@blockrun/clawrouter 0.12.86 → 0.12.88

package/README.md

@@ -92,6 +92,7 @@ Done. Smart routing (`blockrun/auto`) is now your default model.
 No OpenClaw required. ClawRouter runs as a local proxy on port 8402.
 
 **1. Start the proxy**
+
 ```bash
 npx @blockrun/clawrouter
 ```
@@ -102,7 +103,29 @@ Your wallet address is printed on first run. Send a few USDC on Base or Solana
 **3. Point your client at `http://localhost:8402`**
 
 <details>
-<summary><strong>continue.dev</strong> — <code>~/.continue/config.json</code></summary>
+<summary><strong>continue.dev</strong> — <code>~/.continue/config.yaml</code></summary>
+
+> **Important:** `apiBase` must end with `/v1/` (including the trailing slash). Without it, continue.dev constructs the URL as `/chat/completions` instead of `/v1/chat/completions`, and the proxy returns 404.
+
+```yaml
+models:
+  - name: ClawRouter Auto
+    provider: openai
+    model: blockrun/auto
+    apiBase: http://localhost:8402/v1/
+    apiKey: x402
+    roles:
+      - chat
+      - edit
+      - apply
+```
+
+To pin a specific model, replace `blockrun/auto` with any model from [blockrun.ai/models](https://blockrun.ai/models), e.g. `anthropic/claude-opus-4.6`, `xai/grok-4-0709`.
+
+Both `provider: openai` and `provider: clawrouter` work — just make sure `apiBase` ends with `/v1/`.
+
+<details>
+<summary>Legacy JSON format (<code>~/.continue/config.json</code>)</summary>
 
 ```json
 {
@@ -111,18 +134,21 @@ Your wallet address is printed on first run. Send a few USDC on Base or Solana
       "title": "ClawRouter Auto",
       "provider": "openai",
       "model": "blockrun/auto",
-      "apiBase": "http://localhost:8402",
+      "apiBase": "http://localhost:8402/v1/",
       "apiKey": "x402"
     }
   ]
 }
 ```
+
+</details>
 </details>
 
 <details>
 <summary><strong>Cursor</strong> — Settings → Models → OpenAI-compatible</summary>
 
 Set base URL to `http://localhost:8402`, API key to `x402`, model to `blockrun/auto`.
+
 </details>
 
 <details>
@@ -133,6 +159,7 @@ from openai import OpenAI
 client = OpenAI(base_url="http://localhost:8402", api_key="x402")
 response = client.chat.completions.create(model="blockrun/auto", messages=[...])
 ```
+
 </details>
 
 ---
@@ -490,14 +517,14 @@ Run Claude Code with 50+ models, no rate limits, no Anthropic account, no phone
 
 ### Blog
 
-| Article | Topic |
-| ------- | ----- |
-| [11 Free AI Models, Zero Cost](docs/11-free-ai-models-zero-cost-blockrun.md) | How BlockRun gives developers top-tier LLMs for nothing |
-| [ClawRouter Cuts LLM API Costs 500×](docs/clawrouter-cuts-llm-api-costs-500x.md) | Deep dive into cost savings |
-| [ClawRouter vs OpenRouter](docs/clawrouter-vs-openrouter-llm-routing-comparison.md) | Head-to-head comparison |
-| [Smart LLM Router: 14-Dimension Classifier](docs/smart-llm-router-14-dimension-classifier.md) | How the routing engine works |
-| [LLM Router Benchmark: 46 Models, Sub-1ms](docs/llm-router-benchmark-46-models-sub-1ms-routing.md) | Performance benchmarks |
-| [Anthropic Cost Savings](docs/anthropic-cost-savings.md) | Reducing Claude API spend |
+| Article                                                                                            | Topic                                                   |
+| -------------------------------------------------------------------------------------------------- | ------------------------------------------------------- |
+| [11 Free AI Models, Zero Cost](docs/11-free-ai-models-zero-cost-blockrun.md)                       | How BlockRun gives developers top-tier LLMs for nothing |
+| [ClawRouter Cuts LLM API Costs 500×](docs/clawrouter-cuts-llm-api-costs-500x.md)                   | Deep dive into cost savings                             |
+| [ClawRouter vs OpenRouter](docs/clawrouter-vs-openrouter-llm-routing-comparison.md)                | Head-to-head comparison                                 |
+| [Smart LLM Router: 14-Dimension Classifier](docs/smart-llm-router-14-dimension-classifier.md)      | How the routing engine works                            |
+| [LLM Router Benchmark: 46 Models, Sub-1ms](docs/llm-router-benchmark-46-models-sub-1ms-routing.md) | Performance benchmarks                                  |
+| [Anthropic Cost Savings](docs/anthropic-cost-savings.md)                                           | Reducing Claude API spend                               |
 
 ---