@blockrun/clawrouter 0.12.278 → 0.12.280

package/dist/router/index.js

@@ -656,18 +656,12 @@ var DEFAULT_MODEL_CAPABILITIES = Object.freeze({
     supportsTools: false,
     supportsVision: true
   },
-  "nvidia/nemotron-3-nano-30b": {
-    // supportsTools: not probed — fails closed
-    contextWindow: 131072,
-    maxOutputTokens: 16384,
-    supportsTools: false,
-    supportsVision: false
-  },
   "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
+    // override: The catalog tags this model "vision", but a correctly sized probe does not hold up (ClawRouter, 2026-08-31): a 64x64 solid-red PNG was named correctly 1 of 4 times on Base, and on Solana the image was silently dropped and a text model answered "white". An HTTP 200 with a confident wrong answer gives the caller nothing to branch on, so image turns must not be routed here. It is ecoTiers.SIMPLE.fallback[0] since nemotron-3-nano-30b was delisted (2026-09-08); remove once a probe of this size comes back right on both chains.
     contextWindow: 256e3,
     maxOutputTokens: 16384,
     supportsTools: false,
-    supportsVision: true
+    supportsVision: false
   },
   "nvidia/nemotron-3-ultra-550b": {
     // supportsTools: not probed — fails closed
@@ -3484,8 +3478,13 @@ var DEFAULT_ROUTING_CONFIG = {
       primary: "nvidia/nemotron-3.5-lightning",
       // FREE — NVIDIA free tier flagship, 1M ctx
       fallback: [
-        "nvidia/nemotron-3-nano-30b",
-        // FREE — fastest free model (~121 tok/s)
+        // Was nvidia/nemotron-3-nano-30b until blockrun delisted it on 2026-09-08
+        // (NVIDIA deprovisioned it for the account — a structured per-account
+        // 404). nano-omni is blockrun's own redirect target for that id, so this
+        // follows the same rule as the head: the router and the gateway name the
+        // same model.
+        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
+        // FREE — nano-30b's successor, 256K ctx
         // The free head keeps rotting with NVIDIA's hosting (deepseek-v4-flash
         // 410 2026-08-12, seed-oss-36b 410 2026-08-03, gpt-oss-120b/20b 400
         // 2026-08-21, and on 2026-08-30 FOUR of the five visible free models at

package/docs/9-free-ai-models-zero-cost-blockrun.md

@@ -1,7 +1,7 @@
 # 9 Free AI Models, Zero Cost: How BlockRun Gives Developers Top-Tier LLMs for Nothing
 
 > **The count in this title is a snapshot, and so is every model name below.**
-> It was 9 when this was written; the published free tier is <!-- br:models.free -->7<!-- /br:models.free --> today, and _none_ of the
+> It was 9 when this was written; the published free tier is <!-- br:models.free -->6<!-- /br:models.free --> today, and _none_ of the
 > nine originals is still in it. Free hosting is volatile — NVIDIA retired four
 > of the five visible free models in a single sweep on 2026-08-30 — so the tier
 > gets rebuilt rather than topped up. The URL keeps its original slug so existing
@@ -23,14 +23,13 @@ BlockRun's answer: just take them.
 
 ---
 
-## The Lineup: <!-- br:models.free -->7<!-- /br:models.free --> Models, $0.00
+## The Lineup: <!-- br:models.free -->6<!-- /br:models.free --> Models, $0.00
 
-Through [ClawRouter](https://github.com/BlockRunAI/ClawRouter) — BlockRun's local AI routing proxy — you get zero-cost access to the following (verified live 2026-08-30):
+Through [ClawRouter](https://github.com/BlockRunAI/ClawRouter) — BlockRun's local AI routing proxy — you get zero-cost access to the following (checked against the live catalog 2026-09-29):
 
 | Model                        | Context | Reasoning | Best For                                   |
 | ---------------------------- | ------- | --------- | ------------------------------------------ |
 | **Nemotron 3.5 Lightning**   | 1M      | ✅        | The free default — thinking-mode reasoning |
-| **Nemotron 3 Nano 30B**      | 131K    | ✅        | Fastest free model (~121 tok/s)            |
 | **Nemotron 3 Ultra 550B**    | 1M      | ✅        | Largest free model — 550B / 55B active MoE |
 | **Nemotron 3 Nano Omni 30B** | 256K    | ✅        | Strong generalist (text only in practice)  |
 | **Llama 3.2 11B Vision**     | 128K    | —         | Meta Llama (text only in practice)         |
@@ -99,12 +98,6 @@ A 30B-A3B mixture-of-experts model with a **1M-token context** and thinking-mode
 
 **Best for:** Long-context reasoning, multi-step planning, anything where the input is big. If you remember one free model name, remember this one.
 
-### Nemotron 3 Nano 30B — The Fast One
-
-The **fastest free model in the catalog** — around 121 tokens/second on realistic workloads, not just short pings. Returns reasoning content. When you are iterating rapidly and each round-trip is a tax on your attention, this is the one to pin.
-
-**Best for:** Rapid iteration, prompt engineering, high-volume light tasks.
-
 ### Nemotron 3 Ultra 550B — The Big One
 
 550 billion total parameters, 55B active, 1M context — the **largest free model ever listed**. It is genuinely strong, and it is genuinely slower than the rest of the tier; treat it as the one you reach for when the task is hard rather than the one you leave pinned.
@@ -176,7 +169,6 @@ If you're using Claude Code, one command switches you to any free model:
 
 ```
 /model free              → Nemotron 3.5 Lightning (1M ctx, the default)
-/model nano-30b          → Nemotron 3 Nano 30B (fastest)
 /model ultra-550b        → Nemotron 3 Ultra 550B (largest)
 /model vision-free       → Nemotron 3 Nano Omni (text only, see below)
 /model llama-vision      → Llama 3.2 11B Vision (text only, see below)
@@ -198,17 +190,17 @@ The gateway will return structured tool calls from these models, but ClawRouter
 
 ### 2. Reasoning Has a Ceiling
 
-Five of the seven are reasoning-capable and handle most tasks well. On the hardest problems — competition-level math, formal proofs, deep multi-step planning — they don't match Claude Opus 5 or Sonnet 5. That's why ClawRouter's REASONING tier doesn't use free models.
+Four of the six are reasoning-capable and handle most tasks well. On the hardest problems — competition-level math, formal proofs, deep multi-step planning — they don't match Claude Opus 5 or Sonnet 5. That's why ClawRouter's REASONING tier doesn't use free models.
 
 ### 3. There Is No Working Free Vision
 
-Two of the seven are catalogued as vision-capable, and neither survives a real probe. On a 64×64 solid-red PNG, `nemotron-3-nano-omni` answered correctly 1 time in 4 on Base and returned "white" on Solana — where the response's own `model` field revealed a silent fallback to a text model. `llama-3.2-11b-vision` replied "I'm unable to see the image" on 3 of 3 attempts while answering plain text fine. Every one of those failures is an **HTTP 200**: the image is dropped and a confident wrong answer comes back with no error to branch on.
+Two of the six are catalogued as vision-capable, and neither survives a real probe. On a 64×64 solid-red PNG, `nemotron-3-nano-omni` answered correctly 1 time in 4 on Base and returned "white" on Solana — where the response's own `model` field revealed a silent fallback to a text model. `llama-3.2-11b-vision` replied "I'm unable to see the image" on 3 of 3 attempts while answering plain text fine. Every one of those failures is an **HTTP 200**: the image is dropped and a confident wrong answer comes back with no error to branch on.
 
 ClawRouter therefore ships no `vision` flag on any free model, so requests carrying an image route to a paid vision model instead. The general lesson is worth more than the specific finding: **a catalog's capability list is a claim, not a measurement** — and one passing sample is not a measurement either. The first probe here returned the right colour; it took four to see that was luck.
 
 ### 4. Free Hosting Is Volatile
 
-This is the real limitation, and it is worth more than the other two. On 2026-08-30 NVIDIA retired four of the five visible free models in one sweep, and none of the nine models this article originally listed is still in the tier. Free capacity comes from whatever a provider is willing to give away this quarter. Pin a free model if you like — but build so that losing it costs you a config line, not a rewrite. That is the entire argument for putting a router in front of them.
+This is the real limitation, and it is worth more than the other two. On 2026-08-30 NVIDIA retired four of the five visible free models in one sweep, and none of the nine models this article originally listed is still in the tier. Nine days after the replacements were listed, NVIDIA deprovisioned one of them — `nemotron-3-nano-30b`, the fastest in the tier — and it was delisted on 2026-09-08. Free capacity comes from whatever a provider is willing to give away this quarter. Pin a free model if you like — but build so that losing it costs you a config line, not a rewrite. That is the entire argument for putting a router in front of them.
 
 ---
 
@@ -219,7 +211,7 @@ This is the real limitation, and it is worth more than the other two. On 2026-08
 Don't use one model for everything. Route by task type:
 
 ```
-Quick chat, formatting    → Nemotron 3 Nano 30B (fastest)
+Quick chat, formatting    → Nemotron 3 Nano Omni 30B
 Code generation           → North Mini Code or Laguna XS 2.1
 Reasoning required        → Nemotron 3.5 Lightning (1M ctx)
 Hardest free reasoning    → Nemotron 3 Ultra 550B
@@ -244,13 +236,13 @@ Look at the cost trajectory over the past three years:
 - **2023:** GPT-4 dominates alone at $30/$60 per M tokens
 - **2024:** Open-source models surge, prices halve repeatedly
 - **2025:** DeepSeek, Qwen push top-tier inference below $1/M
-- **2026:** BlockRun offers <!-- br:models.free -->7<!-- /br:models.free --> free models through a single API
+- **2026:** BlockRun offers <!-- br:models.free -->6<!-- /br:models.free --> free models through a single API
 
 **A free tier that gets rebuilt rather than retired isn't just a product feature — it's a signal.** Baseline AI capability is becoming infrastructure. Like internet bandwidth before it, the cost of "good enough" AI inference is converging toward zero.
 
 BlockRun and ClawRouter exist to be the **routing layer** in this transition: not locked to any single provider, not bound to any single model, always giving developers the lowest-cost path to the right capability.
 
-Today it's <!-- br:models.free -->7<!-- /br:models.free --> free models, and they are not the same seven as last month. Tomorrow it could be 50. Prices will only drop. Capabilities will only improve. The names will keep churning.
+Today it's <!-- br:models.free -->6<!-- /br:models.free --> free models, and they are not the same seven as last month. Tomorrow it could be 50. Prices will only drop. Capabilities will only improve. The names will keep churning.
 
 **The one constant: your code doesn't need to change.**
 
@@ -265,7 +257,7 @@ clawrouter start
 
 Point your `base_url` to `http://localhost:8402/v1`. That's the whole setup.
 
-<!-- br:models.free -->7<!-- /br:models.free --> free models. Up to 1M context. Unlimited calls. Zero cost.
+<!-- br:models.free -->6<!-- /br:models.free --> free models. Up to 1M context. Unlimited calls. Zero cost.
 
 Go build something.
 

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 -->76<!-- /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 -->82<!-- /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 -->76<!-- /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 -->82<!-- /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
@@ -74,12 +74,12 @@ 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 -->76<!-- /br:models.chatVisible --> models, switch anytime
+- **No vendor lock-in** — <!-- br:models.chatVisible -->82<!-- /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
 - **Response caching** — identical requests within 10 minutes cost $0
-- **<!-- br:models.free -->7<!-- /br:models.free --> free models** — for tasks that don't need a paid model at all
+- **<!-- br:models.free -->6<!-- /br:models.free --> free models** — for tasks that don't need a paid model at all
 
 ### Routing Profiles
 

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 -->76<!-- /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 82 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.
 
@@ -144,7 +144,7 @@ There is no monthly invoice. There is no 3am email. There is a wallet balance, a
 **`maxCostPerRun`** — a per-session cost ceiling that stops or downgrades requests once a session exceeds a configured threshold (e.g., `$0.50`). This closes the remaining gap ([#3181](https://github.com/openclaw/openclaw/issues/3181)) where a wallet with sufficient funds can still accumulate within a single run. Two modes: `graceful` (downgrade to cheaper models) and `strict` (hard 429 once the cap is hit).
 
 ```
-<!-- br:models.chatVisible@live -->76<!-- /br:models.chatVisible@live --> models. One wallet. Pay per call.
+82 models. One wallet. Pay per call.
 ```
 
 ---

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 -->76<!-- /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 -->82<!-- /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 -->76<!-- /br:models.chatVisible --> models across 9 providers (including <!-- br:models.free -->7<!-- /br:models.free --> free models), updated with each release. Delisted models have automatic redirect aliases:
+ClawRouter maintains a curated catalog of <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models across 9 providers (including <!-- br:models.free -->6<!-- /br:models.free --> free models), updated with each release. Delisted models have automatic redirect aliases:
 
 ```typescript
 // Delisted models redirect automatically
@@ -250,7 +250,7 @@ ClawRouter maintains a curated catalog of <!-- br:models.chatVisible -->76<!-- /
 
 No silent drops. No stale catalog. Models are benchmarked for speed, quality, and tool support before inclusion.
 
-![The Cost/Transparency Nexus — Local routing engine + direct connections + x402 micropayments = 100% transparency = 92% cost savings. Direct Opus routing: $25.00/M tokens. ClawRouter auto-routed: $2.05/M tokens. Transparency and cost savings are two sides of the same architectural coin.](./assets/clawrouter-cost-transparency-nexus-92-savings.png)
+![The Cost/Transparency Nexus — Local routing engine + direct connections + x402 micropayments = 100% transparency = 84% cost savings. ClawRouter auto-routing vs. pinning Claude Opus 5 on every request: 84% lower cost (98% on eco). Transparency and cost savings are two sides of the same architectural coin.](./assets/clawrouter-cost-transparency-nexus-84-savings.png)
 
 ---
 
@@ -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 -->76<!-- /br:models.chatVisible --> models, redirect aliases         |
+| **Model catalog**   | Laggy, silent drops              | Curated <!-- br:models.chatVisible -->82<!-- /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 -->84<!-- /br:savings.autoVsBaselinePct -->% savings** |

package/docs/routing-profiles.md

@@ -32,12 +32,12 @@ Use `blockrun/auto` (or `/model auto`) for the best quality/price balance.
 
 Use `blockrun/eco` for maximum cost savings. The first stop is the free tier, so simple requests can cost $0.00.
 
-| Tier      | Primary Model               | Input | Output | Fallback chain (in order)                                                                                                |
-| --------- | --------------------------- | ----- | ------ | ------------------------------------------------------------------------------------------------------------------------ |
-| SIMPLE    | free/nemotron-3.5-lightning | $0.00 | $0.00  | nemotron-3-nano-30b (free) → gemini-2.5-flash-lite → glm-5.3-flash → gpt-5.6-luna → gpt-5.4-nano → gemini-3.1-flash-lite |
-| MEDIUM    | zai/glm-5.3-flash           | $0.15 | $0.50  | deepseek-chat → gemini-3.1-flash-lite → gpt-5.6-luna → gpt-5.4-nano → gemini-2.5-flash-lite → gemini-2.5-flash           |
-| COMPLEX   | zai/glm-5.3-flash           | $0.15 | $0.50  | deepseek-chat → minimax-m3 → deepseek-v4-pro → gemini-3.1-flash-lite → gemini-2.5-flash                                  |
-| REASONING | deepseek/deepseek-reasoner  | $0.14 | $0.28  | deepseek-v4-pro → qwen3.7-plus → minimax-m3 → glm-5.3-flash                                                              |
+| Tier      | Primary Model               | Input | Output | Fallback chain (in order)                                                                                                 |
+| --------- | --------------------------- | ----- | ------ | ------------------------------------------------------------------------------------------------------------------------- |
+| SIMPLE    | free/nemotron-3.5-lightning | $0.00 | $0.00  | nemotron-3-nano-omni (free) → gemini-2.5-flash-lite → glm-5.3-flash → gpt-5.6-luna → gpt-5.4-nano → gemini-3.1-flash-lite |
+| MEDIUM    | zai/glm-5.3-flash           | $0.15 | $0.50  | deepseek-chat → gemini-3.1-flash-lite → gpt-5.6-luna → gpt-5.4-nano → gemini-2.5-flash-lite → gemini-2.5-flash            |
+| COMPLEX   | zai/glm-5.3-flash           | $0.15 | $0.50  | deepseek-chat → minimax-m3 → deepseek-v4-pro → gemini-3.1-flash-lite → gemini-2.5-flash                                   |
+| REASONING | deepseek/deepseek-reasoner  | $0.14 | $0.28  | deepseek-v4-pro → qwen3.7-plus → minimax-m3 → glm-5.3-flash                                                               |
 
 The two free rungs at the head of ECO SIMPLE follow NVIDIA's free hosting, which retires models without notice (deepseek-v4-flash 410'd 2026-08-12, seed-oss-36b 2026-08-03, gpt-oss-120b hung 2026-08-16, and on 2026-08-30 NVIDIA retired FOUR of the five visible free models at once). Each retirement retargets the free rungs to the current free tier; the paid rungs never move. `src/router/free-model-liveness.test.ts` fails the build if a chain names a free model the picker no longer lists.
 
@@ -75,11 +75,11 @@ Set `routing.overrides.agenticMode: false` to disable the agentic tier set, or `
 
 ## FREE (`/model free`)
 
-`free` is an alias, not a routed profile: it pins the free-tier default, currently **`free/nemotron-3.5-lightning`** — the same model that opens ECO SIMPLE. If that model is excluded (`/exclude add lightning`) or the budget cap forces a free fallback, the proxy walks the free cascade in this order: nemotron-3.5-lightning → nemotron-3-nano-30b → laguna-xs-2.1 → north-mini-code → nemotron-3-nano-omni-30b-a3b-reasoning → nemotron-3-ultra-550b → llama-3.2-11b-vision. All seven are $0.00 and need no USDC, and all seven are treated as **text-only** — see the vision note below.
+`free` is an alias, not a routed profile: it pins the free-tier default, currently **`free/nemotron-3.5-lightning`** — the same model that opens ECO SIMPLE. If that model is excluded (`/exclude add lightning`) or the budget cap forces a free fallback, the proxy walks the free cascade in this order: nemotron-3.5-lightning → laguna-xs-2.1 → north-mini-code → nemotron-3-nano-omni-30b-a3b-reasoning → nemotron-3-ultra-550b → llama-3.2-11b-vision. All six are $0.00 and need no USDC, and all six are treated as **text-only** — see the vision note below.
 
-The order is not arbitrary. The head is whatever the gateway itself redirects the previous head to, so the proxy and the gateway never name different models. After it comes the fastest rung, then the two sub-second coders — adjacent on purpose, because they sit on _different_ capacity pools (our own NVIDIA key vs OpenRouter's $0 pool), so one pool's outage cannot take both. The vision model sits mid-chain, and the two slowest rungs go last. The tier stopped being NVIDIA-only on 2026-08-30: two of the seven come from Cohere and Poolside.
+The order is not arbitrary. The head is whatever the gateway itself redirects the previous head to, so the proxy and the gateway never name different models. After it come the two sub-second coders — adjacent on purpose, because they sit on _different_ capacity pools (our own NVIDIA key vs OpenRouter's $0 pool), so one pool's outage cannot take both. The vision model sits mid-chain, and the two slowest rungs go last. The tier stopped being NVIDIA-only on 2026-08-30: two of the six come from Cohere and Poolside. The fastest rung, `nemotron-3-nano-30b`, left on 2026-09-08 when NVIDIA deprovisioned it for blockrun's account; its aliases (`nano-30b`, `nemotron-nano`) now follow the gateway's redirect to `nemotron-3-nano-omni`.
 
-Pin any of them directly with `/model lightning`, `/model nano-30b`, `/model laguna`, `/model north-mini`, `/model nemotron-omni`, `/model ultra-550b` or `/model llama-vision`.
+Pin any of them directly with `/model lightning`, `/model laguna`, `/model north-mini`, `/model nemotron-omni`, `/model ultra-550b` or `/model llama-vision`.
 
 **No free model carries the `vision` flag,** even the two the upstream catalogs advertise as vision-capable. A 64×64 solid-colour probe on 2026-08-31 got the right answer 1 time in 4 from `nemotron-3-nano-omni` on Base, and "white" for red on Solana — where the response's own `model` field showed a silent fallback to a text model. `llama-3.2-11b-vision`, despite the name, said "I'm unable to see the image" on 3 of 3 while a plain-text control passed. Every one of those is an HTTP 200, so the caller gets a confident wrong answer with nothing to branch on. Since `vision` is what `filterByVision()` uses to _aim_ image turns at a model, flagging them would route real traffic into that. Requests carrying an `image_url` go to a paid vision model.
 

package/openclaw.plugin.json

@@ -1,7 +1,7 @@
 {
   "id": "blockrun-clawrouter",
   "name": "BlockRun ClawRouter",
-  "description": "Smart LLM router \u2014 55+ models, x402 micropayments, 92% cost savings. Phone lookup + AI voice calls (Twilio + Bland.ai). Surf crypto-data API (84 endpoints, on-chain SQL, 100M+ labeled wallets) via skill.",
+  "description": "Smart LLM router \u2014 82 models, x402 micropayments, 84% cost savings. Phone lookup + AI voice calls (Twilio + Bland.ai). Surf crypto-data API (84 endpoints, on-chain SQL, 100M+ labeled wallets) via skill.",
   "skills": ["./skills"],
   "activation": {
     "onStartup": true

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@blockrun/clawrouter",
-  "version": "0.12.278",
-  "description": "Smart LLM router — save 84% on inference costs. 76 models (7 free). Pay by credit card (API key) or USDC (x402 wallet).",
+  "version": "0.12.280",
+  "description": "Smart LLM router — save 84% on inference costs. 82 models (6 free). Pay by credit card (API key) or USDC (x402 wallet).",
   "type": "module",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -95,7 +95,7 @@
     "@polymarket/clob-client-v2": "1.0.8",
     "@scure/bip32": "^2.0.1",
     "@scure/bip39": "^1.5.0",
-    "@solana/kit": "^5.0.0",
+    "@solana/kit": "^8.4.0",
     "@x402/core": "^2.9.0",
     "@x402/evm": "^2.9.0",
     "@x402/fetch": "^2.9.0",
@@ -115,7 +115,7 @@
     }
   },
   "devDependencies": {
-    "@blockrun/router-core": "https://codeload.github.com/BlockRunAI/router-core/tar.gz/5ee7c23c993013a8052588191569db5cf7fb793c",
+    "@blockrun/router-core": "https://codeload.github.com/BlockRunAI/router-core/tar.gz/e38958bba9af0aaa788c5baafbdaff539638b7c9",
     "@eslint/js": "^10.0.1",
     "eslint": "^10.2.0",
     "openclaw": "^2026.7.2-beta.7",
@@ -129,19 +129,18 @@
   "overrides": {
     "axios": "$axios",
     "undici": "$undici",
-    "basic-ftp": "^5.3.1",
     "ws": "^8.21.2",
     "postcss": "^8.5.25",
     "esbuild": "^0.28.1",
     "brace-expansion": "^5.0.9",
     "fast-uri": "^3.1.5",
     "tar": "^7.5.22",
-    "hono": "^4.13.0",
+    "hono": "^4.13.5",
     "@hono/node-server": "^2.1.0",
     "ip-address": "^10.4.0",
-    "jayson": {
-      "uuid": "^11.1.1"
-    }
+    "@solana-program/compute-budget": "^0.18.1",
+    "@solana-program/token": "^0.16.1",
+    "@solana-program/token-2022": "^0.16.1"
   },
   "engines": {
     "node": ">=22"

package/scripts/reinstall.sh

@@ -988,7 +988,6 @@ echo "  /model free      → nemotron-3.5-lightning (default free)"
 echo ""
 echo "Free models (no wallet needed):"
 echo "  /model lightning      → nemotron-3.5-lightning (1M ctx, reasoning)"
-echo "  /model nano-30b       → nemotron-3-nano-30b (fastest, ~121 tok/s)"
 echo "  /model north-mini     → north-mini-code (Cohere, coding, sub-second)"
 echo "  /model laguna         → laguna-xs-2.1 (Poolside, coding, ~161 tok/s)"
 echo "  /model vision-free    → nemotron-3-nano-omni (text/image/video/audio)"

package/skills/clawrouter/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: clawrouter
-description: Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight 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 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 82 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 6 free open-weight 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 -->84<!-- /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 -->76<!-- /br:models.chatVisible --> models from 9 providers (<!-- br:models.free -->7<!-- /br:models.free --> free open-weight models). All billing flows through one BlockRun credential — either a USDC wallet paying x402 per call, or a BlockRun API key drawing on card-funded account credit. Either way you do not hold provider API keys.
+Hosted-gateway LLM router that saves <!-- br:savings.autoVsBaselinePct -->84<!-- /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 -->82<!-- /br:models.chatVisible --> models from 9 providers (<!-- br:models.free -->6<!-- /br:models.free --> free open-weight models). All billing flows through one BlockRun credential — either a USDC wallet paying x402 per call, or a BlockRun API key drawing on card-funded account credit. Either way 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.
 
@@ -147,7 +147,7 @@ it against a baseline nobody wrote down. See
 
 ## Available Models
 
-<!-- br:models.chatVisible -->76<!-- /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, glm-5.3 [Z.AI flagship, 1M ctx], glm-5.3-flash [natively multimodal, 1M ctx — $0.15/$0.50], glm-5.2, minimax-m3, 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 7 free open-weight models (nemotron-3.5-lightning [1M ctx, thinking mode — the free default], nemotron-3-nano-30b [fastest, ~121 tok/s], nemotron-3-ultra-550b [550B/55B MoE, 1M ctx — the largest free model], nemotron-3-nano-omni-30b-a3b-reasoning [256K ctx], llama-3.2-11b-vision [Meta Llama], north-mini-code [Cohere, coding, sub-second], laguna-xs-2.1 [Poolside, coding, ~161 tok/s]). The free tier is text-only — image turns route to a paid vision model, because the two free models the catalogs advertise as vision-capable fail a solid-colour probe on both chains and do so with an HTTP 200.
+<!-- br:models.chatVisible -->82<!-- /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, glm-5.3 [Z.AI flagship, 1M ctx], glm-5.3-flash [natively multimodal, 1M ctx — $0.15/$0.50], glm-5.2, minimax-m3, 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 <!-- br:models.free -->6<!-- /br:models.free --> free open-weight models (nemotron-3.5-lightning [1M ctx, thinking mode — the free default], nemotron-3-ultra-550b [550B/55B MoE, 1M ctx — the largest free model], nemotron-3-nano-omni-30b-a3b-reasoning [256K ctx], llama-3.2-11b-vision [Meta Llama], north-mini-code [Cohere, coding, sub-second], laguna-xs-2.1 [Poolside, coding, ~161 tok/s]). The free tier is text-only — image turns route to a paid vision model, because the two free models the catalogs advertise as vision-capable fail a solid-colour probe on both chains and do so with an HTTP 200.
 
 ## Built-in Agent Tools
 

package/src/top-models.json

@@ -49,7 +49,6 @@
   "deepseek/deepseek-chat",
   "deepseek/deepseek-reasoner",
   "free/nemotron-3.5-lightning",
-  "free/nemotron-3-nano-30b",
   "free/laguna-xs-2.1",
   "free/north-mini-code",
   "free/nemotron-3-nano-omni-30b-a3b-reasoning",