@blockrun/clawrouter 0.12.56 → 0.12.61

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 (9) hide show
  1. package/README.md +93 -51
  2. package/dist/cli.js +456 -68
  3. package/dist/cli.js.map +1 -1
  4. package/dist/index.d.ts +34 -0
  5. package/dist/index.js +601 -84
  6. package/dist/index.js.map +1 -1
  7. package/package.json +1 -1
  8. package/scripts/reinstall.sh +96 -17
  9. package/scripts/update.sh +93 -17
package/README.md CHANGED
@@ -56,7 +56,7 @@ This is the stack that lets agents operate autonomously: **x402 + USDC + local r
56
56
 
57
57
  | | OpenRouter | LiteLLM | Martian | Portkey | **ClawRouter** |
58
58
  | ---------------- | ----------------- | ---------------- | ----------------- | ----------------- | ----------------------- |
59
- | **Models** | 200+ | 100+ | Smart routing | Gateway | **41+** |
59
+ | **Models** | 200+ | 100+ | Smart routing | Gateway | **44+** |
60
60
  | **Routing** | Manual selection | Manual selection | Smart (closed) | Observability | **Smart (open source)** |
61
61
  | **Auth** | Account + API key | Your API keys | Account + API key | Account + API key | **Wallet signature** |
62
62
  | **Payment** | Credit card | BYO keys | Credit card | $49-499/mo | **USDC per-request** |
@@ -108,12 +108,12 @@ Choose your routing strategy with `/model <profile>`:
108
108
  Request → Weighted Scorer (15 dimensions) → Tier → Best Model → Response
109
109
  ```
110
110
 
111
- | Tier | ECO Model | AUTO Model | PREMIUM Model |
112
- | --------- | ----------------------------------- | ---------------------------- | ---------------------------- |
113
- | SIMPLE | nvidia/gpt-oss-120b (FREE) | kimi-k2.5 ($0.60/$3.00) | kimi-k2.5 |
114
- | MEDIUM | gemini-2.5-flash-lite ($0.10/$0.40) | grok-code-fast ($0.20/$1.50) | gpt-5.2-codex ($1.75/$14.00) |
115
- | COMPLEX | gemini-2.5-flash-lite ($0.10/$0.40) | gemini-3.1-pro ($2/$12) | claude-opus-4.6 ($5/$25) |
116
- | REASONING | grok-4-fast ($0.20/$0.50) | grok-4-fast ($0.20/$0.50) | claude-sonnet-4.6 ($3/$15) |
111
+ | Tier | ECO Model | AUTO Model | PREMIUM Model |
112
+ | --------- | ----------------------------------- | ---------------------------------- | ---------------------------- |
113
+ | SIMPLE | nvidia/gpt-oss-120b (FREE) | kimi-k2.5 ($0.60/$3.00) | kimi-k2.5 |
114
+ | MEDIUM | gemini-2.5-flash-lite ($0.10/$0.40) | grok-4-0709 ($0.20/$1.50) | gpt-5.3-codex ($1.75/$14.00) |
115
+ | COMPLEX | gemini-2.5-flash-lite ($0.10/$0.40) | gemini-3.1-pro ($2/$12) | claude-opus-4.6 ($5/$25) |
116
+ | REASONING | grok-4-fast ($0.20/$0.50) | grok-4-1-fast-reasoning ($0.20/$0.50) | claude-sonnet-4.6 ($3/$15) |
117
117
 
118
118
  **Blended average: $2.05/M** vs $25/M for Claude Opus = **92% savings**
119
119
 
@@ -159,48 +159,71 @@ Edit existing images with `/img2img`:
159
159
 
160
160
  ## Models & Pricing
161
161
 
162
- 41+ models across 7 providers, one wallet:
163
-
164
- <details>
165
- <summary><strong>Click to expand full model list</strong></summary>
166
-
167
- | Model | Input $/M | Output $/M | Context | Reasoning |
168
- | ----------------------- | --------- | ---------- | ------- | :-------: |
169
- | **OpenAI** | | | | |
170
- | gpt-5.2 | $1.75 | $14.00 | 400K | \* |
171
- | gpt-4o | $2.50 | $10.00 | 128K | |
172
- | gpt-4o-mini | $0.15 | $0.60 | 128K | |
173
- | gpt-oss-120b | **FREE** | **FREE** | 128K | |
174
- | o1 | $15.00 | $60.00 | 200K | \* |
175
- | o1-mini | $1.10 | $4.40 | 128K | \* |
176
- | o3 | $2.00 | $8.00 | 200K | \* |
177
- | o4-mini | $1.10 | $4.40 | 128K | \* |
178
- | **Anthropic** | | | | |
179
- | claude-opus-4.6 | $5.00 | $25.00 | 200K | \* |
180
- | claude-sonnet-4.6 | $3.00 | $15.00 | 200K | \* |
181
- | claude-haiku-4.5 | $1.00 | $5.00 | 200K | |
182
- | **Google** | | | | |
183
- | gemini-3.1-pro | $2.00 | $12.00 | 1M | \* |
184
- | gemini-3-pro-preview | $2.00 | $12.00 | 1M | \* |
185
- | gemini-3-flash-preview | $0.50 | $3.00 | 1M | |
186
- | gemini-2.5-pro | $1.25 | $10.00 | 1M | \* |
187
- | gemini-2.5-flash | $0.30 | $2.50 | 1M | |
188
- | gemini-2.5-flash-lite | $0.10 | $0.40 | 1M | |
189
- | **DeepSeek** | | | | |
190
- | deepseek-chat | $0.28 | $0.42 | 128K | |
191
- | deepseek-reasoner | $0.28 | $0.42 | 128K | \* |
192
- | **xAI** | | | | |
193
- | grok-4-0709 | $0.20 | $1.50 | 131K | \* |
194
- | grok-4-1-fast-reasoning | $0.20 | $0.50 | 131K | \* |
195
- | grok-code-fast-1 | $0.20 | $1.50 | 131K | |
196
- | **Moonshot** | | | | |
197
- | kimi-k2.5 | $0.60 | $3.00 | 262K | \* |
198
- | **MiniMax** | | | | |
199
- | minimax-m2.5 | $0.30 | $1.20 | 205K | \* |
200
-
201
- </details>
202
-
203
- > **Free tier:** `gpt-oss-120b` costs nothing and serves as automatic fallback when wallet is empty.
162
+ 44 models across 8 providers, one wallet. **Starting at $0.0002/request.**
163
+
164
+ > **💡 "Cost per request"** = estimated cost for a typical chat message (~500 input + 500 output tokens).
165
+
166
+ ### Budget Models (under $0.001/request)
167
+
168
+ | Model | Input $/M | Output $/M | ~$/request | Context | Features |
169
+ | --- | ---: | ---: | ---: | --- | --- |
170
+ | nvidia/gpt-oss-120b | **FREE** | **FREE** | **$0** | 128K | |
171
+ | openai/gpt-5-nano | $0.05 | $0.40 | $0.0002 | 128K | tools |
172
+ | openai/gpt-4.1-nano | $0.10 | $0.40 | $0.0003 | 128K | tools |
173
+ | google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.0003 | 1M | tools |
174
+ | openai/gpt-4o-mini | $0.15 | $0.60 | $0.0004 | 128K | tools |
175
+ | xai/grok-4-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
176
+ | xai/grok-4-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools |
177
+ | xai/grok-4-1-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
178
+ | xai/grok-4-1-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools |
179
+ | xai/grok-4-0709 | $0.20 | $1.50 | $0.0009 | 131K | reasoning, tools |
180
+ | openai/gpt-5-mini | $0.25 | $2.00 | $0.0011 | 200K | tools |
181
+ | deepseek/deepseek-chat | $0.28 | $0.42 | $0.0004 | 128K | tools |
182
+ | deepseek/deepseek-reasoner | $0.28 | $0.42 | $0.0004 | 128K | reasoning, tools |
183
+ | xai/grok-3-mini | $0.30 | $0.50 | $0.0004 | 131K | tools |
184
+ | minimax/minimax-m2.7 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
185
+ | minimax/minimax-m2.5 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
186
+ | google/gemini-2.5-flash | $0.30 | $2.50 | $0.0014 | 1M | vision, tools |
187
+ | openai/gpt-4.1-mini | $0.40 | $1.60 | $0.0010 | 128K | tools |
188
+ | google/gemini-3-flash-preview | $0.50 | $3.00 | $0.0018 | 1M | vision |
189
+ | nvidia/kimi-k2.5 | $0.55 | $2.50 | $0.0015 | 262K | tools |
190
+ | moonshot/kimi-k2.5 | $0.60 | $3.00 | $0.0018 | 262K | reasoning, vision, agentic, tools |
191
+
192
+ ### Mid-Range Models ($0.001–$0.01/request)
193
+
194
+ | Model | Input $/M | Output $/M | ~$/request | Context | Features |
195
+ | --- | ---: | ---: | ---: | --- | --- |
196
+ | anthropic/claude-haiku-4.5 | $1.00 | $5.00 | $0.0030 | 200K | vision, agentic, tools |
197
+ | zai/glm-5 | $1.00 | $3.20 | $0.0021 | 200K | tools |
198
+ | openai/o1-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
199
+ | openai/o3-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
200
+ | openai/o4-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
201
+ | zai/glm-5-turbo | $1.20 | $4.00 | $0.0026 | 200K | tools |
202
+ | google/gemini-2.5-pro | $1.25 | $10.00 | $0.0056 | 1M | reasoning, vision, tools |
203
+ | openai/gpt-5.2 | $1.75 | $14.00 | $0.0079 | 400K | reasoning, vision, agentic, tools |
204
+ | openai/gpt-5.3 | $1.75 | $14.00 | $0.0079 | 128K | reasoning, vision, agentic, tools |
205
+ | openai/gpt-5.3-codex | $1.75 | $14.00 | $0.0079 | 400K | agentic, tools |
206
+ | openai/gpt-4.1 | $2.00 | $8.00 | $0.0050 | 128K | vision, tools |
207
+ | openai/o3 | $2.00 | $8.00 | $0.0050 | 200K | reasoning, tools |
208
+ | google/gemini-3-pro-preview | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, tools |
209
+ | google/gemini-3.1-pro | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, tools |
210
+ | xai/grok-2-vision | $2.00 | $10.00 | $0.0060 | 131K | vision, tools |
211
+ | openai/gpt-4o | $2.50 | $10.00 | $0.0063 | 128K | vision, agentic, tools |
212
+ | openai/gpt-5.4 | $2.50 | $15.00 | $0.0088 | 400K | reasoning, vision, agentic, tools |
213
+
214
+ ### Premium Models ($0.01+/request)
215
+
216
+ | Model | Input $/M | Output $/M | ~$/request | Context | Features |
217
+ | --- | ---: | ---: | ---: | --- | --- |
218
+ | anthropic/claude-sonnet-4.6 | $3.00 | $15.00 | $0.0090 | 200K | reasoning, vision, agentic, tools |
219
+ | xai/grok-3 | $3.00 | $15.00 | $0.0090 | 131K | reasoning, tools |
220
+ | anthropic/claude-opus-4.6 | $5.00 | $25.00 | $0.0150 | 200K | reasoning, vision, agentic, tools |
221
+ | openai/o1 | $15.00 | $60.00 | $0.0375 | 200K | reasoning, tools |
222
+ | openai/gpt-5.2-pro | $21.00 | $168.00 | $0.0945 | 400K | reasoning, tools |
223
+ | openai/gpt-5.4-pro | $30.00 | $180.00 | $0.1050 | 400K | reasoning, tools |
224
+
225
+ > **Free tier:** `nvidia/gpt-oss-120b` costs nothing and serves as automatic fallback when wallet is empty.
226
+ > **Best value:** `gpt-5-nano` and `gemini-2.5-flash-lite` deliver strong results at ~$0.0003/request.
204
227
 
205
228
  ---
206
229
 
@@ -225,6 +248,10 @@ USDC stays in your wallet until spent — non-custodial. Price is visible in the
225
248
  /chain solana # Alias for /wallet solana
226
249
  /stats # View usage and savings
227
250
  /stats clear # Reset usage statistics
251
+ /exclude # Show excluded models
252
+ /exclude add <model> # Block a model from routing (aliases work: "grok-4", "free")
253
+ /exclude remove <model> # Unblock a model
254
+ /exclude clear # Remove all exclusions
228
255
  ```
229
256
 
230
257
  **Fund your wallet:**
@@ -266,6 +293,21 @@ For basic usage, no configuration needed. For advanced options:
266
293
 
267
294
  **Full reference:** [docs/configuration.md](docs/configuration.md)
268
295
 
296
+ ### Model Exclusion
297
+
298
+ Block specific models from being routed to. Useful if a model doesn't follow your agent instructions or you want to control costs.
299
+
300
+ ```bash
301
+ /exclude add nvidia/gpt-oss-120b # Block the free model
302
+ /exclude add grok-4 # Aliases work — blocks all grok-4 variants
303
+ /exclude add gpt-5.4 # Skip expensive models
304
+ /exclude # Show current exclusions
305
+ /exclude remove grok-4 # Unblock a model
306
+ /exclude clear # Remove all exclusions
307
+ ```
308
+
309
+ Exclusions persist across restarts (`~/.openclaw/blockrun/exclude-models.json`). If all models in a tier are excluded, the safety net ignores the filter so routing never breaks.
310
+
269
311
  ---
270
312
 
271
313
  ## Troubleshooting
@@ -334,7 +376,7 @@ npm test
334
376
  | --------------------- | ------------------------------------------------------------------ |
335
377
  | 📅 Schedule Demo | [calendly.com/vickyfu9/30min](https://calendly.com/vickyfu9/30min) |
336
378
  | 💬 Community Telegram | [t.me/blockrunAI](https://t.me/blockrunAI) |
337
- | 🐦 X / Twitter | [x.com/ClawRou](https://x.com/ClawRou) |
379
+ | 🐦 X / Twitter | [x.com/blockrunai](https://x.com/blockrunai) |
338
380
  | 📱 Founder Telegram | [@bc1max](https://t.me/bc1max) |
339
381
  | ✉️ Email | vicky@blockrun.ai |
340
382
 
@@ -350,7 +392,7 @@ npm test
350
392
 
351
393
  **The LLM router built for autonomous agents**
352
394
 
353
- You're here. 41+ models, local smart routing, x402 USDC payments — the only stack that lets agents operate independently.
395
+ You're here. 44+ models, local smart routing, x402 USDC payments — the only stack that lets agents operate independently.
354
396
 
355
397
  `curl -fsSL https://blockrun.ai/ClawRouter-update | bash`
356
398