@blockrun/clawrouter 0.12.227 → 0.12.228

package/README.md

@@ -382,16 +382,16 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 
 ## Models & Pricing
 
-55+ models across 9 providers, one wallet. **Starting at $0.0002/request.**
+55+ models across 9 providers, one wallet. **8 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).
+> **💡 "Cost per request"** = estimated cost for a typical chat message (~500 input + 500 output tokens). Paid requests also carry a flat **$0.002/tx settlement fee** (covers on-chain gas; already included in the price the gateway quotes). Free models never pay it.
 
 ### Budget Models (under $0.001/request)
 
 | Model                                         | Input $/M | Output $/M | ~$/request | Context | Features                                     |
 | --------------------------------------------- | --------: | ---------: | ---------: | ------- | -------------------------------------------- |
 | free/mistral-large-3-675b                     |  **FREE** |   **FREE** |     **$0** | 131K    | 675B general flagship, default free model    |
-| free/qwen3-next-80b-a3b-instruct              |  **FREE** |   **FREE** |     **$0** | 262K    | reasoning + coding                           |
+| free/deepseek-v4-flash                        |  **FREE** |   **FREE** |     **$0** | 1M      | reasoning + coding, huge context             |
 | free/seed-oss-36b                             |  **FREE** |   **FREE** |     **$0** | 131K    | coding                                       |
 | free/nemotron-3-nano-omni-30b-a3b-reasoning   |  **FREE** |   **FREE** |     **$0** | 256K    | reasoning, **vision** (text+img+video+audio) |
 | free/mistral-nemotron                         |  **FREE** |   **FREE** |     **$0** | 131K    | instruction following                        |
@@ -461,7 +461,7 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 | openai/gpt-5.2-pro          |    $21.00 |    $168.00 |    $0.0945 | 400K    | reasoning, tools                  |
 | openai/gpt-5.4-pro          |    $30.00 |    $180.00 |    $0.1050 | 400K    | reasoning, tools                  |
 
-> **Free tier:** several NVIDIA-hosted models cost nothing — `/model free` smart-routes across them, or pick one directly (e.g., `/model nemotron-omni` for vision, `/model qwen3-next` for 262K reasoning, `/model seed-oss` for coding, `/model mistral-large` for the 675B flagship).
+> **Free tier:** several NVIDIA-hosted models cost nothing — `/model free` smart-routes across them, or pick one directly (e.g., `/model nemotron-omni` for vision, `/model v4-flash` for 1M-context reasoning, `/model seed-oss` for coding, `/model mistral-large` for the 675B flagship).
 > **Best value:** `gpt-5-nano` and `gemini-2.5-flash-lite` deliver strong results at ~$0.0003/request.
 
 ---
@@ -720,7 +720,7 @@ ClawRouter works with any tool that makes OpenAI-compatible API calls — point
 
 ### Is ClawRouter free?
 
-ClawRouter itself is free and MIT licensed. You pay only for the LLM API calls routed through it — and several NVIDIA-hosted models (`mistral-large-3-675b`, `qwen3-next-80b-a3b-instruct`, `seed-oss-36b`, `nemotron-3-nano-omni-30b-a3b-reasoning`, `mistral-nemotron`, `step-3.7-flash`, `nemotron-nano-9b-v2`, `nemotron-nano-12b-v2-vl`) are completely free. Use `/model free` to smart-route across them, or pick any by name.
+ClawRouter itself is free and MIT licensed. You pay only for the LLM API calls routed through it — and several NVIDIA-hosted models (`mistral-large-3-675b`, `deepseek-v4-flash`, `seed-oss-36b`, `nemotron-3-nano-omni-30b-a3b-reasoning`, `mistral-nemotron`, `step-3.7-flash`, `nemotron-nano-9b-v2`, `nemotron-nano-12b-v2-vl`) are completely free. Use `/model free` to smart-route across them, or pick any by name.
 
 ---
 

package/dist/cli.js

@@ -33992,10 +33992,10 @@ var init_config = __esm({
             // FREE — smaller, faster
             "free/mistral-large-3-675b",
             // FREE — 675B general flagship (re-featured 2026-06-14)
-            "free/qwen3.5-122b-a10b",
-            // FREE — newest-gen Qwen, strong general
-            "free/qwen3-next-80b-a3b-instruct",
-            // FREE — 262K ctx, strong general (deepseek-v4-flash retired)
+            "free/deepseek-v4-flash",
+            // FREE — 1M ctx, recovered in blockrun's 2026-07-17 re-probe
+            "free/seed-oss-36b",
+            // FREE — live coder (qwen3.5-122b + qwen3-next died 2026-07)
             "google/gemini-3.1-flash-lite",
             // $0.25/$1.50 — newest flash-lite
             "openai/gpt-5.4-nano",
@@ -34300,7 +34300,7 @@ var init_top_models = __esm({
       "deepseek/deepseek-chat",
       "deepseek/deepseek-reasoner",
       "free/mistral-large-3-675b",
-      "free/qwen3-next-80b-a3b-instruct",
+      "free/deepseek-v4-flash",
       "free/seed-oss-36b",
       "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       "free/mistral-nemotron",
@@ -34570,14 +34570,12 @@ var init_models = __esm({
       "gpt-20b": "free/gpt-oss-20b",
       "nvidia/gpt-oss-120b": "free/gpt-oss-120b",
       "nvidia/gpt-oss-20b": "free/gpt-oss-20b",
+      // deepseek family → v4-flash, matching blockrun's 2026-07-17 redirect map
+      // (v4-flash recovered in the live re-probe; v3.2/v4-pro stay dead upstream).
       "nvidia/deepseek-v3.2": "free/deepseek-v4-flash",
-      // v3.2 → v4-flash (v4-pro NVIDIA hung 2026-04-30)
       "free/deepseek-v3.2": "free/deepseek-v4-flash",
-      // local pin redirect
       "nvidia/deepseek-v4-pro": "free/deepseek-v4-flash",
-      // V4 Pro NVIDIA hung 2026-04-30
       "free/deepseek-v4-pro": "free/deepseek-v4-flash",
-      // V4 Pro delisted — redirect pinned callers
       "nvidia/deepseek-v4-flash": "free/deepseek-v4-flash",
       "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       // qwen3-coder-480b retired (NVIDIA EOL 2026-06-14) → redirects to seed-oss-36b
@@ -34585,58 +34583,62 @@ var init_models = __esm({
       // resolves them), but point the generic coding shorthands at the live successor.
       "nvidia/qwen3-coder-480b": "free/qwen3-coder-480b",
       "qwen/qwen3-coder-480b-a35b-instruct": "free/qwen3-coder-480b",
-      "nvidia/glm-4.7": "free/seed-oss-36b",
+      // glm-4.7 pin keeps the real id — blockrun redirects it server-side (→ gpt-oss-120b).
+      "nvidia/glm-4.7": "free/glm-4.7",
       "nvidia/llama-4-maverick": "free/llama-4-maverick",
-      // qwen3-next thinking variant retired; live sibling is the instruct model
+      // qwen3-next: both variants died in the 2026-07-17 re-probe; pins keep the id
+      // (blockrun redirects them server-side to gpt-oss-120b).
       "nvidia/qwen3-next-80b-a3b-thinking": "free/qwen3-next-80b-a3b-instruct",
-      // New live free models from the 2026-06-14 BlockRun free-tier refresh
       "nvidia/qwen3-next-80b-a3b-instruct": "free/qwen3-next-80b-a3b-instruct",
       "nvidia/seed-oss-36b": "free/seed-oss-36b",
       "nvidia/mistral-nemotron": "free/mistral-nemotron",
       "nvidia/step-3.7-flash": "free/step-3.7-flash",
       "nvidia/nemotron-nano-9b-v2": "free/nemotron-nano-9b-v2",
       "nvidia/nemotron-nano-12b-v2-vl": "free/nemotron-nano-12b-v2-vl",
-      "nvidia/mistral-small-4-119b": "free/llama-4-maverick",
-      // NVIDIA upstream timing out — hidden + redirected server-side 2026-06-08
-      // Retired free IDs → successors (mirror server-side redirects)
-      "nvidia/nemotron-ultra-253b": "free/llama-4-maverick",
-      "nvidia/nemotron-3-super-120b": "free/llama-4-maverick",
-      "nvidia/nemotron-super-49b": "free/llama-4-maverick",
+      // nvidia/mistral-small-4-119b: no local redirect — recovered in the 2026-07-17
+      // re-probe and blockrun removed its server redirect, so pinned callers reach the
+      // real model again (upstream fallbackModel + health gate cover a relapse).
+      // Retired free IDs → successors (mirror blockrun's 2026-07-17 redirect map:
+      // ultra-253b redirects to gpt-oss-120b; the two supers have NO server redirect —
+      // they stay hidden-but-routable, so their pins pass through to the real ids).
+      "nvidia/nemotron-ultra-253b": "free/gpt-oss-120b",
       // mistral-large-3-675b un-retired 2026-06-14: BlockRun re-featured it (available,
       // NVIDIA upstream recovered) so it's a real free catalog entry again.
       "nvidia/mistral-large-3-675b": "free/mistral-large-3-675b",
       "nvidia/qwen3.5-122b-a10b": "free/qwen3.5-122b-a10b",
-      "nvidia/devstral-2-123b": "free/seed-oss-36b",
-      "free/nemotron-ultra-253b": "free/llama-4-maverick",
-      "free/nemotron-3-super-120b": "free/llama-4-maverick",
-      "free/nemotron-super-49b": "free/llama-4-maverick",
-      "free/devstral-2-123b": "free/seed-oss-36b",
+      // devstral-2-123b died upstream; blockrun redirects it to gpt-oss-120b (2026-07-17 map)
+      "nvidia/devstral-2-123b": "free/gpt-oss-120b",
+      "free/nemotron-ultra-253b": "free/gpt-oss-120b",
+      "free/devstral-2-123b": "free/gpt-oss-120b",
       // New blockrun-featured free models (2026-06-14 catalog sweep)
       "mistral-large": "free/mistral-large-3-675b",
       "mistral-large-3-675b": "free/mistral-large-3-675b",
       "qwen3.5-122b": "free/qwen3.5-122b-a10b",
       "qwen3-122b": "free/qwen3.5-122b-a10b",
-      // Free model shorthand aliases
+      // Free model shorthand aliases (v4-flash recovered 2026-07-17 — live again)
       "deepseek-free": "free/deepseek-v4-flash",
-      // V4 Pro NVIDIA hung 2026-04-30 → flash
       "deepseek-v4-pro": "free/deepseek-v4-flash",
-      // free shorthand → flash (pro hung)
+      // free shorthand → flash (pro still hung)
       "deepseek-v4-flash": "free/deepseek-v4-flash",
       "v4-pro": "free/deepseek-v4-flash",
       // V4 Pro NVIDIA hung → flash
       "v4-flash": "free/deepseek-v4-flash",
-      "mistral-free": "free/llama-4-maverick",
+      "mistral-free": "free/mistral-large-3-675b",
+      // was llama-4-maverick (died 2026-07) — live Mistral flagship
       "glm-free": "free/seed-oss-36b",
       // qwen3-coder retired → live coder successor
-      "llama-free": "free/llama-4-maverick",
+      "llama-free": "free/gpt-oss-120b",
+      // no live free Llama left (maverick died 2026-07)
       "qwen-coder": "free/seed-oss-36b",
       // qwen3-coder-480b retired → seed-oss-36b
       "qwen-coder-free": "free/seed-oss-36b",
-      "qwen-thinking": "free/qwen3-next-80b-a3b-instruct",
+      "qwen-thinking": "free/gpt-oss-120b",
+      // qwen3-next died 2026-07-17; no live free Qwen left
       "qwen3-next": "free/qwen3-next-80b-a3b-instruct",
-      // now a live model (instruct)
+      // explicit-ish pin — gateway redirects
       "qwen3-next-80b": "free/qwen3-next-80b-a3b-instruct",
-      "mistral-small": "free/llama-4-maverick",
+      "mistral-small": "free/mistral-nemotron",
+      // closest live Mistral-family free model
       // New live free models (2026-06-14 BlockRun free-tier refresh)
       "seed-oss": "free/seed-oss-36b",
       "seed-oss-36b": "free/seed-oss-36b",
@@ -34652,16 +34654,19 @@ var init_models = __esm({
       "nemotron-omni": "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       "nano-omni": "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       "vision-free": "free/nemotron-3-nano-omni-30b-a3b-reasoning",
-      // Retired shorthand aliases redirect to successors
-      nemotron: "free/llama-4-maverick",
-      "nemotron-ultra": "free/llama-4-maverick",
-      "nemotron-253b": "free/llama-4-maverick",
-      "nemotron-super": "free/llama-4-maverick",
-      "nemotron-49b": "free/llama-4-maverick",
-      "nemotron-120b": "free/llama-4-maverick",
+      // Retired shorthand aliases redirect to live successors (2026-07-17 map:
+      // llama-4-maverick died, so the old catch-all target moved to gpt-oss-120b)
+      nemotron: "free/nemotron-3-nano-omni-30b-a3b-reasoning",
+      // strongest live Nemotron
+      "nemotron-ultra": "free/gpt-oss-120b",
+      "nemotron-253b": "free/gpt-oss-120b",
+      "nemotron-super": "free/gpt-oss-120b",
+      "nemotron-49b": "free/gpt-oss-120b",
+      "nemotron-120b": "free/gpt-oss-120b",
       devstral: "free/seed-oss-36b",
       "devstral-2": "free/seed-oss-36b",
       maverick: "free/llama-4-maverick",
+      // explicit-ish pin — gateway redirects
       free: "free/gpt-oss-120b",
       // MiniMax (minimax → current flagship: M3)
       minimax: "minimax/minimax-m3",
@@ -35590,6 +35595,8 @@ var init_models = __esm({
         // V4 Flash: 284B / 13B active MoE, 1M context. ~5x faster than V4 Pro.
         // Strong on chat/summarization (MMLU-Pro 86.2). Caveat: weaker factual
         // recall (SimpleQA 34% vs Pro's 58%) — pick V4 Pro for fact-heavy loops.
+        // Recovered in blockrun's 2026-07-17 live re-probe (3.2s both passes) —
+        // un-hidden upstream and back in the advertised free 8.
         id: "free/deepseek-v4-flash",
         name: "[Free] DeepSeek V4 Flash",
         version: "v4-flash",
@@ -35670,10 +35677,12 @@ var init_models = __esm({
       },
       // 2026-06-16: BlockRun's 2026-06-14 free-tier refresh (self-healing health gate
       // + probe-verified lineup, blockrun commit 5817ecd) added these live NVIDIA free
-      // models. qwen3-coder-480b was retired (NVIDIA EOL 2026-06-14) and now redirects
-      // server-side to seed-oss-36b; deepseek-v4-flash/glm-4.7 stay catalog-only.
+      // models. Status per blockrun's 2026-07-17 live re-probe: qwen3-coder-480b and
+      // glm-4.7 stay dead (server-redirected); deepseek-v4-flash recovered (see above).
       {
-        // Qwen3-Next 80B (A3B active MoE): 262K context, strong reasoning + coding.
+        // Qwen3-Next 80B (A3B active MoE): 262K context. DIED in the 2026-07-17
+        // re-probe (">60s / DEGRADED") — hidden upstream, gateway redirects pinned
+        // callers to gpt-oss-120b. Entry kept so pins stay routable; off the picker.
         id: "free/qwen3-next-80b-a3b-instruct",
         name: "[Free] Qwen3-Next 80B Instruct",
         version: "next-80b-a3b",
@@ -84552,6 +84561,7 @@ function estimateAmount(modelId, bodyLength, maxTokens) {
     const estimatedOutputTokens = maxTokens || model.maxOutput || 4096;
     costUsd = estimatedInputTokens / 1e6 * model.inputPrice + estimatedOutputTokens / 1e6 * model.outputPrice;
   }
+  if (costUsd > 0) costUsd += 2e-3;
   const amountMicros = Math.max(1e3, Math.ceil(costUsd * 1.2 * 1e6));
   return amountMicros.toString();
 }
@@ -88009,12 +88019,8 @@ var init_proxy = __esm({
       "free/gpt-oss-20b",
       "free/mistral-large-3-675b",
       // 675B general flagship (re-featured 2026-06-14)
-      "free/qwen3.5-122b-a10b",
-      // newest-gen Qwen, strong general
-      "free/qwen3-next-80b-a3b-instruct",
-      // 262K ctx, strong reasoning + coding
-      "free/llama-4-maverick",
-      // BlockRun's primary free fallback
+      "free/deepseek-v4-flash",
+      // 1M ctx, recovered 2026-07-17 (3.2s probe)
       "free/seed-oss-36b",
       // live coder (successor to retired qwen3-coder-480b)
       "free/mistral-nemotron",

package/dist/index.js

@@ -90,7 +90,7 @@ var init_top_models = __esm({
       "deepseek/deepseek-chat",
       "deepseek/deepseek-reasoner",
       "free/mistral-large-3-675b",
-      "free/qwen3-next-80b-a3b-instruct",
+      "free/deepseek-v4-flash",
       "free/seed-oss-36b",
       "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       "free/mistral-nemotron",
@@ -360,14 +360,12 @@ var init_models = __esm({
       "gpt-20b": "free/gpt-oss-20b",
       "nvidia/gpt-oss-120b": "free/gpt-oss-120b",
       "nvidia/gpt-oss-20b": "free/gpt-oss-20b",
+      // deepseek family → v4-flash, matching blockrun's 2026-07-17 redirect map
+      // (v4-flash recovered in the live re-probe; v3.2/v4-pro stay dead upstream).
       "nvidia/deepseek-v3.2": "free/deepseek-v4-flash",
-      // v3.2 → v4-flash (v4-pro NVIDIA hung 2026-04-30)
       "free/deepseek-v3.2": "free/deepseek-v4-flash",
-      // local pin redirect
       "nvidia/deepseek-v4-pro": "free/deepseek-v4-flash",
-      // V4 Pro NVIDIA hung 2026-04-30
       "free/deepseek-v4-pro": "free/deepseek-v4-flash",
-      // V4 Pro delisted — redirect pinned callers
       "nvidia/deepseek-v4-flash": "free/deepseek-v4-flash",
       "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       // qwen3-coder-480b retired (NVIDIA EOL 2026-06-14) → redirects to seed-oss-36b
@@ -375,58 +373,62 @@ var init_models = __esm({
       // resolves them), but point the generic coding shorthands at the live successor.
       "nvidia/qwen3-coder-480b": "free/qwen3-coder-480b",
       "qwen/qwen3-coder-480b-a35b-instruct": "free/qwen3-coder-480b",
-      "nvidia/glm-4.7": "free/seed-oss-36b",
+      // glm-4.7 pin keeps the real id — blockrun redirects it server-side (→ gpt-oss-120b).
+      "nvidia/glm-4.7": "free/glm-4.7",
       "nvidia/llama-4-maverick": "free/llama-4-maverick",
-      // qwen3-next thinking variant retired; live sibling is the instruct model
+      // qwen3-next: both variants died in the 2026-07-17 re-probe; pins keep the id
+      // (blockrun redirects them server-side to gpt-oss-120b).
       "nvidia/qwen3-next-80b-a3b-thinking": "free/qwen3-next-80b-a3b-instruct",
-      // New live free models from the 2026-06-14 BlockRun free-tier refresh
       "nvidia/qwen3-next-80b-a3b-instruct": "free/qwen3-next-80b-a3b-instruct",
       "nvidia/seed-oss-36b": "free/seed-oss-36b",
       "nvidia/mistral-nemotron": "free/mistral-nemotron",
       "nvidia/step-3.7-flash": "free/step-3.7-flash",
       "nvidia/nemotron-nano-9b-v2": "free/nemotron-nano-9b-v2",
       "nvidia/nemotron-nano-12b-v2-vl": "free/nemotron-nano-12b-v2-vl",
-      "nvidia/mistral-small-4-119b": "free/llama-4-maverick",
-      // NVIDIA upstream timing out — hidden + redirected server-side 2026-06-08
-      // Retired free IDs → successors (mirror server-side redirects)
-      "nvidia/nemotron-ultra-253b": "free/llama-4-maverick",
-      "nvidia/nemotron-3-super-120b": "free/llama-4-maverick",
-      "nvidia/nemotron-super-49b": "free/llama-4-maverick",
+      // nvidia/mistral-small-4-119b: no local redirect — recovered in the 2026-07-17
+      // re-probe and blockrun removed its server redirect, so pinned callers reach the
+      // real model again (upstream fallbackModel + health gate cover a relapse).
+      // Retired free IDs → successors (mirror blockrun's 2026-07-17 redirect map:
+      // ultra-253b redirects to gpt-oss-120b; the two supers have NO server redirect —
+      // they stay hidden-but-routable, so their pins pass through to the real ids).
+      "nvidia/nemotron-ultra-253b": "free/gpt-oss-120b",
       // mistral-large-3-675b un-retired 2026-06-14: BlockRun re-featured it (available,
       // NVIDIA upstream recovered) so it's a real free catalog entry again.
       "nvidia/mistral-large-3-675b": "free/mistral-large-3-675b",
       "nvidia/qwen3.5-122b-a10b": "free/qwen3.5-122b-a10b",
-      "nvidia/devstral-2-123b": "free/seed-oss-36b",
-      "free/nemotron-ultra-253b": "free/llama-4-maverick",
-      "free/nemotron-3-super-120b": "free/llama-4-maverick",
-      "free/nemotron-super-49b": "free/llama-4-maverick",
-      "free/devstral-2-123b": "free/seed-oss-36b",
+      // devstral-2-123b died upstream; blockrun redirects it to gpt-oss-120b (2026-07-17 map)
+      "nvidia/devstral-2-123b": "free/gpt-oss-120b",
+      "free/nemotron-ultra-253b": "free/gpt-oss-120b",
+      "free/devstral-2-123b": "free/gpt-oss-120b",
       // New blockrun-featured free models (2026-06-14 catalog sweep)
       "mistral-large": "free/mistral-large-3-675b",
       "mistral-large-3-675b": "free/mistral-large-3-675b",
       "qwen3.5-122b": "free/qwen3.5-122b-a10b",
       "qwen3-122b": "free/qwen3.5-122b-a10b",
-      // Free model shorthand aliases
+      // Free model shorthand aliases (v4-flash recovered 2026-07-17 — live again)
       "deepseek-free": "free/deepseek-v4-flash",
-      // V4 Pro NVIDIA hung 2026-04-30 → flash
       "deepseek-v4-pro": "free/deepseek-v4-flash",
-      // free shorthand → flash (pro hung)
+      // free shorthand → flash (pro still hung)
       "deepseek-v4-flash": "free/deepseek-v4-flash",
       "v4-pro": "free/deepseek-v4-flash",
       // V4 Pro NVIDIA hung → flash
       "v4-flash": "free/deepseek-v4-flash",
-      "mistral-free": "free/llama-4-maverick",
+      "mistral-free": "free/mistral-large-3-675b",
+      // was llama-4-maverick (died 2026-07) — live Mistral flagship
       "glm-free": "free/seed-oss-36b",
       // qwen3-coder retired → live coder successor
-      "llama-free": "free/llama-4-maverick",
+      "llama-free": "free/gpt-oss-120b",
+      // no live free Llama left (maverick died 2026-07)
       "qwen-coder": "free/seed-oss-36b",
       // qwen3-coder-480b retired → seed-oss-36b
       "qwen-coder-free": "free/seed-oss-36b",
-      "qwen-thinking": "free/qwen3-next-80b-a3b-instruct",
+      "qwen-thinking": "free/gpt-oss-120b",
+      // qwen3-next died 2026-07-17; no live free Qwen left
       "qwen3-next": "free/qwen3-next-80b-a3b-instruct",
-      // now a live model (instruct)
+      // explicit-ish pin — gateway redirects
       "qwen3-next-80b": "free/qwen3-next-80b-a3b-instruct",
-      "mistral-small": "free/llama-4-maverick",
+      "mistral-small": "free/mistral-nemotron",
+      // closest live Mistral-family free model
       // New live free models (2026-06-14 BlockRun free-tier refresh)
       "seed-oss": "free/seed-oss-36b",
       "seed-oss-36b": "free/seed-oss-36b",
@@ -442,16 +444,19 @@ var init_models = __esm({
       "nemotron-omni": "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       "nano-omni": "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       "vision-free": "free/nemotron-3-nano-omni-30b-a3b-reasoning",
-      // Retired shorthand aliases redirect to successors
-      nemotron: "free/llama-4-maverick",
-      "nemotron-ultra": "free/llama-4-maverick",
-      "nemotron-253b": "free/llama-4-maverick",
-      "nemotron-super": "free/llama-4-maverick",
-      "nemotron-49b": "free/llama-4-maverick",
-      "nemotron-120b": "free/llama-4-maverick",
+      // Retired shorthand aliases redirect to live successors (2026-07-17 map:
+      // llama-4-maverick died, so the old catch-all target moved to gpt-oss-120b)
+      nemotron: "free/nemotron-3-nano-omni-30b-a3b-reasoning",
+      // strongest live Nemotron
+      "nemotron-ultra": "free/gpt-oss-120b",
+      "nemotron-253b": "free/gpt-oss-120b",
+      "nemotron-super": "free/gpt-oss-120b",
+      "nemotron-49b": "free/gpt-oss-120b",
+      "nemotron-120b": "free/gpt-oss-120b",
       devstral: "free/seed-oss-36b",
       "devstral-2": "free/seed-oss-36b",
       maverick: "free/llama-4-maverick",
+      // explicit-ish pin — gateway redirects
       free: "free/gpt-oss-120b",
       // MiniMax (minimax → current flagship: M3)
       minimax: "minimax/minimax-m3",
@@ -1380,6 +1385,8 @@ var init_models = __esm({
         // V4 Flash: 284B / 13B active MoE, 1M context. ~5x faster than V4 Pro.
         // Strong on chat/summarization (MMLU-Pro 86.2). Caveat: weaker factual
         // recall (SimpleQA 34% vs Pro's 58%) — pick V4 Pro for fact-heavy loops.
+        // Recovered in blockrun's 2026-07-17 live re-probe (3.2s both passes) —
+        // un-hidden upstream and back in the advertised free 8.
         id: "free/deepseek-v4-flash",
         name: "[Free] DeepSeek V4 Flash",
         version: "v4-flash",
@@ -1460,10 +1467,12 @@ var init_models = __esm({
       },
       // 2026-06-16: BlockRun's 2026-06-14 free-tier refresh (self-healing health gate
       // + probe-verified lineup, blockrun commit 5817ecd) added these live NVIDIA free
-      // models. qwen3-coder-480b was retired (NVIDIA EOL 2026-06-14) and now redirects
-      // server-side to seed-oss-36b; deepseek-v4-flash/glm-4.7 stay catalog-only.
+      // models. Status per blockrun's 2026-07-17 live re-probe: qwen3-coder-480b and
+      // glm-4.7 stay dead (server-redirected); deepseek-v4-flash recovered (see above).
       {
-        // Qwen3-Next 80B (A3B active MoE): 262K context, strong reasoning + coding.
+        // Qwen3-Next 80B (A3B active MoE): 262K context. DIED in the 2026-07-17
+        // re-probe (">60s / DEGRADED") — hidden upstream, gateway redirects pinned
+        // callers to gpt-oss-120b. Entry kept so pins stay routable; off the picker.
         id: "free/qwen3-next-80b-a3b-instruct",
         name: "[Free] Qwen3-Next 80B Instruct",
         version: "next-80b-a3b",
@@ -35452,10 +35461,10 @@ var init_config = __esm({
             // FREE — smaller, faster
             "free/mistral-large-3-675b",
             // FREE — 675B general flagship (re-featured 2026-06-14)
-            "free/qwen3.5-122b-a10b",
-            // FREE — newest-gen Qwen, strong general
-            "free/qwen3-next-80b-a3b-instruct",
-            // FREE — 262K ctx, strong general (deepseek-v4-flash retired)
+            "free/deepseek-v4-flash",
+            // FREE — 1M ctx, recovered in blockrun's 2026-07-17 re-probe
+            "free/seed-oss-36b",
+            // FREE — live coder (qwen3.5-122b + qwen3-next died 2026-07)
             "google/gemini-3.1-flash-lite",
             // $0.25/$1.50 — newest flash-lite
             "openai/gpt-5.4-nano",
@@ -84372,6 +84381,7 @@ function estimateAmount(modelId, bodyLength, maxTokens) {
     const estimatedOutputTokens = maxTokens || model.maxOutput || 4096;
     costUsd = estimatedInputTokens / 1e6 * model.inputPrice + estimatedOutputTokens / 1e6 * model.outputPrice;
   }
+  if (costUsd > 0) costUsd += 2e-3;
   const amountMicros = Math.max(1e3, Math.ceil(costUsd * 1.2 * 1e6));
   return amountMicros.toString();
 }
@@ -87829,12 +87839,8 @@ var init_proxy = __esm({
       "free/gpt-oss-20b",
       "free/mistral-large-3-675b",
       // 675B general flagship (re-featured 2026-06-14)
-      "free/qwen3.5-122b-a10b",
-      // newest-gen Qwen, strong general
-      "free/qwen3-next-80b-a3b-instruct",
-      // 262K ctx, strong reasoning + coding
-      "free/llama-4-maverick",
-      // BlockRun's primary free fallback
+      "free/deepseek-v4-flash",
+      // 1M ctx, recovered 2026-07-17 (3.2s probe)
       "free/seed-oss-36b",
       // live coder (successor to retired qwen3-coder-480b)
       "free/mistral-nemotron",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@blockrun/clawrouter",
-  "version": "0.12.227",
+  "version": "0.12.228",
   "description": "Smart LLM router — save 85% on inference costs. 55+ models (8 free), one wallet, x402 micropayments.",
   "type": "module",
   "main": "dist/index.js",

package/skills/clawrouter/SKILL.md

@@ -135,7 +135,7 @@ Rules handle ~~80% of requests in <1ms. Only ambiguous queries hit the LLM class
 
 ## Available Models
 
-55+ models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.5, gpt-5.4, gpt-4o, o3, claude-fable-5, claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, claude-sonnet-5, claude-sonnet-4.6, gemini-3.1-pro, gemini-2.5-flash, deepseek-v4-pro, deepseek-chat, grok-4.5, grok-4.3, grok-build-0.1, kimi-k2.7, and 8 free NVIDIA models (mistral-large-3-675b [default, 675B flagship], qwen3-next-80b-a3b-instruct, seed-oss-36b [coding], nemotron-3-nano-omni-30b-a3b-reasoning [vision], mistral-nemotron, step-3.7-flash, nemotron-nano-9b-v2, nemotron-nano-12b-v2-vl [vision]).
+55+ models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.5, gpt-5.4, gpt-4o, o3, claude-fable-5, claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, claude-sonnet-5, claude-sonnet-4.6, gemini-3.1-pro, gemini-2.5-flash, deepseek-v4-pro, deepseek-chat, grok-4.5, grok-4.3, grok-build-0.1, kimi-k2.7, and 8 free NVIDIA models (mistral-large-3-675b [default, 675B flagship], deepseek-v4-flash [1M context], seed-oss-36b [coding], 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
 

package/src/top-models.json

@@ -36,7 +36,7 @@
   "deepseek/deepseek-chat",
   "deepseek/deepseek-reasoner",
   "free/mistral-large-3-675b",
-  "free/qwen3-next-80b-a3b-instruct",
+  "free/deepseek-v4-flash",
   "free/seed-oss-36b",
   "free/nemotron-3-nano-omni-30b-a3b-reasoning",
   "free/mistral-nemotron",