@blockrun/clawrouter 0.12.233 → 0.12.235

package/README.md

@@ -460,9 +460,11 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
 | 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-5.5              |     $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                  |
 | openai/gpt-5.2-pro          |    $21.00 |    $168.00 |    $0.0945 | 400K    | reasoning, tools                  |
 | 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 seed-oss` for coding, `/model mistral-large` for the 675B flagship).
 > **Best value:** `gpt-5-nano` and `gemini-2.5-flash-lite` deliver strong results at ~$0.0003/request.

package/dist/cli.js

@@ -34303,6 +34303,7 @@ var init_top_models = __esm({
       "openai/gpt-5.6-sol",
       "openai/gpt-5.6-luna",
       "openai/gpt-5.5",
+      "openai/gpt-5.5-pro",
       "openai/gpt-5.4-pro",
       "openai/gpt-5.4",
       "openai/gpt-5.4-mini",
@@ -34474,8 +34475,12 @@ var init_models = __esm({
       "fable-5": "anthropic/claude-fable-5",
       "fable-5.0": "anthropic/claude-fable-5",
       // Opus 5 (2026-07-24) takes the bare `opus` alias: identical $5/$25 and the
-      // same 1M/128K envelope as 4.8, so no per-call-cap wallet changes behavior,
-      // and BlockRun already repointed `clawrouter-premium` → opus-5. `opus-4` and
+      // same 1M/128K envelope as 4.8, so a wallet with a per-call cost cap sees no
+      // change in how a request is priced or sized — the promotion cannot push a
+      // caller through a cap. BlockRun repointed `clawrouter-premium` → opus-5 for
+      // the same reason. (Unit price only: adaptive thinking may emit more output
+      // tokens per call, which raises realized spend without changing the cap math.)
+      // `opus-4` and
       // `anthropic/claude-opus-4` stay on 4.8 — they name the 4-series generation.
       // Note: `anthropic/claude-opus-5` must NOT be an alias key (see fable note).
       opus: "anthropic/claude-opus-5",
@@ -34525,6 +34530,11 @@ var init_models = __esm({
       "gpt-5.6-terra": "openai/gpt-5.6-terra",
       "gpt-5.6-luna": "openai/gpt-5.6-luna",
       "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
+      // "whatever ChatGPT's default is today", not a fixed snapshot.
+      "chat-latest": "openai/chat-latest",
+      chatgpt: "openai/chat-latest",
       "gpt-5.4": "openai/gpt-5.4",
       "gpt-5.4-pro": "openai/gpt-5.4-pro",
       "gpt-5.4-nano": "openai/gpt-5.4-nano",
@@ -34840,6 +34850,7 @@ var init_models = __esm({
         contextWindow: 4e5,
         maxOutput: 128e3,
         reasoning: true,
+        vision: true,
         toolCalling: true
       },
       // GPT-5.6 Family — GA 2026-07-09. Three fixed tiers (Sol/Terra/Luna) replace the
@@ -34904,6 +34915,38 @@ var init_models = __esm({
         agentic: true,
         toolCalling: true
       },
+      // GPT-5.5 Pro — max-compute tier of the 5.5 family, mirrors the gpt-5.4-pro
+      // shape. Upstream also has an OpenAI long-context tier (2x in / 1.5x out above
+      // 272K prompt tokens) that this registry cannot express; as with grok, that
+      // skews `logUsage` only — the charge is server-dictated via 402.
+      {
+        id: "openai/gpt-5.5-pro",
+        name: "GPT-5.5 Pro",
+        version: "5.5",
+        inputPrice: 30,
+        outputPrice: 180,
+        contextWindow: 105e4,
+        maxOutput: 128e3,
+        reasoning: true,
+        vision: true,
+        toolCalling: true
+      },
+      // ChatGPT Instant — upstream exposes ChatGPT's default model ONLY as the
+      // rolling version-less `chat-latest` id, so that is the honest catalog id: it
+      // stays correct when OpenAI rolls the default to the next Instant. The display
+      // name tracks whichever snapshot is current and must be refreshed on each roll.
+      // Chat/vision only upstream — no reasoning or agentic categories.
+      {
+        id: "openai/chat-latest",
+        name: "ChatGPT Instant (GPT-5.5)",
+        version: "5.5",
+        inputPrice: 5,
+        outputPrice: 30,
+        contextWindow: 128e3,
+        maxOutput: 128e3,
+        vision: true,
+        toolCalling: true
+      },
       // GPT-5.4 — flagship benchmarked into routing tiers
       {
         id: "openai/gpt-5.4",
@@ -34939,6 +34982,7 @@ var init_models = __esm({
         contextWindow: 4e5,
         maxOutput: 128e3,
         reasoning: true,
+        vision: true,
         toolCalling: true
       },
       {
@@ -35275,6 +35319,7 @@ var init_models = __esm({
         outputPrice: 3,
         contextWindow: 1e6,
         maxOutput: 65536,
+        reasoning: true,
         vision: true
       },
       {
@@ -35839,7 +35884,8 @@ var init_models = __esm({
         inputPrice: 0,
         outputPrice: 0,
         contextWindow: 131072,
-        maxOutput: 16384
+        maxOutput: 16384,
+        reasoning: true
       },
       {
         // NVIDIA Nemotron Nano 12B v2 VL: vision-language (text + image), 131K context.
@@ -35850,6 +35896,7 @@ var init_models = __esm({
         outputPrice: 0,
         contextWindow: 131072,
         maxOutput: 16384,
+        reasoning: true,
         vision: true
       },
       // Z.AI GLM-5 Models
@@ -35864,6 +35911,7 @@ var init_models = __esm({
         outputPrice: 4.4,
         contextWindow: 1e6,
         maxOutput: 262144,
+        reasoning: true,
         toolCalling: true
       },
       {
@@ -35876,6 +35924,7 @@ var init_models = __esm({
         outputPrice: 4.4,
         contextWindow: 2e5,
         maxOutput: 128e3,
+        reasoning: true,
         toolCalling: true,
         promo: { flatPrice: 1e-3, startDate: "2026-04-01", endDate: "2026-06-05" }
       },
@@ -35888,6 +35937,7 @@ var init_models = __esm({
         outputPrice: 1.92,
         contextWindow: 2e5,
         maxOutput: 128e3,
+        reasoning: true,
         toolCalling: true
       },
       {
@@ -35899,6 +35949,7 @@ var init_models = __esm({
         outputPrice: 4,
         contextWindow: 2e5,
         maxOutput: 128e3,
+        reasoning: true,
         toolCalling: true
       }
     ];

package/dist/index.js

@@ -68,6 +68,7 @@ var init_top_models = __esm({
       "openai/gpt-5.6-sol",
       "openai/gpt-5.6-luna",
       "openai/gpt-5.5",
+      "openai/gpt-5.5-pro",
       "openai/gpt-5.4-pro",
       "openai/gpt-5.4",
       "openai/gpt-5.4-mini",
@@ -239,8 +240,12 @@ var init_models = __esm({
       "fable-5": "anthropic/claude-fable-5",
       "fable-5.0": "anthropic/claude-fable-5",
       // Opus 5 (2026-07-24) takes the bare `opus` alias: identical $5/$25 and the
-      // same 1M/128K envelope as 4.8, so no per-call-cap wallet changes behavior,
-      // and BlockRun already repointed `clawrouter-premium` → opus-5. `opus-4` and
+      // same 1M/128K envelope as 4.8, so a wallet with a per-call cost cap sees no
+      // change in how a request is priced or sized — the promotion cannot push a
+      // caller through a cap. BlockRun repointed `clawrouter-premium` → opus-5 for
+      // the same reason. (Unit price only: adaptive thinking may emit more output
+      // tokens per call, which raises realized spend without changing the cap math.)
+      // `opus-4` and
       // `anthropic/claude-opus-4` stay on 4.8 — they name the 4-series generation.
       // Note: `anthropic/claude-opus-5` must NOT be an alias key (see fable note).
       opus: "anthropic/claude-opus-5",
@@ -290,6 +295,11 @@ var init_models = __esm({
       "gpt-5.6-terra": "openai/gpt-5.6-terra",
       "gpt-5.6-luna": "openai/gpt-5.6-luna",
       "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
+      // "whatever ChatGPT's default is today", not a fixed snapshot.
+      "chat-latest": "openai/chat-latest",
+      chatgpt: "openai/chat-latest",
       "gpt-5.4": "openai/gpt-5.4",
       "gpt-5.4-pro": "openai/gpt-5.4-pro",
       "gpt-5.4-nano": "openai/gpt-5.4-nano",
@@ -605,6 +615,7 @@ var init_models = __esm({
         contextWindow: 4e5,
         maxOutput: 128e3,
         reasoning: true,
+        vision: true,
         toolCalling: true
       },
       // GPT-5.6 Family — GA 2026-07-09. Three fixed tiers (Sol/Terra/Luna) replace the
@@ -669,6 +680,38 @@ var init_models = __esm({
         agentic: true,
         toolCalling: true
       },
+      // GPT-5.5 Pro — max-compute tier of the 5.5 family, mirrors the gpt-5.4-pro
+      // shape. Upstream also has an OpenAI long-context tier (2x in / 1.5x out above
+      // 272K prompt tokens) that this registry cannot express; as with grok, that
+      // skews `logUsage` only — the charge is server-dictated via 402.
+      {
+        id: "openai/gpt-5.5-pro",
+        name: "GPT-5.5 Pro",
+        version: "5.5",
+        inputPrice: 30,
+        outputPrice: 180,
+        contextWindow: 105e4,
+        maxOutput: 128e3,
+        reasoning: true,
+        vision: true,
+        toolCalling: true
+      },
+      // ChatGPT Instant — upstream exposes ChatGPT's default model ONLY as the
+      // rolling version-less `chat-latest` id, so that is the honest catalog id: it
+      // stays correct when OpenAI rolls the default to the next Instant. The display
+      // name tracks whichever snapshot is current and must be refreshed on each roll.
+      // Chat/vision only upstream — no reasoning or agentic categories.
+      {
+        id: "openai/chat-latest",
+        name: "ChatGPT Instant (GPT-5.5)",
+        version: "5.5",
+        inputPrice: 5,
+        outputPrice: 30,
+        contextWindow: 128e3,
+        maxOutput: 128e3,
+        vision: true,
+        toolCalling: true
+      },
       // GPT-5.4 — flagship benchmarked into routing tiers
       {
         id: "openai/gpt-5.4",
@@ -704,6 +747,7 @@ var init_models = __esm({
         contextWindow: 4e5,
         maxOutput: 128e3,
         reasoning: true,
+        vision: true,
         toolCalling: true
       },
       {
@@ -1040,6 +1084,7 @@ var init_models = __esm({
         outputPrice: 3,
         contextWindow: 1e6,
         maxOutput: 65536,
+        reasoning: true,
         vision: true
       },
       {
@@ -1604,7 +1649,8 @@ var init_models = __esm({
         inputPrice: 0,
         outputPrice: 0,
         contextWindow: 131072,
-        maxOutput: 16384
+        maxOutput: 16384,
+        reasoning: true
       },
       {
         // NVIDIA Nemotron Nano 12B v2 VL: vision-language (text + image), 131K context.
@@ -1615,6 +1661,7 @@ var init_models = __esm({
         outputPrice: 0,
         contextWindow: 131072,
         maxOutput: 16384,
+        reasoning: true,
         vision: true
       },
       // Z.AI GLM-5 Models
@@ -1629,6 +1676,7 @@ var init_models = __esm({
         outputPrice: 4.4,
         contextWindow: 1e6,
         maxOutput: 262144,
+        reasoning: true,
         toolCalling: true
       },
       {
@@ -1641,6 +1689,7 @@ var init_models = __esm({
         outputPrice: 4.4,
         contextWindow: 2e5,
         maxOutput: 128e3,
+        reasoning: true,
         toolCalling: true,
         promo: { flatPrice: 1e-3, startDate: "2026-04-01", endDate: "2026-06-05" }
       },
@@ -1653,6 +1702,7 @@ var init_models = __esm({
         outputPrice: 1.92,
         contextWindow: 2e5,
         maxOutput: 128e3,
+        reasoning: true,
         toolCalling: true
       },
       {
@@ -1664,6 +1714,7 @@ var init_models = __esm({
         outputPrice: 4,
         contextWindow: 2e5,
         maxOutput: 128e3,
+        reasoning: true,
         toolCalling: true
       }
     ];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@blockrun/clawrouter",
-  "version": "0.12.233",
+  "version": "0.12.235",
   "description": "Smart LLM router — save 85% on inference costs. 55+ models (8 free), one wallet, x402 micropayments.",
   "type": "module",
   "main": "dist/index.js",

package/skills/clawrouter/SKILL.md

@@ -135,7 +135,7 @@ Rules handle ~~80% of requests in <1ms. Only ambiguous queries hit the LLM class
 
 ## Available Models
 
-55+ models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.5, gpt-5.4, 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 8 free NVIDIA models (mistral-large-3-675b [default, 675B flagship], deepseek-v4-flash [1M context], seed-oss-36b [coding], nemotron-3-nano-omni-30b-a3b-reasoning [vision], mistral-nemotron, step-3.7-flash, nemotron-nano-9b-v2, nemotron-nano-12b-v2-vl [vision]).
+55+ 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 8 free NVIDIA models (mistral-large-3-675b [default, 675B flagship], deepseek-v4-flash [1M context], seed-oss-36b [coding], 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

@@ -14,6 +14,7 @@
   "openai/gpt-5.6-sol",
   "openai/gpt-5.6-luna",
   "openai/gpt-5.5",
+  "openai/gpt-5.5-pro",
   "openai/gpt-5.4-pro",
   "openai/gpt-5.4",
   "openai/gpt-5.4-mini",