOutputTokens: 16384,
@@ -34976,9 +34992,12 @@ ${value.slice(-(scanLimit - prefixLength))}`;
         const targetTier = (features.taskType === "reasoning_mcq" || features.taskType === "reasoning_math") && (base3.tier === "SIMPLE" || base3.tier === "MEDIUM") ? "REASONING" : base3.tier;
         const tierConfig = tierConfigs[targetTier];
         const configuredCandidates = tierConfig ? getFallbackChain(targetTier, tierConfigs) : [];
+        const unavailable = new Set(options.unavailableModels ?? []);
         const chain3 = [
           .../* @__PURE__ */ new Set([...configuredCandidates, ...evidenceCandidates(features.taskType)])
-        ].filter((model2) => typeof model2 === "string" && model2.length > 0);
+        ].filter(
+          (model2) => typeof model2 === "string" && model2.length > 0 && !unavailable.has(model2)
+        );
         const eligible = chain3.filter(
           (model2) => isEligible(model2, features, maxOutputTokens, options)
         );
@@ -35055,13 +35074,7 @@ ${value.slice(-(scanLimit - prefixLength))}`;
           ...eligibleCandidates.filter(
             (model2) => !scoredModels.includes(model2) && !webResearchFallbackOrder.includes(model2)
           )
-        ] : features.taskType === "tool_agent" || features.taskType === "tool_agent_parallel" && features.agentDomain !== "other" ? [
-          ...scoredModels,
-          ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))
-        ] : [
-          ...scoredModels,
-          ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))
-        ];
+        ] : [...scoredModels, ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))];
         const model = ranked[0] ?? base3.model;
         const selectedTierConfigs = {
           ...tierConfigs,
@@ -36173,8 +36186,8 @@ ${value.slice(-(scanLimit - prefixLength))}`;
             // $0.20/$1.25, 1M context
             "xai/grok-4-fast-non-reasoning",
             // 1,143ms, $0.20/$0.50 — fast fallback
-            "free/gpt-oss-120b"
-            // 1,252ms, FREE fallback (hidden from /v1/models but direct calls work)
+            "nvidia/step-3.7-flash"
+            // FREE backstop — new NVIDIA free tier (gpt-oss-120b now 400s; probed 2026-08-21)
           ]
         },
         MEDIUM: {
@@ -36247,14 +36260,15 @@ ${value.slice(-(scanLimit - prefixLength))}`;
       // Eco tier configs - absolute cheapest (blockrun/eco)
       ecoTiers: {
         SIMPLE: {
-          primary: "free/gpt-oss-120b",
-          // FREE! $0.00/$0.00 — heavy user default
+          primary: "nvidia/step-3.7-flash",
+          // FREE! $0.00/$0.00 — new NVIDIA free tier flagship
           fallback: [
-            "free/gpt-oss-20b",
-            // FREE — smaller, faster
-            // deepseek-v4-flash and seed-oss-36b sat here until NVIDIA EOL'd them
-            // (410; 2026-08-12 and 2026-08-03 respectively). gpt-oss-120b/20b already
-            // head this chain, so the rungs are dropped, not retargeted.
+            "nvidia/nemotron-nano-9b-v2",
+            // FREE — compact + fast (~0.7s), high-volume light tasks
+            // This head keeps rotting with NVIDIA's free hosting: deepseek-v4-flash
+            // (410, 2026-08-12), seed-oss-36b (410, 2026-08-03), then gpt-oss-120b/20b
+            // (400 Unknown model, probed 2026-08-21). Each retirement retargets the
+            // two free rungs to the current free tier; the paid rungs below never move.
             "google/gemini-3.1-flash-lite",
             // $0.25/$1.50 — newest flash-lite
             "openai/gpt-5.4-nano",
@@ -36371,8 +36385,8 @@ ${value.slice(-(scanLimit - prefixLength))}`;
             "openai/gpt-5.3-codex",
             "deepseek/deepseek-chat",
             // Cheap, reliable
-            "free/gpt-oss-120b"
-            // NVIDIA free ultimate backstop (was seed-oss-36b; EOL'd 2026-08-03)
+            "nvidia/step-3.7-flash"
+            // NVIDIA free ultimate backstop (was gpt-oss-120b; 400s since ~2026-08)
           ]
         },
         REASONING: {
@@ -36461,8 +36475,8 @@ ${value.slice(-(scanLimit - prefixLength))}`;
             // Previous flagship — 6,213ms, reliable
             "deepseek/deepseek-chat",
             // 1,431ms — cheap, reliable
-            "free/gpt-oss-120b"
-            // NVIDIA free ultimate backstop (was seed-oss-36b; EOL'd 2026-08-03)
+            "nvidia/step-3.7-flash"
+            // NVIDIA free ultimate backstop (was gpt-oss-120b; 400s since ~2026-08)
           ]
         },
         REASONING: {
@@ -57934,6 +57948,14 @@ Then run: npx @blockrun/clawrouter`
     solanaAddress = await getSolanaAddress(derived.solanaPrivateKeyBytes);
   } catch {
   }
+  let solanaDefaultSaved = false;
+  if (solanaAddress) {
+    try {
+      await savePaymentChain("solana");
+      solanaDefaultSaved = true;
+    } catch {
+    }
+  }
   console.log(`[ClawRouter]`);
   console.log(`[ClawRouter] \u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550`);
   console.log(`[ClawRouter]   NEW WALLET GENERATED \u2014 BACK UP YOUR KEY NOW`);
@@ -57946,6 +57968,12 @@ Then run: npx @blockrun/clawrouter`
   console.log(`[ClawRouter]   Mnemonic       : ${MNEMONIC_FILE}`);
   console.log(`[ClawRouter]`);
   console.log(`[ClawRouter]   Both EVM (Base) and Solana wallets are ready.`);
+  if (solanaDefaultSaved) {
+    console.log(
+      `[ClawRouter]   Default payment chain: Solana \u2014 fund the Solana address above with USDC.`
+    );
+    console.log(`[ClawRouter]   To switch to Base, run in OpenClaw: /wallet base`);
+  }
   console.log(`[ClawRouter]   To back up, run in OpenClaw:`);
   console.log(`[ClawRouter]     /wallet export`);
   console.log(`[ClawRouter]`);

package/dist/index.d.ts

@@ -767,7 +767,11 @@ type PaymentChain = "base" | "solana";
 type ProxyOptions = {
     wallet: WalletConfig;
     apiBase?: string;
-    /** Payment chain: "base" (default) or "solana". Can also be set via CLAWROUTER_PAYMENT_CHAIN env var. */
+    /**
+     * Payment chain: "base" or "solana". New installs persist "solana" at wallet
+     * generation; absent config resolves to "base" for pre-existing installs.
+     * Can also be set via CLAWROUTER_PAYMENT_CHAIN env var.
+     */
     paymentChain?: PaymentChain;
     /** Port to listen on (default: 8402) */
     port?: number;
@@ -895,6 +899,8 @@ declare function savePaymentChain(chain: "base" | "solana"): Promise<void>;
 /**
  * Load the persisted payment chain selection from disk.
  * Returns "base" if no file exists or the file is invalid.
+ * New installs persist "solana" at wallet generation, so an absent file
+ * means a pre-existing install whose funds live on Base.
  */
 declare function loadPaymentChain(): Promise<"base" | "solana">;
 /**
@@ -1488,7 +1494,8 @@ declare function buildPartnerTools(proxyBaseUrl: string): PartnerToolDefinition[
  *   # Install the plugin
  *   openclaw plugins install @blockrun/clawrouter
  *
- *   # Fund your wallet with USDC on Base (address printed on install)
+ *   # Fund your wallet with USDC (Solana for new installs, Base for existing ones;
+ *   # the funding address is printed on install)
  *
  *   # Use smart routing (auto-picks cheapest model)
  *   openclaw models set blockrun/auto

package/dist/index.js

@@ -35385,6 +35385,21 @@ function applyPromotions(tierConfigs, promotions, profile, now2 = /* @__PURE__ *
   }
   return result;
 }
+function applyUnavailableModels(tierConfigs, unavailableModels) {
+  if (!unavailableModels || unavailableModels.length === 0) return tierConfigs;
+  const dead = new Set(unavailableModels);
+  let result = tierConfigs;
+  for (const tier of Object.keys(tierConfigs)) {
+    const config = tierConfigs[tier];
+    const alive = [config.primary, ...config.fallback].filter((model) => !dead.has(model));
+    if (alive.length === 0 || alive[0] === config.primary && alive.length === config.fallback.length + 1) {
+      continue;
+    }
+    if (result === tierConfigs) result = { ...tierConfigs };
+    result[tier] = { primary: alive[0], fallback: alive.slice(1) };
+  }
+  return result;
+}
 function getStrategy(name) {
   const strategy = registry.get(name);
   if (!strategy) {
@@ -36082,6 +36097,7 @@ ${value.slice(-(scanLimit - prefixLength))}`;
           profile = useAgenticTiers ? "agentic" : "auto";
         }
         tierConfigs = applyPromotions(tierConfigs, config.promotions, profile, options.now);
+        tierConfigs = applyUnavailableModels(tierConfigs, options.unavailableModels);
         const agenticScoreValue = ruleResult.agenticScore;
         if (estimatedTokens > config.overrides.maxTokensForceComplex) {
           const decision2 = selectModel(
@@ -36210,18 +36226,6 @@ ${value.slice(-(scanLimit - prefixLength))}`;
         supportsTools: false,
         supportsVision: false
       },
-      "free/gpt-oss-120b": {
-        contextWindow: 128e3,
-        maxOutputTokens: 16384,
-        supportsTools: false,
-        supportsVision: false
-      },
-      "free/gpt-oss-20b": {
-        contextWindow: 128e3,
-        maxOutputTokens: 16384,
-        supportsTools: false,
-        supportsVision: false
-      },
       "free/seed-oss-36b": {
         contextWindow: 131072,
         maxOutputTokens: 16384,
@@ -36294,6 +36298,18 @@ ${value.slice(-(scanLimit - prefixLength))}`;
         supportsTools: true,
         supportsVision: true
       },
+      "nvidia/nemotron-nano-9b-v2": {
+        contextWindow: 131072,
+        maxOutputTokens: 16384,
+        supportsTools: false,
+        supportsVision: false
+      },
+      "nvidia/step-3.7-flash": {
+        contextWindow: 131072,
+        maxOutputTokens: 16384,
+        supportsTools: false,
+        supportsVision: false
+      },
       "openai/gpt-4.1": {
         contextWindow: 128e3,
         maxOutputTokens: 16384,
@@ -36767,9 +36783,12 @@ ${value.slice(-(scanLimit - prefixLength))}`;
         const targetTier = (features.taskType === "reasoning_mcq" || features.taskType === "reasoning_math") && (base3.tier === "SIMPLE" || base3.tier === "MEDIUM") ? "REASONING" : base3.tier;
         const tierConfig = tierConfigs[targetTier];
         const configuredCandidates = tierConfig ? getFallbackChain(targetTier, tierConfigs) : [];
+        const unavailable = new Set(options.unavailableModels ?? []);
         const chain3 = [
           .../* @__PURE__ */ new Set([...configuredCandidates, ...evidenceCandidates(features.taskType)])
-        ].filter((model2) => typeof model2 === "string" && model2.length > 0);
+        ].filter(
+          (model2) => typeof model2 === "string" && model2.length > 0 && !unavailable.has(model2)
+        );
         const eligible = chain3.filter(
           (model2) => isEligible(model2, features, maxOutputTokens, options)
         );
@@ -36846,13 +36865,7 @@ ${value.slice(-(scanLimit - prefixLength))}`;
           ...eligibleCandidates.filter(
             (model2) => !scoredModels.includes(model2) && !webResearchFallbackOrder.includes(model2)
           )
-        ] : features.taskType === "tool_agent" || features.taskType === "tool_agent_parallel" && features.agentDomain !== "other" ? [
-          ...scoredModels,
-          ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))
-        ] : [
-          ...scoredModels,
-          ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))
-        ];
+        ] : [...scoredModels, ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))];
         const model = ranked[0] ?? base3.model;
         const selectedTierConfigs = {
           ...tierConfigs,
@@ -37964,8 +37977,8 @@ ${value.slice(-(scanLimit - prefixLength))}`;
             // $0.20/$1.25, 1M context
             "xai/grok-4-fast-non-reasoning",
             // 1,143ms, $0.20/$0.50 — fast fallback
-            "free/gpt-oss-120b"
-            // 1,252ms, FREE fallback (hidden from /v1/models but direct calls work)
+            "nvidia/step-3.7-flash"
+            // FREE backstop — new NVIDIA free tier (gpt-oss-120b now 400s; probed 2026-08-21)
           ]
         },
         MEDIUM: {
@@ -38038,14 +38051,15 @@ ${value.slice(-(scanLimit - prefixLength))}`;
       // Eco tier configs - absolute cheapest (blockrun/eco)
       ecoTiers: {
         SIMPLE: {
-          primary: "free/gpt-oss-120b",
-          // FREE! $0.00/$0.00 — heavy user default
+          primary: "nvidia/step-3.7-flash",
+          // FREE! $0.00/$0.00 — new NVIDIA free tier flagship
           fallback: [
-            "free/gpt-oss-20b",
-            // FREE — smaller, faster
-            // deepseek-v4-flash and seed-oss-36b sat here until NVIDIA EOL'd them
-            // (410; 2026-08-12 and 2026-08-03 respectively). gpt-oss-120b/20b already
-            // head this chain, so the rungs are dropped, not retargeted.
+            "nvidia/nemotron-nano-9b-v2",
+            // FREE — compact + fast (~0.7s), high-volume light tasks
+            // This head keeps rotting with NVIDIA's free hosting: deepseek-v4-flash
+            // (410, 2026-08-12), seed-oss-36b (410, 2026-08-03), then gpt-oss-120b/20b
+            // (400 Unknown model, probed 2026-08-21). Each retirement retargets the
+            // two free rungs to the current free tier; the paid rungs below never move.
             "google/gemini-3.1-flash-lite",
             // $0.25/$1.50 — newest flash-lite
             "openai/gpt-5.4-nano",
@@ -38162,8 +38176,8 @@ ${value.slice(-(scanLimit - prefixLength))}`;
             "openai/gpt-5.3-codex",
             "deepseek/deepseek-chat",
             // Cheap, reliable
-            "free/gpt-oss-120b"
-            // NVIDIA free ultimate backstop (was seed-oss-36b; EOL'd 2026-08-03)
+            "nvidia/step-3.7-flash"
+            // NVIDIA free ultimate backstop (was gpt-oss-120b; 400s since ~2026-08)
           ]
         },
         REASONING: {
@@ -38252,8 +38266,8 @@ ${value.slice(-(scanLimit - prefixLength))}`;
             // Previous flagship — 6,213ms, reliable
             "deepseek/deepseek-chat",
             // 1,431ms — cheap, reliable
-            "free/gpt-oss-120b"
-            // NVIDIA free ultimate backstop (was seed-oss-36b; EOL'd 2026-08-03)
+            "nvidia/step-3.7-flash"
+            // NVIDIA free ultimate backstop (was gpt-oss-120b; 400s since ~2026-08)
           ]
         },
         REASONING: {
@@ -57791,6 +57805,14 @@ Then run: npx @blockrun/clawrouter`
     solanaAddress = await getSolanaAddress(derived.solanaPrivateKeyBytes);
   } catch {
   }
+  let solanaDefaultSaved = false;
+  if (solanaAddress) {
+    try {
+      await savePaymentChain("solana");
+      solanaDefaultSaved = true;
+    } catch {
+    }
+  }
   console.log(`[ClawRouter]`);
   console.log(`[ClawRouter] \u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550`);
   console.log(`[ClawRouter]   NEW WALLET GENERATED \u2014 BACK UP YOUR KEY NOW`);
@@ -57803,6 +57825,12 @@ Then run: npx @blockrun/clawrouter`
   console.log(`[ClawRouter]   Mnemonic       : ${MNEMONIC_FILE}`);
   console.log(`[ClawRouter]`);
   console.log(`[ClawRouter]   Both EVM (Base) and Solana wallets are ready.`);
+  if (solanaDefaultSaved) {
+    console.log(
+      `[ClawRouter]   Default payment chain: Solana \u2014 fund the Solana address above with USDC.`
+    );
+    console.log(`[ClawRouter]   To switch to Base, run in OpenClaw: /wallet base`);
+  }
   console.log(`[ClawRouter]   To back up, run in OpenClaw:`);
   console.log(`[ClawRouter]     /wallet export`);
   console.log(`[ClawRouter]`);

package/dist/router/index.js

@@ -363,6 +363,21 @@ function applyPromotions(tierConfigs, promotions, profile, now = /* @__PURE__ */
   }
   return result;
 }
+function applyUnavailableModels(tierConfigs, unavailableModels) {
+  if (!unavailableModels || unavailableModels.length === 0) return tierConfigs;
+  const dead = new Set(unavailableModels);
+  let result = tierConfigs;
+  for (const tier of Object.keys(tierConfigs)) {
+    const config = tierConfigs[tier];
+    const alive = [config.primary, ...config.fallback].filter((model) => !dead.has(model));
+    if (alive.length === 0 || alive[0] === config.primary && alive.length === config.fallback.length + 1) {
+      continue;
+    }
+    if (result === tierConfigs) result = { ...tierConfigs };
+    result[tier] = { primary: alive[0], fallback: alive.slice(1) };
+  }
+  return result;
+}
 var RulesStrategy = class {
   name = "rules";
   route(prompt, systemPrompt, maxOutputTokens, options) {
@@ -414,6 +429,7 @@ ${value.slice(-(scanLimit - prefixLength))}`;
       profile = useAgenticTiers ? "agentic" : "auto";
     }
     tierConfigs = applyPromotions(tierConfigs, config.promotions, profile, options.now);
+    tierConfigs = applyUnavailableModels(tierConfigs, options.unavailableModels);
     const agenticScoreValue = ruleResult.agenticScore;
     if (estimatedTokens > config.overrides.maxTokensForceComplex) {
       const decision2 = selectModel(
@@ -552,18 +568,6 @@ var DEFAULT_MODEL_CAPABILITIES = Object.freeze({
     supportsTools: false,
     supportsVision: false
   },
-  "free/gpt-oss-120b": {
-    contextWindow: 128e3,
-    maxOutputTokens: 16384,
-    supportsTools: false,
-    supportsVision: false
-  },
-  "free/gpt-oss-20b": {
-    contextWindow: 128e3,
-    maxOutputTokens: 16384,
-    supportsTools: false,
-    supportsVision: false
-  },
   "free/seed-oss-36b": {
     contextWindow: 131072,
     maxOutputTokens: 16384,
@@ -636,6 +640,18 @@ var DEFAULT_MODEL_CAPABILITIES = Object.freeze({
     supportsTools: true,
     supportsVision: true
   },
+  "nvidia/nemotron-nano-9b-v2": {
+    contextWindow: 131072,
+    maxOutputTokens: 16384,
+    supportsTools: false,
+    supportsVision: false
+  },
+  "nvidia/step-3.7-flash": {
+    contextWindow: 131072,
+    maxOutputTokens: 16384,
+    supportsTools: false,
+    supportsVision: false
+  },
   "openai/gpt-4.1": {
     contextWindow: 128e3,
     maxOutputTokens: 16384,
@@ -1732,9 +1748,12 @@ var PortfolioStrategy = class {
     const targetTier = (features.taskType === "reasoning_mcq" || features.taskType === "reasoning_math") && (base.tier === "SIMPLE" || base.tier === "MEDIUM") ? "REASONING" : base.tier;
     const tierConfig = tierConfigs[targetTier];
     const configuredCandidates = tierConfig ? getFallbackChain(targetTier, tierConfigs) : [];
+    const unavailable = new Set(options.unavailableModels ?? []);
     const chain = [
       .../* @__PURE__ */ new Set([...configuredCandidates, ...evidenceCandidates(features.taskType)])
-    ].filter((model2) => typeof model2 === "string" && model2.length > 0);
+    ].filter(
+      (model2) => typeof model2 === "string" && model2.length > 0 && !unavailable.has(model2)
+    );
     const eligible = chain.filter(
       (model2) => isEligible(model2, features, maxOutputTokens, options)
     );
@@ -1811,13 +1830,7 @@ var PortfolioStrategy = class {
       ...eligibleCandidates.filter(
         (model2) => !scoredModels.includes(model2) && !webResearchFallbackOrder.includes(model2)
       )
-    ] : features.taskType === "tool_agent" || features.taskType === "tool_agent_parallel" && features.agentDomain !== "other" ? [
-      ...scoredModels,
-      ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))
-    ] : [
-      ...scoredModels,
-      ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))
-    ];
+    ] : [...scoredModels, ...eligibleCandidates.filter((model2) => !scoredModels.includes(model2))];
     const model = ranked[0] ?? base.model;
     const selectedTierConfigs = {
       ...tierConfigs,
@@ -2929,8 +2942,8 @@ var DEFAULT_ROUTING_CONFIG = {
         // $0.20/$1.25, 1M context
         "xai/grok-4-fast-non-reasoning",
         // 1,143ms, $0.20/$0.50 — fast fallback
-        "free/gpt-oss-120b"
-        // 1,252ms, FREE fallback (hidden from /v1/models but direct calls work)
+        "nvidia/step-3.7-flash"
+        // FREE backstop — new NVIDIA free tier (gpt-oss-120b now 400s; probed 2026-08-21)
       ]
     },
     MEDIUM: {
@@ -3003,14 +3016,15 @@ var DEFAULT_ROUTING_CONFIG = {
   // Eco tier configs - absolute cheapest (blockrun/eco)
   ecoTiers: {
     SIMPLE: {
-      primary: "free/gpt-oss-120b",
-      // FREE! $0.00/$0.00 — heavy user default
+      primary: "nvidia/step-3.7-flash",
+      // FREE! $0.00/$0.00 — new NVIDIA free tier flagship
       fallback: [
-        "free/gpt-oss-20b",
-        // FREE — smaller, faster
-        // deepseek-v4-flash and seed-oss-36b sat here until NVIDIA EOL'd them
-        // (410; 2026-08-12 and 2026-08-03 respectively). gpt-oss-120b/20b already
-        // head this chain, so the rungs are dropped, not retargeted.
+        "nvidia/nemotron-nano-9b-v2",
+        // FREE — compact + fast (~0.7s), high-volume light tasks
+        // This head keeps rotting with NVIDIA's free hosting: deepseek-v4-flash
+        // (410, 2026-08-12), seed-oss-36b (410, 2026-08-03), then gpt-oss-120b/20b
+        // (400 Unknown model, probed 2026-08-21). Each retirement retargets the
+        // two free rungs to the current free tier; the paid rungs below never move.
         "google/gemini-3.1-flash-lite",
         // $0.25/$1.50 — newest flash-lite
         "openai/gpt-5.4-nano",
@@ -3127,8 +3141,8 @@ var DEFAULT_ROUTING_CONFIG = {
         "openai/gpt-5.3-codex",
         "deepseek/deepseek-chat",
         // Cheap, reliable
-        "free/gpt-oss-120b"
-        // NVIDIA free ultimate backstop (was seed-oss-36b; EOL'd 2026-08-03)
+        "nvidia/step-3.7-flash"
+        // NVIDIA free ultimate backstop (was gpt-oss-120b; 400s since ~2026-08)
       ]
     },
     REASONING: {
@@ -3217,8 +3231,8 @@ var DEFAULT_ROUTING_CONFIG = {
         // Previous flagship — 6,213ms, reliable
         "deepseek/deepseek-chat",
         // 1,431ms — cheap, reliable
-        "free/gpt-oss-120b"
-        // NVIDIA free ultimate backstop (was seed-oss-36b; EOL'd 2026-08-03)
+        "nvidia/step-3.7-flash"
+        // NVIDIA free ultimate backstop (was gpt-oss-120b; 400s since ~2026-08)
       ]
     },
     REASONING: {
@@ -3275,6 +3289,7 @@ export {
   LIVE_MODEL_PROFILES,
   PortfolioStrategy,
   RulesStrategy,
+  applyUnavailableModels,
   calculateModelCost,
   classifyByRules,
   filterByExcludeList,

package/docs/anthropic-cost-savings.md

@@ -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 <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> 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 -->71<!-- /br:models.chatVisible --> AI models. It saves you money in three ways: **smart routing**, **token optimization**, and **response caching**.
 
 ```
 ┌─────────────┐     ┌──────────────────────────────┐     ┌──────────────────┐

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

@@ -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 <!-- br:models.chatVisible -->70<!-- /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.
+ClawRouter is an open-source local proxy that sits between your agent and <!-- br:models.chatVisible -->71<!-- /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
@@ -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** — <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> models, switch anytime
+- **No vendor lock-in** — <!-- br:models.chatVisible -->71<!-- /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

package/docs/clawrouter-cuts-llm-api-costs-500x.md

@@ -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 <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> 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 -->71<!-- /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.
 

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

@@ -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 <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> 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 -->71<!-- /br:models.chatVisible --> models with automatic legacy-to-modern redirects). Direct provider routing means no dropped payloads.](./assets/clawrouter-feature-parity-direct-connectivity.png)
 
 ---
 
@@ -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 <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> 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 -->71<!-- /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
@@ -268,7 +268,7 @@ No silent drops. No stale catalog. Models are benchmarked for speed, quality, an
 | **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 -->70<!-- /br:models.chatVisible --> models, redirect aliases         |
+| **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 -->88<!-- /br:savings.autoVsBaselinePct -->% savings** |

package/docs/configuration.md

@@ -158,17 +158,10 @@ Response (dual-chain):
 
 ```bash
 /wallet solana    # Switch to Solana USDC payments
-/wallet base      # Switch back to Base (EVM) USDC payments
+/wallet base      # Switch to Base (EVM) USDC payments
 ```
 
-Or use the `/chain` command:
-
-```bash
-/chain solana
-/chain base
-```
-
-The selected chain is persisted across gateway restarts.
+The selected chain is persisted across gateway restarts (in `~/.openclaw/blockrun/payment-chain`). New installs default to **Solana** (persisted when the wallet is first generated); existing installs without a saved selection stay on **Base**, where their funds already live. The `CLAWROUTER_PAYMENT_CHAIN` environment variable (`solana` or `base`) overrides the persisted selection.
 
 ### Switch Wallets
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@blockrun/clawrouter",
-  "version": "0.12.245",
-  "description": "Smart LLM router — save 88% on inference costs. 70 models (5 free), one wallet, x402 micropayments.",
+  "version": "0.12.246",
+  "description": "Smart LLM router — save 88% on inference costs. 71 models (5 free), one wallet, x402 micropayments.",
   "type": "module",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -110,7 +110,7 @@
     }
   },
   "devDependencies": {
-    "@blockrun/router-core": "https://codeload.github.com/BlockRunAI/router-core/tar.gz/18bf4abc7e34599e51595b90703c385f53d4f4a6",
+    "@blockrun/router-core": "https://codeload.github.com/BlockRunAI/router-core/tar.gz/d7bc10ce184b3daa40bcc115b523fd629d847a52",
     "@eslint/js": "^10.0.1",
     "eslint": "^10.2.0",
     "openclaw": "^2026.7.2-beta.7",

package/skills/clawrouter/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: clawrouter
-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 70 models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 5 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. 5 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 -->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 -->70<!-- /br:models.chatVisible --> models from 9 providers (<!-- br:models.free -->5<!-- /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 -->5<!-- /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.
 
@@ -85,7 +85,7 @@ ClawRouter does **not** collect or forward third-party provider API keys. You do
 | ----------- | --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `walletKey` | Yes       | EVM private key used to sign USDC micropayments via x402. **Auto-generated locally on first run** — no user input required. Never transmitted over the network; only detached payment signatures are sent. |
 | `solanaKey` | Yes       | Solana keypair (BIP-44 `m/44'/501'/0'/0'`). Auto-derived from the same local mnemonic via `@scure/bip32` + `@scure/bip39`.                                                                                 |
-| `gateway`   | No        | Gateway URL. Defaults: `https://blockrun.ai/api` (Base) · `https://sol.blockrun.ai/api` (Solana).                                                                                                          |
+| `gateway`   | No        | Gateway URL. Defaults: `https://sol.blockrun.ai/api` (Solana, default chain for new installs) · `https://blockrun.ai/api` (Base, default for pre-existing installs).                                       |
 | `routing`   | No        | Optional override of the default four-tier router.                                                                                                                                                         |
 
 **How and where keys are stored:**
@@ -141,7 +141,7 @@ Rules handle ~~80% of requests in <1ms. Only ambiguous queries hit the LLM class
 
 ## Available Models
 
-<!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.6-sol/terra/luna-pro [pro reasoning tiers], gpt-5.5, gpt-5.5-pro [max compute], chat-latest [ChatGPT Instant], gpt-5.4, gpt-4o, o3, claude-fable-5, claude-opus-5 [Anthropic flagship, 1M ctx], claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, claude-sonnet-5, claude-sonnet-4.6, gemini-3.1-pro, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-2.5-flash, deepseek-v4-pro, deepseek-chat, grok-4.5, grok-4.3, grok-build-0.1, kimi-k3 [1M ctx flagship], kimi-k2.7, qwen3.7-max [Qwen flagship, 1M ctx], qwen3.7-plus, qwen3.7-flash, hy3 [Tencent], mimo [Xiaomi MiMo-V2.5 Pro, 1M ctx], and 5 free NVIDIA models (nemotron-3-nano-omni-30b-a3b-reasoning [vision], mistral-nemotron, step-3.7-flash, nemotron-nano-9b-v2, nemotron-nano-12b-v2-vl [vision]).
+<!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.6-sol/terra/luna-pro [pro reasoning tiers], gpt-5.5, gpt-5.5-pro [max compute], chat-latest [ChatGPT Instant], gpt-5.4, gpt-4o, o3, claude-fable-5, claude-opus-5 [Anthropic flagship, 1M ctx], claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, claude-sonnet-5, claude-sonnet-4.6, gemini-3.1-pro, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-2.5-flash, deepseek-v4-pro, deepseek-chat, grok-4.5, grok-4.3, grok-build-0.1, kimi-k3 [1M ctx flagship], kimi-k2.7, qwen3.7-max [Qwen flagship, 1M ctx], qwen3.7-plus, qwen3.7-flash, hy3 [Tencent], mimo [Xiaomi MiMo-V2.5 Pro, 1M ctx], and 5 free NVIDIA models (nemotron-3-nano-omni-30b-a3b-reasoning [vision], mistral-nemotron, step-3.7-flash, nemotron-nano-9b-v2, nemotron-nano-12b-v2-vl [vision]).
 
 ## Built-in Agent Tools