@blockrun/clawrouter 0.12.76 → 0.12.77

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 (2) hide show
  1. package/README.md +19 -9
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -96,7 +96,7 @@ Choose your routing strategy with `/model <profile>`:
96
96
  | `/model auto` | Balanced (default) | 74-100% | General use |
97
97
  | `/model eco` | Cheapest possible | 95-100% | Maximum savings |
98
98
  | `/model premium` | Best quality | 0% | Mission-critical |
99
- | `/model free` | Free tier only | 100% | Zero cost |
99
+ | `/model free` | 11 free NVIDIA models | 100% | Zero cost |
100
100
 
101
101
  **Shortcuts:** `/model grok`, `/model br-sonnet`, `/model gpt5`, `/model o3`
102
102
 
@@ -110,12 +110,12 @@ Choose your routing strategy with `/model <profile>`:
110
110
  Request → Weighted Scorer (15 dimensions) → Tier → Best Model → Response
111
111
  ```
112
112
 
113
- | Tier | ECO Model | AUTO Model | PREMIUM Model |
114
- | --------- | ----------------------------------- | ------------------------------------- | ---------------------------- |
115
- | SIMPLE | nvidia/gpt-oss-120b (FREE) | kimi-k2.5 ($0.60/$3.00) | kimi-k2.5 |
116
- | 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) |
117
- | COMPLEX | gemini-2.5-flash-lite ($0.10/$0.40) | gemini-3.1-pro ($2/$12) | claude-opus-4.6 ($5/$25) |
118
- | REASONING | grok-4-fast ($0.20/$0.50) | grok-4-1-fast-reasoning ($0.20/$0.50) | claude-sonnet-4.6 ($3/$15) |
113
+ | Tier | ECO Model | AUTO Model | PREMIUM Model |
114
+ | --------- | -------------------------------------- | ------------------------------------- | ---------------------------- |
115
+ | SIMPLE | nvidia/gpt-oss-120b (**FREE**) | gemini-2.5-flash ($0.30/$2.50) | kimi-k2.5 |
116
+ | MEDIUM | nvidia/deepseek-v3.2 (**FREE**) | kimi-k2.5 ($0.60/$3.00) | gpt-5.3-codex ($1.75/$14.00) |
117
+ | COMPLEX | nvidia/nemotron-ultra-253b (**FREE**) | gemini-3.1-pro ($2/$12) | claude-opus-4.6 ($5/$25) |
118
+ | REASONING | grok-4-1-fast ($0.20/$0.50) | grok-4-1-fast-reasoning ($0.20/$0.50) | claude-sonnet-4.6 ($3/$15) |
119
119
 
120
120
  **Blended average: $2.05/M** vs $25/M for Claude Opus = **92% savings**
121
121
 
@@ -170,6 +170,16 @@ Edit existing images with `/img2img`:
170
170
  | Model | Input $/M | Output $/M | ~$/request | Context | Features |
171
171
  | ----------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------- |
172
172
  | nvidia/gpt-oss-120b | **FREE** | **FREE** | **$0** | 128K | |
173
+ | nvidia/gpt-oss-20b | **FREE** | **FREE** | **$0** | 128K | |
174
+ | nvidia/nemotron-ultra-253b | **FREE** | **FREE** | **$0** | 131K | reasoning |
175
+ | nvidia/nemotron-3-super-120b | **FREE** | **FREE** | **$0** | 131K | reasoning |
176
+ | nvidia/nemotron-super-49b | **FREE** | **FREE** | **$0** | 131K | reasoning |
177
+ | nvidia/deepseek-v3.2 | **FREE** | **FREE** | **$0** | 131K | reasoning |
178
+ | nvidia/mistral-large-3-675b | **FREE** | **FREE** | **$0** | 131K | reasoning |
179
+ | nvidia/qwen3-coder-480b | **FREE** | **FREE** | **$0** | 131K | |
180
+ | nvidia/devstral-2-123b | **FREE** | **FREE** | **$0** | 131K | |
181
+ | nvidia/glm-4.7 | **FREE** | **FREE** | **$0** | 131K | reasoning |
182
+ | nvidia/llama-4-maverick | **FREE** | **FREE** | **$0** | 131K | reasoning |
173
183
  | openai/gpt-5-nano | $0.05 | $0.40 | $0.0002 | 128K | tools |
174
184
  | openai/gpt-4.1-nano | $0.10 | $0.40 | $0.0003 | 128K | tools |
175
185
  | google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.0003 | 1M | tools |
@@ -224,7 +234,7 @@ Edit existing images with `/img2img`:
224
234
  | openai/gpt-5.2-pro | $21.00 | $168.00 | $0.0945 | 400K | reasoning, tools |
225
235
  | openai/gpt-5.4-pro | $30.00 | $180.00 | $0.1050 | 400K | reasoning, tools |
226
236
 
227
- > **Free tier:** `nvidia/gpt-oss-120b` costs nothing and serves as automatic fallback when wallet is empty.
237
+ > **Free tier:** 11 NVIDIA models cost nothing — use `/model free` for smart routing across all of them, or pick one directly (e.g., `/model nemotron`). Auto-fallback when wallet is empty also uses free models matched to task complexity.
228
238
  > **Best value:** `gpt-5-nano` and `gemini-2.5-flash-lite` deliver strong results at ~$0.0003/request.
229
239
 
230
240
  ---
@@ -455,7 +465,7 @@ ClawRouter integrates with OpenClaw (Claude Code), ElizaOS, and any agent that m
455
465
 
456
466
  ### Is ClawRouter free?
457
467
 
458
- ClawRouter itself is free and MIT licensed. You pay only for the LLM API calls routed through it — and NVIDIA GPT-OSS models are completely free, so you can even use it at zero cost.
468
+ ClawRouter itself is free and MIT licensed. You pay only for the LLM API calls routed through it — and 11 NVIDIA models (DeepSeek V3.2, Nemotron Ultra 253B, Mistral Large 675B, Llama 4 Maverick, and more) are completely free. Use `/model free` for zero-cost smart routing.
459
469
 
460
470
  ---
461
471
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@blockrun/clawrouter",
3
- "version": "0.12.76",
3
+ "version": "0.12.77",
4
4
  "description": "Smart LLM router — save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",