npm - @blockrun/clawrouter - Versions diffs - 0.12.244 → 0.12.245 - Mend

@blockrun/clawrouter 0.12.244 → 0.12.245

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (11) hide show

package/README.md +31 -23
package/dist/cli.js +217 -40
package/dist/index.js +217 -40
package/dist/router/index.js +3 -4
package/docs/anthropic-cost-savings.md +1 -1
package/docs/anthropic-third-party-harness-changes.md +2 -2
package/docs/clawrouter-cuts-llm-api-costs-500x.md +1 -1
package/docs/clawrouter-vs-openrouter-llm-routing-comparison.md +3 -3
package/package.json +3 -3
package/skills/clawrouter/SKILL.md +3 -3
package/src/top-models.json +0 -1

package/README.md CHANGED Viewed

@@ -7,11 +7,11 @@
 <p>Agents can't sign up for accounts. Agents can't enter credit cards.<br>
 Agents can only sign transactions.<br><br>
 <strong>ClawRouter is the only LLM router that lets agents operate independently.</strong><br><br>
-<em><!-- br:models.free -->6<!-- /br:models.free --> models free, no crypto required. No signup. No API key. No credit card.</em></p>
+<em><!-- br:models.free -->5<!-- /br:models.free --> models free, no crypto required. No signup. No API key. No credit card.</em></p>
 <br>
-<img src="https://img.shields.io/badge/🆓_6_Free_Models-success?style=for-the-badge" alt="6 free models">&nbsp;
+<img src="https://img.shields.io/badge/🆓_5_Free_Models-success?style=for-the-badge" alt="5 free models">&nbsp;
 <img src="https://img.shields.io/badge/🤖_Agent--Native-black?style=for-the-badge" alt="Agent native">&nbsp;
 <img src="https://img.shields.io/badge/🔑_Zero_API_Keys-blue?style=for-the-badge" alt="No API keys">&nbsp;
 <img src="https://img.shields.io/badge/⚡_Local_Routing-yellow?style=for-the-badge" alt="Local routing">&nbsp;
@@ -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 -->71<!-- /br:models.chatVisible --> models from OpenAI, Anthropic, Google, xAI, DeepSeek, and more. MIT licensed.
+> **ClawRouter** is an open-source smart LLM router that reduces AI API costs by up to <!-- br:savings.autoVsBaselinePct -->88<!-- /br:savings.autoVsBaselinePct -->%. It analyzes each request across <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions --> dimensions and routes to the cheapest capable model in under 1ms, entirely locally. ClawRouter is the only LLM router built for autonomous AI agents — it uses wallet signatures for authentication (no API keys) and USDC micropayments via the x402 protocol (no credit cards). <!-- br:models.chatVisible -->70<!-- /br:models.chatVisible --> models from OpenAI, Anthropic, Google, xAI, DeepSeek, and more. MIT licensed.
 ---
@@ -46,7 +46,7 @@ Every other LLM router was built for **human developers** — create an account,
 ClawRouter is built for the agent-first world:
-- **Starts at $0** — <!-- br:models.free -->6<!-- /br:models.free --> NVIDIA models are free forever (incl. 1M-context DeepSeek V4 Flash + a vision-capable Nemotron Omni)
+- **Starts at $0** — <!-- br:models.free -->5<!-- /br:models.free --> NVIDIA models are free forever (incl. 1M-context DeepSeek V4 Flash + a vision-capable Nemotron Omni)
 - **No accounts** — a wallet is generated locally, no signup
 - **No API keys** — your wallet signature IS authentication
 - **No model selection** — <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions -->-dimension scoring picks the right model automatically
@@ -61,8 +61,8 @@ 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 -->71<!-- /br:models.chatVisible -->**    |
-| **Free tier**    | Rate-limited      | BYO keys         | No                | No                | **<!-- br:models.free -->6<!-- /br:models.free --> models, no signup** |
+| **Models**       | 200+              | 100+             | Smart routing     | Gateway           | **<!-- br:models.chatVisible -->70<!-- /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**                                                   |
 | **Payment**      | Credit card       | BYO keys         | Credit card       | $49-499/mo        | **USDC per-request**                                                   |
@@ -78,7 +78,7 @@ This is the stack that lets agents operate autonomously: **x402 + USDC + local r
 ## Quick Start
-> **No wallet? <!-- br:models.free -->6<!-- /br:models.free --> models work free out of the box.** Install, run, and pin `free/mistral-nemotron` (or any of the <!-- br:models.free -->6<!-- /br:models.free -->) — no crypto, no signup, no balance required. Add USDC later when you want paid models.
+> **No wallet? <!-- br:models.free -->5<!-- /br:models.free --> models work free out of the box.** Install, run, and pin `free/mistral-nemotron` (or any of the <!-- br:models.free -->5<!-- /br:models.free -->) — no crypto, no signup, no balance required. Add USDC later when you want paid models.
 ### Option A — OpenClaw Agent
@@ -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 -->71<!-- /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 -->70<!-- /br:models.chatVisible --> models, same x402 USDC settlement on Base & Solana.
 No OpenClaw required. ClawRouter runs as a local proxy on port 8402.
@@ -118,7 +118,7 @@ npx @blockrun/clawrouter
 ```
 **2. Fund your wallet** — optional, skip for free tier
-Your wallet address is printed on first run. For paid models, send a few USDC on Base or Solana — $5 covers thousands of requests. To stay at $0, pin any of the <!-- br:models.free -->6<!-- /br:models.free --> free models (e.g. `free/mistral-nemotron`) or use `/model free` inside OpenClaw.
+Your wallet address is printed on first run. For paid models, send a few USDC on Base or Solana — $5 covers thousands of requests. To stay at $0, pin any of the <!-- br:models.free -->5<!-- /br:models.free --> free models (e.g. `free/mistral-nemotron`) or use `/model free` inside OpenClaw.
 **3. Point your client at `http://localhost:8402`**
@@ -393,7 +393,7 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 ## Models & Pricing
-<!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> models across 9 providers, one wallet. **<!-- br:models.free -->6<!-- /br:models.free --> models are $0 — paid models start at fractions of a cent.**
+<!-- 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.**
 > **💡 "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.
@@ -401,31 +401,35 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 | Model                                       | Input $/M | Output $/M | ~$/request | Context | Features                                     |
 | ------------------------------------------- | --------: | ---------: | ---------: | ------- | -------------------------------------------- |
-| free/deepseek-v4-flash                      |  **FREE** |   **FREE** |     **$0** | 1M      | reasoning + coding, huge context             |
 | 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                        |
 | free/step-3.7-flash                         |  **FREE** |   **FREE** |     **$0** | 131K    | reasoning                                    |
 | free/nemotron-nano-9b-v2                    |  **FREE** |   **FREE** |     **$0** | 131K    | fast lightweight generalist                  |
 | free/nemotron-nano-12b-v2-vl                |  **FREE** |   **FREE** |     **$0** | 131K    | vision (text + image)                        |
+| qwen/qwen3.7-flash                          |     $0.03 |      $0.13 |    $0.0001 | 1M      | reasoning, tools (fastest Qwen tier)         |
 | openai/gpt-5-nano                           |     $0.05 |      $0.40 |    $0.0002 | 128K    | tools                                        |
+| openai/gpt-5.6-luna-pro                     |     $0.10 |      $0.60 |    $0.0004 | 1M      | reasoning, vision, agentic, tools            |
 | openai/gpt-4.1-nano                         |     $0.10 |      $0.40 |    $0.0003 | 128K    | tools                                        |
 | google/gemini-2.5-flash-lite                |     $0.10 |      $0.40 |    $0.0003 | 1M      | tools                                        |
 | openai/gpt-4o-mini                          |     $0.15 |      $0.60 |    $0.0004 | 128K    | tools                                        |
+| tencent/hy3                                 |    $0.132 |     $0.528 |    $0.0003 | 262K    | reasoning (Tencent Hy3)                      |
 | xai/grok-4-fast                             |     $0.20 |      $0.50 |    $0.0004 | 131K    | tools                                        |
+| openai/gpt-5.6-luna                         |     $0.20 |      $1.20 |    $0.0007 | 1M      | vision, agentic, tools                       |
 | xai/grok-4-fast-reasoning                   |     $0.20 |      $0.50 |    $0.0004 | 131K    | reasoning, tools                             |
 | xai/grok-4-1-fast                           |     $0.20 |      $0.50 |    $0.0004 | 131K    | tools                                        |
 | openai/gpt-5-mini                           |     $0.25 |      $2.00 |    $0.0011 | 200K    | tools                                        |
-| deepseek/deepseek-chat                      |     $0.20 |      $0.40 |    $0.0003 | 1M      | tools (V4 Flash chat)                        |
-| deepseek/deepseek-reasoner                  |     $0.20 |      $0.40 |    $0.0003 | 1M      | reasoning, tools (V4 Flash thinking)         |
+| qwen/qwen3.7-plus                           |     $0.32 |      $1.28 |    $0.0008 | 1M      | reasoning, agentic, tools (balanced Qwen)    |
+| deepseek/deepseek-chat                      |     $0.14 |      $0.28 |    $0.0002 | 1M      | tools (V4 Flash chat)                        |
+| deepseek/deepseek-reasoner                  |     $0.14 |      $0.28 |    $0.0002 | 1M      | reasoning, tools (V4 Flash thinking)         |
 | deepseek/deepseek-v4-pro                    |    $0.435 |      $0.87 |    $0.0007 | 1M      | reasoning, agentic, tools (V4 flagship)      |
-| zai/glm-5                                   |     $0.60 |      $1.92 |    $0.0013 | 200K    | tools                                        |
+| xiaomi/mimo-v2.5-pro                        |    $0.435 |      $0.87 |    $0.0007 | 1M      | reasoning (Xiaomi MiMo-V2.5 Pro)             |
 | zai/glm-5-turbo                             |     $1.20 |      $4.00 |    $0.0026 | 200K    | tools                                        |
 | minimax/minimax-m3                          |     $0.30 |      $1.20 |    $0.0008 | 1M      | reasoning, agentic, tools                    |
 | minimax/minimax-m2.7                        |     $0.30 |      $1.20 |    $0.0008 | 205K    | reasoning, agentic, tools                    |
 | minimax/minimax-m2.5                        |     $0.30 |      $1.20 |    $0.0008 | 205K    | reasoning, agentic, tools                    |
 | google/gemini-2.5-flash                     |     $0.30 |      $2.50 |    $0.0014 | 1M      | vision, tools                                |
+| google/gemini-3.5-flash-lite                |     $0.30 |      $2.50 |    $0.0014 | 1M      | reasoning, tools (thinking built-in)         |
 | openai/gpt-4.1-mini                         |     $0.40 |      $1.60 |    $0.0010 | 128K    | tools                                        |
-| google/gemini-3.5-flash                     |     $0.50 |      $3.00 |    $0.0018 | 1M      | reasoning, vision, tools (thinking built-in) |
 | google/gemini-3-flash-preview               |     $0.50 |      $3.00 |    $0.0018 | 1M      | vision                                       |
 | moonshot/kimi-k2.5                          |     $0.60 |      $3.00 |    $0.0018 | 262K    | reasoning, vision, agentic, tools            |
 | moonshot/kimi-k2.7                          |     $0.95 |      $4.00 |    $0.0025 | 262K    | reasoning, vision, agentic, tools            |
@@ -436,7 +440,8 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 | Model                       | Input $/M | Output $/M | ~$/request | Context | Features                                  |
 | --------------------------- | --------: | ---------: | ---------: | ------- | ----------------------------------------- |
 | anthropic/claude-haiku-4.5  |     $1.00 |      $5.00 |    $0.0030 | 200K    | vision, agentic, tools                    |
-| openai/gpt-5.6-luna         |     $1.00 |      $6.00 |    $0.0035 | 1M      | vision, agentic, tools                    |
+| zai/glm-5                   |     $1.00 |      $3.20 |    $0.0021 | 200K    | reasoning, tools                          |
+| openai/gpt-5.6-terra-pro    |     $1.00 |      $6.00 |    $0.0035 | 1M      | reasoning, vision, agentic, tools         |
 | openai/o1-mini              |     $1.10 |      $4.40 |    $0.0028 | 128K    | reasoning, tools                          |
 | openai/o3-mini              |     $1.10 |      $4.40 |    $0.0028 | 128K    | reasoning, tools                          |
 | openai/o4-mini              |     $1.10 |      $4.40 |    $0.0028 | 128K    | reasoning, tools                          |
@@ -445,6 +450,8 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 | zai/glm-5.1                 |     $1.40 |      $4.40 |    $0.0029 | 200K    | reasoning, tools (promo ended 2026-06-05) |
 | qwen/qwen3.7-max            |    $1.475 |     $4.425 |    $0.0030 | 1M      | reasoning, agentic, tools (Qwen flagship) |
 | xai/grok-4.3                |     $1.50 |      $4.00 |    $0.0028 | 1M      | reasoning, vision, agentic, tools         |
+| google/gemini-3.6-flash     |     $1.50 |      $7.50 |    $0.0045 | 1M      | reasoning, vision, tools (newest Flash)   |
+| google/gemini-3.5-flash     |     $1.50 |      $9.00 |    $0.0053 | 1M      | reasoning, vision, tools (thinking)       |
 | xai/grok-4.5                |     $2.50 |      $9.00 |    $0.0058 | 500K    | reasoning, vision, agentic, tools         |
 | xai/grok-build-0.1          |     $1.50 |      $3.00 |    $0.0023 | 256K    | agentic coding, tools                     |
 | openai/gpt-5.2              |     $1.75 |     $14.00 |    $0.0079 | 400K    | reasoning, vision, agentic, tools         |
@@ -457,7 +464,7 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 | xai/grok-2-vision           |     $2.00 |     $10.00 |    $0.0060 | 131K    | vision, tools                             |
 | openai/gpt-4o               |     $2.50 |     $10.00 |    $0.0063 | 128K    | vision, agentic, tools                    |
 | openai/gpt-5.4              |     $2.50 |     $15.00 |    $0.0088 | 400K    | reasoning, vision, agentic, tools         |
-| openai/gpt-5.6-terra        |     $2.50 |     $15.00 |    $0.0088 | 1M      | reasoning, vision, agentic, tools         |
+| openai/gpt-5.6-terra        |     $2.00 |     $12.00 |    $0.0070 | 1M      | reasoning, vision, agentic, tools         |
 ### Premium Models ($0.01+/request)
@@ -468,6 +475,7 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 | anthropic/claude-opus-5     |     $5.00 |     $25.00 |    $0.0150 | 1M      | reasoning, vision, agentic, tools |
 | anthropic/claude-opus-4.8   |     $5.00 |     $25.00 |    $0.0150 | 1M      | reasoning, vision, agentic, tools |
 | openai/gpt-5.6-sol          |     $5.00 |     $30.00 |    $0.0175 | 1M      | reasoning, vision, agentic, tools |
+| openai/gpt-5.6-sol-pro      |     $5.00 |     $30.00 |    $0.0175 | 1M      | reasoning, vision, agentic, tools |
 | openai/gpt-5.5              |     $5.00 |     $30.00 |    $0.0175 | 1M      | reasoning, vision, agentic, tools |
 | openai/chat-latest          |     $5.00 |     $30.00 |    $0.0175 | 128K    | vision, tools                     |
 | openai/o1                   |    $15.00 |     $60.00 |    $0.0375 | 200K    | reasoning, tools                  |
@@ -475,7 +483,7 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 | openai/gpt-5.4-pro          |    $30.00 |    $180.00 |    $0.1050 | 400K    | reasoning, tools                  |
 | openai/gpt-5.5-pro          |    $30.00 |    $180.00 |    $0.1050 | 1M      | reasoning, vision, 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 v4-flash` for 1M-context reasoning, `/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 step-flash` for reasoning, `/model mistral-nemotron` for instruction following).
 > **Best value:** `gpt-5-nano` and `gemini-2.5-flash-lite` deliver strong results at ~$0.0003/request.
 ---
@@ -552,7 +560,7 @@ For basic usage, no configuration needed. For advanced options:
 Block specific models from being routed to. Useful if a model doesn't follow your agent instructions or you want to control costs.
 ```bash
-/exclude add free/deepseek-v4-flash # Block a free model (e.g. too slow for you)
+/exclude add free/step-3.7-flash   # Block a free model (e.g. not for your workload)
 /exclude add grok-4                # Aliases work — blocks all grok-4 variants
 /exclude add gpt-5.4               # Skip expensive models
 /exclude                           # Show current exclusions
@@ -646,7 +654,7 @@ npm test
 **The LLM router built for autonomous agents**
-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.
+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.
 `curl -fsSL https://blockrun.ai/ClawRouter-update | bash`
@@ -657,7 +665,7 @@ You're here. <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible --> mod
 **BlockRun for Claude Code**
-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.
+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.
 `curl -fsSL https://blockrun.ai/brcc-install | bash`
@@ -670,7 +678,7 @@ Run Claude Code with <!-- br:models.chatVisible -->71<!-- /br:models.chatVisible
 **ClawRouter for NousResearch Hermes**
-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.
+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.
 `pip install hermes-plugin-clawrouter`
@@ -734,7 +742,7 @@ 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 (`deepseek-v4-flash`, `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 (`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 CHANGED Viewed

@@ -36252,10 +36252,9 @@ ${value.slice(-(scanLimit - prefixLength))}`;
           fallback: [
             "free/gpt-oss-20b",
             // FREE — smaller, faster
-            "free/deepseek-v4-flash",
-            // FREE — 1M ctx; slow (~10 tok/s, 07-28 probe) but completes
-            // seed-oss-36b sat here as the free coder until it EOL'd 2026-08-03 (HTTP 410).
-            // gpt-oss-120b/20b already head this chain, so the rung is dropped, not retargeted.
+            // 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.
             "google/gemini-3.1-flash-lite",
             // $0.25/$1.50 — newest flash-lite
             "openai/gpt-5.4-nano",
@@ -36564,7 +36563,6 @@ var init_top_models = __esm({
       "deepseek/deepseek-v4-pro",
       "deepseek/deepseek-chat",
       "deepseek/deepseek-reasoner",
-      "free/deepseek-v4-flash",
       "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       "free/mistral-nemotron",
       "free/step-3.7-flash",
@@ -36764,6 +36762,14 @@ var init_models = __esm({
       "gpt-5.6-sol": "openai/gpt-5.6-sol",
       "gpt-5.6-terra": "openai/gpt-5.6-terra",
       "gpt-5.6-luna": "openai/gpt-5.6-luna",
+      // Pro reasoning tiers (2026-08-03). Explicit pins only — the generic
+      // shorthands above stay on standard Terra.
+      "gpt-5.6-sol-pro": "openai/gpt-5.6-sol-pro",
+      "gpt-5.6-terra-pro": "openai/gpt-5.6-terra-pro",
+      "gpt-5.6-luna-pro": "openai/gpt-5.6-luna-pro",
+      "sol-pro": "openai/gpt-5.6-sol-pro",
+      "terra-pro": "openai/gpt-5.6-terra-pro",
+      "luna-pro": "openai/gpt-5.6-luna-pro",
       "gpt-5.5": "openai/gpt-5.5",
       "gpt-5.5-pro": "openai/gpt-5.5-pro",
       // ChatGPT Instant. `chat-latest` is a rolling upstream id — pinning it means
@@ -36815,6 +36821,20 @@ var init_models = __esm({
       "qwen3.7-max": "qwen/qwen3.7-max",
       "qwen-3.7-max": "qwen/qwen3.7-max",
       "qwen3-7-max": "qwen/qwen3.7-max",
+      // Plus/Flash tiers (2026-08-03) — explicit pins, same rule as Max.
+      "qwen3.7-plus": "qwen/qwen3.7-plus",
+      "qwen-3.7-plus": "qwen/qwen3.7-plus",
+      "qwen3.7-flash": "qwen/qwen3.7-flash",
+      "qwen-3.7-flash": "qwen/qwen3.7-flash",
+      // Tencent + Xiaomi (2026-07-25) — each maker has exactly one model, so the
+      // bare maker names are safe to bind.
+      hy3: "tencent/hy3",
+      tencent: "tencent/hy3",
+      hunyuan: "tencent/hy3",
+      mimo: "xiaomi/mimo-v2.5-pro",
+      "mimo-v2.5-pro": "xiaomi/mimo-v2.5-pro",
+      "mimo-v2.5": "xiaomi/mimo-v2.5-pro",
+      xiaomi: "xiaomi/mimo-v2.5-pro",
       // Google
       // gemini-3-pro-preview delisted by Google 2026-06-06 — mirror the gateway
       // redirect to its successor so pinned callers land on 3.1-pro, not an error.
@@ -36830,7 +36850,10 @@ var init_models = __esm({
       flash: "google/gemini-2.5-flash",
       "gemini-3.1-pro-preview": "google/gemini-3.1-pro",
       "google/gemini-3.1-pro-preview": "google/gemini-3.1-pro",
+      "gemini-3.6-flash": "google/gemini-3.6-flash",
+      "gemini-3.6": "google/gemini-3.6-flash",
       "gemini-3.5-flash": "google/gemini-3.5-flash",
+      "gemini-3.5-flash-lite": "google/gemini-3.5-flash-lite",
       "gemini-3.1-flash-lite": "google/gemini-3.1-flash-lite",
       "gemini-2.5-flash-lite": "google/gemini-2.5-flash-lite",
       // xAI — grok-4.3 is the public flagship since 2026-06-04 (grok-3 and the
@@ -36866,12 +36889,17 @@ 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",
-      "free/deepseek-v3.2": "free/deepseek-v4-flash",
-      "nvidia/deepseek-v4-pro": "free/deepseek-v4-flash",
-      "free/deepseek-v4-pro": "free/deepseek-v4-flash",
+      // deepseek free family: v4-flash EOL'd 2026-08-12 (HTTP 410 from NVIDIA on both
+      // probe passes; prod gate fired [ALERT][free-model-dead] kind=gone twice that
+      // morning). The whole nvidia/deepseek-* family is now dead upstream — blockrun
+      // hid flash and retargeted v3.2/v4-pro (whose redirects chained through flash)
+      // straight to gpt-oss-120b. Ids naming v4-flash itself keep the real id (the
+      // gateway redirects them); the v3.2/v4-pro ids follow blockrun's retarget
+      // rather than chaining through a second dead model.
+      "nvidia/deepseek-v3.2": "free/gpt-oss-120b",
+      "free/deepseek-v3.2": "free/gpt-oss-120b",
+      "nvidia/deepseek-v4-pro": "free/gpt-oss-120b",
+      "free/deepseek-v4-pro": "free/gpt-oss-120b",
       "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). Its server-side redirect used
@@ -36913,13 +36941,16 @@ var init_models = __esm({
       "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 (v4-flash recovered 2026-07-17 — live again)
-      "deepseek-free": "free/deepseek-v4-flash",
-      "deepseek-v4-pro": "free/deepseek-v4-flash",
-      // free shorthand → flash (pro still hung)
+      // Free model shorthand aliases. v4-flash EOL'd 2026-08-12 — no free DeepSeek
+      // is left anywhere, so the generic "a free deepseek" shorthand follows the
+      // gateway's retarget (blockrun's /free-deepseek page points at gpt-oss-120b
+      // too). Shorthands naming v4-flash itself stay on the real id — the gateway
+      // redirects them, same treatment as seed-oss/mistral-large pins.
+      "deepseek-free": "free/gpt-oss-120b",
+      "deepseek-v4-pro": "free/gpt-oss-120b",
+      // free shorthand; pro dead upstream (410)
       "deepseek-v4-flash": "free/deepseek-v4-flash",
-      "v4-pro": "free/deepseek-v4-flash",
-      // V4 Pro NVIDIA hung → flash
+      "v4-pro": "free/gpt-oss-120b",
       "v4-flash": "free/deepseek-v4-flash",
       "mistral-free": "free/mistral-nemotron",
       // mistral-large-3-675b EOL'd 2026-07-28 → last live free Mistral (blockrun demoted its /free-mistral primary the same way)
@@ -36999,6 +37030,10 @@ var init_models = __esm({
       banana: "google/nano-banana",
       "banana-pro": "google/nano-banana-pro",
       "nano-banana-pro": "google/nano-banana-pro",
+      // Nano Banana 2 (Gemini 3.1 Flash imagegen, 2026-08-03). Explicit pins —
+      // bare `nano-banana`/`banana` stay on the original.
+      "nano-banana-2": "google/nano-banana-2",
+      "banana-2": "google/nano-banana-2",
       seedream: "bytedance/seedream-5-pro",
       "grok-imagine": "xai/grok-imagine-image",
       "grok-imagine-pro": "xai/grok-imagine-image-pro",
@@ -37015,7 +37050,12 @@ var init_models = __esm({
       "seedance-2-fast": "bytedance/seedance-2.0-fast",
       "seedance-2": "bytedance/seedance-2.0",
       "seedance-2.5": "bytedance/seedance-2.5",
-      "seedance-2-5": "bytedance/seedance-2.5"
+      "seedance-2-5": "bytedance/seedance-2.5",
+      // Seedance 2.0 Mini (2026-08-12): 720p + synced audio at half the flagship
+      // rate. Note it is NOT cheaper than 1.5-pro, so bare `seedance` stays put.
+      "seedance-2-mini": "bytedance/seedance-2.0-mini",
+      "seedance-2.0-mini": "bytedance/seedance-2.0-mini",
+      "seedance-mini": "bytedance/seedance-2.0-mini"
     };
     BLOCKRUN_MODELS = [
       // Smart routing meta-models — proxy replaces with actual model
@@ -37123,11 +37163,12 @@ var init_models = __esm({
         toolCalling: true
       },
       {
+        // Terra/Luna repriced 2026-07-30 (OpenAI price cut, blockrun #326).
         id: "openai/gpt-5.6-terra",
         name: "GPT-5.6 Terra",
         version: "5.6",
-        inputPrice: 2.5,
-        outputPrice: 15,
+        inputPrice: 2,
+        outputPrice: 12,
         contextWindow: 105e4,
         maxOutput: 128e3,
         reasoning: true,
@@ -37139,10 +37180,52 @@ var init_models = __esm({
         id: "openai/gpt-5.6-luna",
         name: "GPT-5.6 Luna",
         version: "5.6",
+        inputPrice: 0.2,
+        outputPrice: 1.2,
+        contextWindow: 105e4,
+        maxOutput: 128e3,
+        vision: true,
+        agentic: true,
+        toolCalling: true
+      },
+      // GPT-5.6 Pro tiers (blockrun #329, 2026-08-03): each base tier with pro
+      // reasoning mode. Terra Pro lands at half the standard Terra rate; Luna Pro
+      // is the budget deep-reasoning tier.
+      {
+        id: "openai/gpt-5.6-sol-pro",
+        name: "GPT-5.6 Sol Pro",
+        version: "5.6",
+        inputPrice: 5,
+        outputPrice: 30,
+        contextWindow: 105e4,
+        maxOutput: 128e3,
+        reasoning: true,
+        vision: true,
+        agentic: true,
+        toolCalling: true
+      },
+      {
+        id: "openai/gpt-5.6-terra-pro",
+        name: "GPT-5.6 Terra Pro",
+        version: "5.6",
         inputPrice: 1,
         outputPrice: 6,
         contextWindow: 105e4,
         maxOutput: 128e3,
+        reasoning: true,
+        vision: true,
+        agentic: true,
+        toolCalling: true
+      },
+      {
+        id: "openai/gpt-5.6-luna-pro",
+        name: "GPT-5.6 Luna Pro",
+        version: "5.6",
+        inputPrice: 0.1,
+        outputPrice: 0.6,
+        contextWindow: 105e4,
+        maxOutput: 128e3,
+        reasoning: true,
         vision: true,
         agentic: true,
         toolCalling: true
@@ -37546,19 +37629,45 @@ var init_models = __esm({
         toolCalling: true
       },
       {
-        // Latest-generation Flash with built-in thinking mode (backend
-        // 2026-05-19) — frontier-class quality at Flash pricing.
+        // Newest-generation Flash with built-in thinking mode (blockrun #329,
+        // 2026-08-03). 17% cheaper output than 3.5 Flash.
+        id: "google/gemini-3.6-flash",
+        name: "Gemini 3.6 Flash",
+        version: "3.6",
+        inputPrice: 1.5,
+        outputPrice: 7.5,
+        contextWindow: 1048576,
+        maxOutput: 65536,
+        reasoning: true,
+        vision: true,
+        toolCalling: true
+      },
+      {
+        // Repriced 0.5/3.0 → 1.5/9.0 (blockrun #304: it was billed at 1/3 of
+        // Google's real rate).
         id: "google/gemini-3.5-flash",
         name: "Gemini 3.5 Flash",
         version: "3.5",
-        inputPrice: 0.5,
-        outputPrice: 3,
+        inputPrice: 1.5,
+        outputPrice: 9,
         contextWindow: 1048576,
         maxOutput: 65536,
         reasoning: true,
         vision: true,
         toolCalling: true
       },
+      {
+        // Ultra-fast lightweight tier with thinking mode (blockrun #329).
+        id: "google/gemini-3.5-flash-lite",
+        name: "Gemini 3.5 Flash Lite",
+        version: "3.5",
+        inputPrice: 0.3,
+        outputPrice: 2.5,
+        contextWindow: 1048576,
+        maxOutput: 65536,
+        reasoning: true,
+        toolCalling: true
+      },
       {
         id: "google/gemini-3-flash-preview",
         name: "Gemini 3 Flash Preview",
@@ -37615,12 +37724,14 @@ var init_models = __esm({
       },
       // DeepSeek — V4 family (2026-04-24). The legacy deepseek-chat/reasoner
       // aliases are served upstream as V4 Flash non-thinking / thinking modes.
+      // Repriced 0.20/0.40 → 0.14/0.28 (blockrun #354: DeepSeek's published
+      // deepseek-v4-flash rate; the old numbers were 1.43x the real rate).
       {
         id: "deepseek/deepseek-chat",
         name: "DeepSeek V4 Flash Chat",
         version: "4-flash",
-        inputPrice: 0.2,
-        outputPrice: 0.4,
+        inputPrice: 0.14,
+        outputPrice: 0.28,
         contextWindow: 1e6,
         maxOutput: 8192,
         toolCalling: true
@@ -37629,8 +37740,8 @@ var init_models = __esm({
         id: "deepseek/deepseek-reasoner",
         name: "DeepSeek V4 Flash Reasoner",
         version: "4-flash",
-        inputPrice: 0.2,
-        outputPrice: 0.4,
+        inputPrice: 0.14,
+        outputPrice: 0.28,
         contextWindow: 1e6,
         maxOutput: 8192,
         reasoning: true,
@@ -37709,6 +37820,32 @@ var init_models = __esm({
         agentic: true,
         toolCalling: true
       },
+      // Qwen3.7 Plus/Flash (blockrun #329, 2026-08-03): the balanced and
+      // latency tiers under Max. Plus genuinely caps output at 131072 while
+      // Flash and Max cap at 65536 (endpoint-probed upstream).
+      {
+        id: "qwen/qwen3.7-plus",
+        name: "Qwen3.7 Plus",
+        version: "3.7-plus",
+        inputPrice: 0.32,
+        outputPrice: 1.28,
+        contextWindow: 1e6,
+        maxOutput: 131072,
+        reasoning: true,
+        agentic: true,
+        toolCalling: true
+      },
+      {
+        id: "qwen/qwen3.7-flash",
+        name: "Qwen3.7 Flash",
+        version: "3.7-flash",
+        inputPrice: 0.03,
+        outputPrice: 0.13,
+        contextWindow: 1e6,
+        maxOutput: 65536,
+        reasoning: true,
+        toolCalling: true
+      },
       // Kimi K2.6 — superseded by K2.7 (2026-06-13), hidden on BlockRun but still routable.
       {
         id: "moonshot/kimi-k2.6",
@@ -37920,6 +38057,34 @@ var init_models = __esm({
         agentic: true,
         toolCalling: true
       },
+      // Tencent + Xiaomi (blockrun 2026-07-25): the two largest real demand gaps
+      // in the catalog — Hy3 held the #1 usage slot on the biggest public
+      // aggregator for 19 days; MiMo ran ~22% weekly share in April. Both are
+      // reasoning models resold via blockrun's OpenRouter pool. toolCalling
+      // LIVE-VERIFIED 2026-08-12: both returned a structured tool_calls array
+      // (name + valid JSON args, finish_reason "tool_calls") through the gateway.
+      {
+        id: "tencent/hy3",
+        name: "Tencent Hy3",
+        version: "hy3",
+        inputPrice: 0.132,
+        outputPrice: 0.528,
+        contextWindow: 262144,
+        maxOutput: 128e3,
+        reasoning: true,
+        toolCalling: true
+      },
+      {
+        id: "xiaomi/mimo-v2.5-pro",
+        name: "Xiaomi MiMo-V2.5 Pro",
+        version: "v2.5-pro",
+        inputPrice: 0.435,
+        outputPrice: 0.87,
+        contextWindow: 1048576,
+        maxOutput: 131072,
+        reasoning: true,
+        toolCalling: true
+      },
       // MiniMax
       {
         id: "minimax/minimax-m3",
@@ -37993,11 +38158,13 @@ var init_models = __esm({
         maxOutput: 16384
       },
       {
-        // 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.
+        // V4 Flash: 284B / 13B active MoE, 1M context. EOL'd 2026-08-12 — NVIDIA
+        // published 410 Gone ("has reached its end of life") on both probe passes
+        // and blockrun's prod gate fired [ALERT][free-model-dead] kind=gone twice
+        // that morning. The whole nvidia/deepseek-* family is dead upstream; there
+        // is no free DeepSeek left anywhere. Blockrun hid it and redirects calls to
+        // gpt-oss-120b. Entry kept so explicit pins stay routable; off the picker,
+        // the FREE_MODELS cascade, and the router fallback chains.
         id: "free/deepseek-v4-flash",
         name: "[Free] DeepSeek V4 Flash",
         version: "v4-flash",
@@ -38081,7 +38248,8 @@ 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. 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).
+      // glm-4.7 stay dead (server-redirected); deepseek-v4-flash recovered then
+      // EOL'd for good 2026-08-12 (see above).
       {
         // Qwen3-Next 80B (A3B active MoE): 262K context. DIED in the 2026-07-17
         // re-probe (">60s / DEGRADED") — hidden upstream, gateway redirects pinned
@@ -38186,11 +38354,12 @@ var init_models = __esm({
       },
       {
         // Flat-rate launch promo ended 2026-06-06 — backend bills per-token now.
+        // Repriced 0.60/1.92 → 1.00/3.20 (blockrun #354 correction).
         id: "zai/glm-5",
         name: "GLM-5",
         version: "5",
-        inputPrice: 0.6,
-        outputPrice: 1.92,
+        inputPrice: 1,
+        outputPrice: 3.2,
         contextWindow: 2e5,
         maxOutput: 128e3,
         reasoning: true,
@@ -92587,8 +92756,6 @@ var init_proxy = __esm({
     FREE_MODELS = /* @__PURE__ */ new Set([
       "free/gpt-oss-120b",
       "free/gpt-oss-20b",
-      "free/deepseek-v4-flash",
-      // 1M ctx; slow (~10 tok/s, 07-28 probe) but completes
       "free/mistral-nemotron",
       // strong instruction following
       "free/step-3.7-flash",
@@ -92685,6 +92852,8 @@ var init_proxy = __esm({
         sizes: { "1024x1024": 0.045, "2048x1024": 0.045, "2048x2048": 0.09 }
       },
       "google/nano-banana": { default: 0.05 },
+      // Nano Banana 2 (Gemini 3.1 Flash imagegen, blockrun #329): $0.09/image at 1K.
+      "google/nano-banana-2": { default: 0.09, sizes: { "1024x1024": 0.09 } },
       "google/nano-banana-pro": {
         default: 0.1,
         sizes: { "1024x1024": 0.1, "2048x2048": 0.1, "4096x4096": 0.15 }
@@ -92718,6 +92887,13 @@ var init_proxy = __esm({
         pricePerSecond: 0.227,
         defaultDurationSeconds: 5
       },
+      // Seedance 2.0 Mini (blockrun #366/#368, 2026-08-12): 720p + synced audio at
+      // half the flagship rate, 480p/720p only, 4–15s. blockrun signs the 3dp-floored
+      // per-second value (0.079, not the raw 0.0797) — mirror the signed number.
+      "bytedance/seedance-2.0-mini": {
+        pricePerSecond: 0.079,
+        defaultDurationSeconds: 5
+      },
       // Seedance 2.5: 720p with synced audio, up to 30s. Not a replacement for 2.0
       // Pro — that is still the one for 1080p/4K. No OpenRouter failover exists for
       // 2.5, so a token360 outage surfaces as an error instead of quietly rendering
@@ -226066,6 +226242,7 @@ function buildVideoGenerationProvider() {
       "bytedance/seedance-1.5-pro",
       "bytedance/seedance-2.0-fast",
       "bytedance/seedance-2.0",
+      "bytedance/seedance-2.0-mini",
       "bytedance/seedance-2.5"
     ],
     capabilities: {
@@ -226567,7 +226744,7 @@ var init_index = __esm({
             const parsed = parseGenArgs(ctx.args ?? "");
             if (!parsed.prompt) {
               return {
-                text: "Usage: `/cr-imagegen <prompt> [--model=<alias>] [--size=1024x1024] [--n=1]`\n\nAliases: `nano-banana` (default), `banana-pro`, `dalle`, `gpt-image`, `flux`, `grok-imagine`, `grok-imagine-pro`, `cogview`."
+                text: "Usage: `/cr-imagegen <prompt> [--model=<alias>] [--size=1024x1024] [--n=1]`\n\nAliases: `nano-banana` (default), `banana-2` (Gemini 3.1 Flash quality), `banana-pro`, `dalle`, `gpt-image`, `flux`, `grok-imagine`, `grok-imagine-pro`, `cogview`."
               };
             }
             const model = resolveModelAlias(parsed.model ?? "nano-banana");
@@ -226619,7 +226796,7 @@ ${errText}`
             const parsed = parseGenArgs(ctx.args ?? "");
             if (!parsed.prompt) {
               return {
-                text: "Usage: `/videogen <prompt> [--model=<alias>] [--duration=5|8|10]`\n\nAliases: `seedance` (1.5-pro, default \u2014 cheapest), `seedance-2-fast`, `seedance-2`, `seedance-2.5` (720p + synced audio, long-form), `grok-video`.\n\n\u23F1\uFE0F  Generation takes 60\u2013180 seconds. Payment settles only on success."
+                text: "Usage: `/videogen <prompt> [--model=<alias>] [--duration=5|8|10]`\n\nAliases: `seedance` (1.5-pro, default \u2014 cheapest), `seedance-2-fast`, `seedance-2`, `seedance-2-mini` (720p + audio, half the flagship rate), `seedance-2.5` (720p + synced audio, long-form), `grok-video`.\n\n\u23F1\uFE0F  Generation takes 60\u2013180 seconds. Payment settles only on success."
               };
             }
             const model = resolveModelAlias(parsed.model ?? "seedance");

package/dist/index.js CHANGED Viewed

@@ -92,7 +92,6 @@ var init_top_models = __esm({
       "deepseek/deepseek-v4-pro",
       "deepseek/deepseek-chat",
       "deepseek/deepseek-reasoner",
-      "free/deepseek-v4-flash",
       "free/nemotron-3-nano-omni-30b-a3b-reasoning",
       "free/mistral-nemotron",
       "free/step-3.7-flash",
@@ -292,6 +291,14 @@ var init_models = __esm({
       "gpt-5.6-sol": "openai/gpt-5.6-sol",
       "gpt-5.6-terra": "openai/gpt-5.6-terra",
       "gpt-5.6-luna": "openai/gpt-5.6-luna",
+      // Pro reasoning tiers (2026-08-03). Explicit pins only — the generic
+      // shorthands above stay on standard Terra.
+      "gpt-5.6-sol-pro": "openai/gpt-5.6-sol-pro",
+      "gpt-5.6-terra-pro": "openai/gpt-5.6-terra-pro",
+      "gpt-5.6-luna-pro": "openai/gpt-5.6-luna-pro",
+      "sol-pro": "openai/gpt-5.6-sol-pro",
+      "terra-pro": "openai/gpt-5.6-terra-pro",
+      "luna-pro": "openai/gpt-5.6-luna-pro",
       "gpt-5.5": "openai/gpt-5.5",
       "gpt-5.5-pro": "openai/gpt-5.5-pro",
       // ChatGPT Instant. `chat-latest` is a rolling upstream id — pinning it means
@@ -343,6 +350,20 @@ var init_models = __esm({
       "qwen3.7-max": "qwen/qwen3.7-max",
       "qwen-3.7-max": "qwen/qwen3.7-max",
       "qwen3-7-max": "qwen/qwen3.7-max",
+      // Plus/Flash tiers (2026-08-03) — explicit pins, same rule as Max.
+      "qwen3.7-plus": "qwen/qwen3.7-plus",
+      "qwen-3.7-plus": "qwen/qwen3.7-plus",
+      "qwen3.7-flash": "qwen/qwen3.7-flash",
+      "qwen-3.7-flash": "qwen/qwen3.7-flash",
+      // Tencent + Xiaomi (2026-07-25) — each maker has exactly one model, so the
+      // bare maker names are safe to bind.
+      hy3: "tencent/hy3",
+      tencent: "tencent/hy3",
+      hunyuan: "tencent/hy3",
+      mimo: "xiaomi/mimo-v2.5-pro",
+      "mimo-v2.5-pro": "xiaomi/mimo-v2.5-pro",
+      "mimo-v2.5": "xiaomi/mimo-v2.5-pro",
+      xiaomi: "xiaomi/mimo-v2.5-pro",
       // Google
       // gemini-3-pro-preview delisted by Google 2026-06-06 — mirror the gateway
       // redirect to its successor so pinned callers land on 3.1-pro, not an error.
@@ -358,7 +379,10 @@ var init_models = __esm({
       flash: "google/gemini-2.5-flash",
       "gemini-3.1-pro-preview": "google/gemini-3.1-pro",
       "google/gemini-3.1-pro-preview": "google/gemini-3.1-pro",
+      "gemini-3.6-flash": "google/gemini-3.6-flash",
+      "gemini-3.6": "google/gemini-3.6-flash",
       "gemini-3.5-flash": "google/gemini-3.5-flash",
+      "gemini-3.5-flash-lite": "google/gemini-3.5-flash-lite",
       "gemini-3.1-flash-lite": "google/gemini-3.1-flash-lite",
       "gemini-2.5-flash-lite": "google/gemini-2.5-flash-lite",
       // xAI — grok-4.3 is the public flagship since 2026-06-04 (grok-3 and the
@@ -394,12 +418,17 @@ 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",
-      "free/deepseek-v3.2": "free/deepseek-v4-flash",
-      "nvidia/deepseek-v4-pro": "free/deepseek-v4-flash",
-      "free/deepseek-v4-pro": "free/deepseek-v4-flash",
+      // deepseek free family: v4-flash EOL'd 2026-08-12 (HTTP 410 from NVIDIA on both
+      // probe passes; prod gate fired [ALERT][free-model-dead] kind=gone twice that
+      // morning). The whole nvidia/deepseek-* family is now dead upstream — blockrun
+      // hid flash and retargeted v3.2/v4-pro (whose redirects chained through flash)
+      // straight to gpt-oss-120b. Ids naming v4-flash itself keep the real id (the
+      // gateway redirects them); the v3.2/v4-pro ids follow blockrun's retarget
+      // rather than chaining through a second dead model.
+      "nvidia/deepseek-v3.2": "free/gpt-oss-120b",
+      "free/deepseek-v3.2": "free/gpt-oss-120b",
+      "nvidia/deepseek-v4-pro": "free/gpt-oss-120b",
+      "free/deepseek-v4-pro": "free/gpt-oss-120b",
       "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). Its server-side redirect used
@@ -441,13 +470,16 @@ var init_models = __esm({
       "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 (v4-flash recovered 2026-07-17 — live again)
-      "deepseek-free": "free/deepseek-v4-flash",
-      "deepseek-v4-pro": "free/deepseek-v4-flash",
-      // free shorthand → flash (pro still hung)
+      // Free model shorthand aliases. v4-flash EOL'd 2026-08-12 — no free DeepSeek
+      // is left anywhere, so the generic "a free deepseek" shorthand follows the
+      // gateway's retarget (blockrun's /free-deepseek page points at gpt-oss-120b
+      // too). Shorthands naming v4-flash itself stay on the real id — the gateway
+      // redirects them, same treatment as seed-oss/mistral-large pins.
+      "deepseek-free": "free/gpt-oss-120b",
+      "deepseek-v4-pro": "free/gpt-oss-120b",
+      // free shorthand; pro dead upstream (410)
       "deepseek-v4-flash": "free/deepseek-v4-flash",
-      "v4-pro": "free/deepseek-v4-flash",
-      // V4 Pro NVIDIA hung → flash
+      "v4-pro": "free/gpt-oss-120b",
       "v4-flash": "free/deepseek-v4-flash",
       "mistral-free": "free/mistral-nemotron",
       // mistral-large-3-675b EOL'd 2026-07-28 → last live free Mistral (blockrun demoted its /free-mistral primary the same way)
@@ -527,6 +559,10 @@ var init_models = __esm({
       banana: "google/nano-banana",
       "banana-pro": "google/nano-banana-pro",
       "nano-banana-pro": "google/nano-banana-pro",
+      // Nano Banana 2 (Gemini 3.1 Flash imagegen, 2026-08-03). Explicit pins —
+      // bare `nano-banana`/`banana` stay on the original.
+      "nano-banana-2": "google/nano-banana-2",
+      "banana-2": "google/nano-banana-2",
       seedream: "bytedance/seedream-5-pro",
       "grok-imagine": "xai/grok-imagine-image",
       "grok-imagine-pro": "xai/grok-imagine-image-pro",
@@ -543,7 +579,12 @@ var init_models = __esm({
       "seedance-2-fast": "bytedance/seedance-2.0-fast",
       "seedance-2": "bytedance/seedance-2.0",
       "seedance-2.5": "bytedance/seedance-2.5",
-      "seedance-2-5": "bytedance/seedance-2.5"
+      "seedance-2-5": "bytedance/seedance-2.5",
+      // Seedance 2.0 Mini (2026-08-12): 720p + synced audio at half the flagship
+      // rate. Note it is NOT cheaper than 1.5-pro, so bare `seedance` stays put.
+      "seedance-2-mini": "bytedance/seedance-2.0-mini",
+      "seedance-2.0-mini": "bytedance/seedance-2.0-mini",
+      "seedance-mini": "bytedance/seedance-2.0-mini"
     };
     BLOCKRUN_MODELS = [
       // Smart routing meta-models — proxy replaces with actual model
@@ -651,11 +692,12 @@ var init_models = __esm({
         toolCalling: true
       },
       {
+        // Terra/Luna repriced 2026-07-30 (OpenAI price cut, blockrun #326).
         id: "openai/gpt-5.6-terra",
         name: "GPT-5.6 Terra",
         version: "5.6",
-        inputPrice: 2.5,
-        outputPrice: 15,
+        inputPrice: 2,
+        outputPrice: 12,
         contextWindow: 105e4,
         maxOutput: 128e3,
         reasoning: true,
@@ -667,10 +709,52 @@ var init_models = __esm({
         id: "openai/gpt-5.6-luna",
         name: "GPT-5.6 Luna",
         version: "5.6",
+        inputPrice: 0.2,
+        outputPrice: 1.2,
+        contextWindow: 105e4,
+        maxOutput: 128e3,
+        vision: true,
+        agentic: true,
+        toolCalling: true
+      },
+      // GPT-5.6 Pro tiers (blockrun #329, 2026-08-03): each base tier with pro
+      // reasoning mode. Terra Pro lands at half the standard Terra rate; Luna Pro
+      // is the budget deep-reasoning tier.
+      {
+        id: "openai/gpt-5.6-sol-pro",
+        name: "GPT-5.6 Sol Pro",
+        version: "5.6",
+        inputPrice: 5,
+        outputPrice: 30,
+        contextWindow: 105e4,
+        maxOutput: 128e3,
+        reasoning: true,
+        vision: true,
+        agentic: true,
+        toolCalling: true
+      },
+      {
+        id: "openai/gpt-5.6-terra-pro",
+        name: "GPT-5.6 Terra Pro",
+        version: "5.6",
         inputPrice: 1,
         outputPrice: 6,
         contextWindow: 105e4,
         maxOutput: 128e3,
+        reasoning: true,
+        vision: true,
+        agentic: true,
+        toolCalling: true
+      },
+      {
+        id: "openai/gpt-5.6-luna-pro",
+        name: "GPT-5.6 Luna Pro",
+        version: "5.6",
+        inputPrice: 0.1,
+        outputPrice: 0.6,
+        contextWindow: 105e4,
+        maxOutput: 128e3,
+        reasoning: true,
         vision: true,
         agentic: true,
         toolCalling: true
@@ -1074,19 +1158,45 @@ var init_models = __esm({
         toolCalling: true
       },
       {
-        // Latest-generation Flash with built-in thinking mode (backend
-        // 2026-05-19) — frontier-class quality at Flash pricing.
+        // Newest-generation Flash with built-in thinking mode (blockrun #329,
+        // 2026-08-03). 17% cheaper output than 3.5 Flash.
+        id: "google/gemini-3.6-flash",
+        name: "Gemini 3.6 Flash",
+        version: "3.6",
+        inputPrice: 1.5,
+        outputPrice: 7.5,
+        contextWindow: 1048576,
+        maxOutput: 65536,
+        reasoning: true,
+        vision: true,
+        toolCalling: true
+      },
+      {
+        // Repriced 0.5/3.0 → 1.5/9.0 (blockrun #304: it was billed at 1/3 of
+        // Google's real rate).
         id: "google/gemini-3.5-flash",
         name: "Gemini 3.5 Flash",
         version: "3.5",
-        inputPrice: 0.5,
-        outputPrice: 3,
+        inputPrice: 1.5,
+        outputPrice: 9,
         contextWindow: 1048576,
         maxOutput: 65536,
         reasoning: true,
         vision: true,
         toolCalling: true
       },
+      {
+        // Ultra-fast lightweight tier with thinking mode (blockrun #329).
+        id: "google/gemini-3.5-flash-lite",
+        name: "Gemini 3.5 Flash Lite",
+        version: "3.5",
+        inputPrice: 0.3,
+        outputPrice: 2.5,
+        contextWindow: 1048576,
+        maxOutput: 65536,
+        reasoning: true,
+        toolCalling: true
+      },
       {
         id: "google/gemini-3-flash-preview",
         name: "Gemini 3 Flash Preview",
@@ -1143,12 +1253,14 @@ var init_models = __esm({
       },
       // DeepSeek — V4 family (2026-04-24). The legacy deepseek-chat/reasoner
       // aliases are served upstream as V4 Flash non-thinking / thinking modes.
+      // Repriced 0.20/0.40 → 0.14/0.28 (blockrun #354: DeepSeek's published
+      // deepseek-v4-flash rate; the old numbers were 1.43x the real rate).
       {
         id: "deepseek/deepseek-chat",
         name: "DeepSeek V4 Flash Chat",
         version: "4-flash",
-        inputPrice: 0.2,
-        outputPrice: 0.4,
+        inputPrice: 0.14,
+        outputPrice: 0.28,
         contextWindow: 1e6,
         maxOutput: 8192,
         toolCalling: true
@@ -1157,8 +1269,8 @@ var init_models = __esm({
         id: "deepseek/deepseek-reasoner",
         name: "DeepSeek V4 Flash Reasoner",
         version: "4-flash",
-        inputPrice: 0.2,
-        outputPrice: 0.4,
+        inputPrice: 0.14,
+        outputPrice: 0.28,
         contextWindow: 1e6,
         maxOutput: 8192,
         reasoning: true,
@@ -1237,6 +1349,32 @@ var init_models = __esm({
         agentic: true,
         toolCalling: true
       },
+      // Qwen3.7 Plus/Flash (blockrun #329, 2026-08-03): the balanced and
+      // latency tiers under Max. Plus genuinely caps output at 131072 while
+      // Flash and Max cap at 65536 (endpoint-probed upstream).
+      {
+        id: "qwen/qwen3.7-plus",
+        name: "Qwen3.7 Plus",
+        version: "3.7-plus",
+        inputPrice: 0.32,
+        outputPrice: 1.28,
+        contextWindow: 1e6,
+        maxOutput: 131072,
+        reasoning: true,
+        agentic: true,
+        toolCalling: true
+      },
+      {
+        id: "qwen/qwen3.7-flash",
+        name: "Qwen3.7 Flash",
+        version: "3.7-flash",
+        inputPrice: 0.03,
+        outputPrice: 0.13,
+        contextWindow: 1e6,
+        maxOutput: 65536,
+        reasoning: true,
+        toolCalling: true
+      },
       // Kimi K2.6 — superseded by K2.7 (2026-06-13), hidden on BlockRun but still routable.
       {
         id: "moonshot/kimi-k2.6",
@@ -1448,6 +1586,34 @@ var init_models = __esm({
         agentic: true,
         toolCalling: true
       },
+      // Tencent + Xiaomi (blockrun 2026-07-25): the two largest real demand gaps
+      // in the catalog — Hy3 held the #1 usage slot on the biggest public
+      // aggregator for 19 days; MiMo ran ~22% weekly share in April. Both are
+      // reasoning models resold via blockrun's OpenRouter pool. toolCalling
+      // LIVE-VERIFIED 2026-08-12: both returned a structured tool_calls array
+      // (name + valid JSON args, finish_reason "tool_calls") through the gateway.
+      {
+        id: "tencent/hy3",
+        name: "Tencent Hy3",
+        version: "hy3",
+        inputPrice: 0.132,
+        outputPrice: 0.528,
+        contextWindow: 262144,
+        maxOutput: 128e3,
+        reasoning: true,
+        toolCalling: true
+      },
+      {
+        id: "xiaomi/mimo-v2.5-pro",
+        name: "Xiaomi MiMo-V2.5 Pro",
+        version: "v2.5-pro",
+        inputPrice: 0.435,
+        outputPrice: 0.87,
+        contextWindow: 1048576,
+        maxOutput: 131072,
+        reasoning: true,
+        toolCalling: true
+      },
       // MiniMax
       {
         id: "minimax/minimax-m3",
@@ -1521,11 +1687,13 @@ var init_models = __esm({
         maxOutput: 16384
       },
       {
-        // 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.
+        // V4 Flash: 284B / 13B active MoE, 1M context. EOL'd 2026-08-12 — NVIDIA
+        // published 410 Gone ("has reached its end of life") on both probe passes
+        // and blockrun's prod gate fired [ALERT][free-model-dead] kind=gone twice
+        // that morning. The whole nvidia/deepseek-* family is dead upstream; there
+        // is no free DeepSeek left anywhere. Blockrun hid it and redirects calls to
+        // gpt-oss-120b. Entry kept so explicit pins stay routable; off the picker,
+        // the FREE_MODELS cascade, and the router fallback chains.
         id: "free/deepseek-v4-flash",
         name: "[Free] DeepSeek V4 Flash",
         version: "v4-flash",
@@ -1609,7 +1777,8 @@ 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. 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).
+      // glm-4.7 stay dead (server-redirected); deepseek-v4-flash recovered then
+      // EOL'd for good 2026-08-12 (see above).
       {
         // Qwen3-Next 80B (A3B active MoE): 262K context. DIED in the 2026-07-17
         // re-probe (">60s / DEGRADED") — hidden upstream, gateway redirects pinned
@@ -1714,11 +1883,12 @@ var init_models = __esm({
       },
       {
         // Flat-rate launch promo ended 2026-06-06 — backend bills per-token now.
+        // Repriced 0.60/1.92 → 1.00/3.20 (blockrun #354 correction).
         id: "zai/glm-5",
         name: "GLM-5",
         version: "5",
-        inputPrice: 0.6,
-        outputPrice: 1.92,
+        inputPrice: 1,
+        outputPrice: 3.2,
         contextWindow: 2e5,
         maxOutput: 128e3,
         reasoning: true,
@@ -37873,10 +38043,9 @@ ${value.slice(-(scanLimit - prefixLength))}`;
           fallback: [
             "free/gpt-oss-20b",
             // FREE — smaller, faster
-            "free/deepseek-v4-flash",
-            // FREE — 1M ctx; slow (~10 tok/s, 07-28 probe) but completes
-            // seed-oss-36b sat here as the free coder until it EOL'd 2026-08-03 (HTTP 410).
-            // gpt-oss-120b/20b already head this chain, so the rung is dropped, not retargeted.
+            // 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.
             "google/gemini-3.1-flash-lite",
             // $0.25/$1.50 — newest flash-lite
             "openai/gpt-5.4-nano",
@@ -92407,8 +92576,6 @@ var init_proxy = __esm({
     FREE_MODELS = /* @__PURE__ */ new Set([
       "free/gpt-oss-120b",
       "free/gpt-oss-20b",
-      "free/deepseek-v4-flash",
-      // 1M ctx; slow (~10 tok/s, 07-28 probe) but completes
       "free/mistral-nemotron",
       // strong instruction following
       "free/step-3.7-flash",
@@ -92505,6 +92672,8 @@ var init_proxy = __esm({
         sizes: { "1024x1024": 0.045, "2048x1024": 0.045, "2048x2048": 0.09 }
       },
       "google/nano-banana": { default: 0.05 },
+      // Nano Banana 2 (Gemini 3.1 Flash imagegen, blockrun #329): $0.09/image at 1K.
+      "google/nano-banana-2": { default: 0.09, sizes: { "1024x1024": 0.09 } },
       "google/nano-banana-pro": {
         default: 0.1,
         sizes: { "1024x1024": 0.1, "2048x2048": 0.1, "4096x4096": 0.15 }
@@ -92538,6 +92707,13 @@ var init_proxy = __esm({
         pricePerSecond: 0.227,
         defaultDurationSeconds: 5
       },
+      // Seedance 2.0 Mini (blockrun #366/#368, 2026-08-12): 720p + synced audio at
+      // half the flagship rate, 480p/720p only, 4–15s. blockrun signs the 3dp-floored
+      // per-second value (0.079, not the raw 0.0797) — mirror the signed number.
+      "bytedance/seedance-2.0-mini": {
+        pricePerSecond: 0.079,
+        defaultDurationSeconds: 5
+      },
       // Seedance 2.5: 720p with synced audio, up to 30s. Not a replacement for 2.0
       // Pro — that is still the one for 1080p/4K. No OpenRouter failover exists for
       // 2.5, so a token360 outage surfaces as an error instead of quietly rendering
@@ -225819,6 +225995,7 @@ function buildVideoGenerationProvider() {
       "bytedance/seedance-1.5-pro",
       "bytedance/seedance-2.0-fast",
       "bytedance/seedance-2.0",
+      "bytedance/seedance-2.0-mini",
       "bytedance/seedance-2.5"
     ],
     capabilities: {
@@ -226319,7 +226496,7 @@ var init_index = __esm({
             const parsed = parseGenArgs(ctx.args ?? "");
             if (!parsed.prompt) {
               return {
-                text: "Usage: `/cr-imagegen <prompt> [--model=<alias>] [--size=1024x1024] [--n=1]`\n\nAliases: `nano-banana` (default), `banana-pro`, `dalle`, `gpt-image`, `flux`, `grok-imagine`, `grok-imagine-pro`, `cogview`."
+                text: "Usage: `/cr-imagegen <prompt> [--model=<alias>] [--size=1024x1024] [--n=1]`\n\nAliases: `nano-banana` (default), `banana-2` (Gemini 3.1 Flash quality), `banana-pro`, `dalle`, `gpt-image`, `flux`, `grok-imagine`, `grok-imagine-pro`, `cogview`."
               };
             }
             const model = resolveModelAlias(parsed.model ?? "nano-banana");
@@ -226371,7 +226548,7 @@ ${errText}`
             const parsed = parseGenArgs(ctx.args ?? "");
             if (!parsed.prompt) {
               return {
-                text: "Usage: `/videogen <prompt> [--model=<alias>] [--duration=5|8|10]`\n\nAliases: `seedance` (1.5-pro, default \u2014 cheapest), `seedance-2-fast`, `seedance-2`, `seedance-2.5` (720p + synced audio, long-form), `grok-video`.\n\n\u23F1\uFE0F  Generation takes 60\u2013180 seconds. Payment settles only on success."
+                text: "Usage: `/videogen <prompt> [--model=<alias>] [--duration=5|8|10]`\n\nAliases: `seedance` (1.5-pro, default \u2014 cheapest), `seedance-2-fast`, `seedance-2`, `seedance-2-mini` (720p + audio, half the flagship rate), `seedance-2.5` (720p + synced audio, long-form), `grok-video`.\n\n\u23F1\uFE0F  Generation takes 60\u2013180 seconds. Payment settles only on success."
               };
             }
             const model = resolveModelAlias(parsed.model ?? "seedance");

package/dist/router/index.js CHANGED Viewed

@@ -3008,10 +3008,9 @@ var DEFAULT_ROUTING_CONFIG = {
       fallback: [
         "free/gpt-oss-20b",
         // FREE — smaller, faster
-        "free/deepseek-v4-flash",
-        // FREE — 1M ctx; slow (~10 tok/s, 07-28 probe) but completes
-        // seed-oss-36b sat here as the free coder until it EOL'd 2026-08-03 (HTTP 410).
-        // gpt-oss-120b/20b already head this chain, so the rung is dropped, not retargeted.
+        // 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.
         "google/gemini-3.1-flash-lite",
         // $0.25/$1.50 — newest flash-lite
         "openai/gpt-5.4-nano",

package/docs/anthropic-cost-savings.md CHANGED Viewed

@@ -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 -->71<!-- /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 -->70<!-- /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 CHANGED Viewed

@@ -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 -->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.
+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.
 ```
 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 -->71<!-- /br:models.chatVisible --> models, switch anytime
+- **No vendor lock-in** — <!-- br:models.chatVisible -->70<!-- /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 CHANGED Viewed

@@ -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 -->71<!-- /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 -->70<!-- /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 CHANGED Viewed

@@ -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 -->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)
+![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)
 ---
@@ -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 -->71<!-- /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 -->70<!-- /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 -->71<!-- /br:models.chatVisible --> models, redirect aliases         |
+| **Model catalog**   | Laggy, silent drops              | Curated <!-- br:models.chatVisible -->70<!-- /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/package.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "name": "@blockrun/clawrouter",
-  "version": "0.12.244",
-  "description": "Smart LLM router — save 88% on inference costs. 71 models (6 free), one wallet, x402 micropayments.",
+  "version": "0.12.245",
+  "description": "Smart LLM router — save 88% on inference costs. 70 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/6a790ebec60161825bbc8c4093fd221006b4e5fb",
+    "@blockrun/router-core": "https://codeload.github.com/BlockRunAI/router-core/tar.gz/18bf4abc7e34599e51595b90703c385f53d4f4a6",
     "@eslint/js": "^10.0.1",
     "eslint": "^10.2.0",
     "openclaw": "^2026.7.2-beta.7",

package/skills/clawrouter/SKILL.md CHANGED Viewed

@@ -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 71 models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 6 free NVIDIA models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai), AND the Surf unified crypto data API (84 endpoints — CEX/DEX, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, prediction markets, social/CT mindshare, news, VC fund intel) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.
+description: Hosted-gateway LLM router — save 88% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 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.
 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 -->71<!-- /br:models.chatVisible --> models from 9 providers (<!-- br:models.free -->6<!-- /br:models.free --> free NVIDIA models). All billing flows through one USDC wallet; you do not hold provider API keys.
+Hosted-gateway LLM router that saves <!-- br:savings.autoVsBaselinePct -->88<!-- /br:savings.autoVsBaselinePct -->% on inference costs by forwarding each request to the blockrun.ai gateway, which picks the cheapest model capable of handling it across <!-- br:models.chatVisible -->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.
 **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.
@@ -141,7 +141,7 @@ Rules handle ~~80% of requests in <1ms. Only ambiguous queries hit the LLM class
 ## Available Models
-<!-- 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-5.5, 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-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], and 6 free NVIDIA models (deepseek-v4-flash [1M context], 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 -->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]).
 ## Built-in Agent Tools

package/src/top-models.json CHANGED Viewed

@@ -38,7 +38,6 @@
   "deepseek/deepseek-v4-pro",
   "deepseek/deepseek-chat",
   "deepseek/deepseek-reasoner",
-  "free/deepseek-v4-flash",
   "free/nemotron-3-nano-omni-30b-a3b-reasoning",
   "free/mistral-nemotron",
   "free/step-3.7-flash",