modelmix 5.2.3 → 5.3.0

package/README.md

@@ -160,7 +160,9 @@ ModelMix provides convenient shorthand methods for quickly accessing different A
 | Method | Provider | Model | Input / 1M | Output / 1M |
 | --- | --- | --- | ---: | ---: |
 | `gpt6astra()` | OpenAI | gpt-6-astra | [\$10.00][1] | [\$50.00][1] |
-| `gpt56sol()` | OpenAI | gpt-5.6-sol | [\$5.00][1] | [\$30.00][1] |
+| `gpt6sol()` | OpenAI | gpt-6-sol | [\$2.00][1] | [\$10.00][1] |
+| `gpt6luna()` | OpenAI | gpt-6-luna | [\$0.10][1] | [\$0.50][1] |
+| `gpt56sol()` | OpenAI | gpt-5.6-sol | [\$4.00][1] | [\$20.00][1] |
 | `gpt56terra()` | OpenAI | gpt-5.6-terra | [\$2.00][1] | [\$12.00][1] |
 | `gpt56luna()` | OpenAI | gpt-5.6-luna | [\$0.20][1] | [\$1.20][1] |
 | `gpt55()` | OpenAI | gpt-5.5 | [\$5.00][1] | [\$30.00][1] |
@@ -320,6 +322,7 @@ ModelMix.new().effort(-1).minimaxM3().addText('...').message();
 
 - **Gemini:** Gemini 3+ uses bands 0–24 / 25–49 / 50–74 / 75–100. Gemini 3.8 Flash and 3.7 Flash clamp these bands to `low` / `low` / `medium` / `high`; `-1` leaves their native `medium` default unchanged. Gemini 2.5 maps 0–100 to `thinkingBudget`.
 - **GPT-6 Astra:** 0–39 maps to `low`, 40–59 to `medium`, 60–79 to `high`, 80–99 to `xhigh`, and 100 to `max`. [Model details](https://developers.openai.com/api/docs/models/gpt-6-astra). Cache reads cost $1.00 and cache writes $12.50 per 1M tokens; requests over 272K input tokens apply 2× input/cache and 1.5× output rates.
+- **GPT-6 Sol and GPT-6 Luna:** `100` maps to `max`; the remaining bands match OpenAI, so 0–19 is `none` and 80–99 is `xhigh`. [Sol model details](https://developers.openai.com/api/docs/models/gpt-6-sol), [Luna model details](https://developers.openai.com/api/docs/models/gpt-6-luna). Cache reads cost $0.20 and $0.01 and cache writes $2.50 and $0.125 per 1M tokens; requests over 272K input tokens apply the same 2× input/cache and 1.5× output rates as Astra.
 - **GPT-5.6:** `100` maps to `max`; 80–99 remains `xhigh`.
 - **Qwen 3.8 27B and Flash:** 0–39 / 40–79 / 80–100 map to `low` / `medium` / `xhigh`; `-1` leaves the native `xhigh` default unchanged. Qwen 3.8 Flash is the managed production version based on the open-weight Flash-Next architecture.
 - **GLM 5.3 and GLM 5.3 Flash:** reasoning is mandatory; 0–39 / 40–79 / 80–100 map to `low` / `high` / `max`; `-1` leaves the native `max` default unchanged.
@@ -831,9 +834,9 @@ await ask('Summarize support ticket 456.');
 
 The contents of `support.md` and the cache key stay the same between calls; only the final question changes. The first request may report `cacheWrite > 0`, while later requests confirm reuse with `cached > 0`. For GPT-5.6, the stable prefix must contain at least 1,024 tokens. Keep all variable content after the breakpoint, and change `prompt_cache_key` when the stable instructions change.
 
-### GPT-5.6 prompt caching
+### GPT-5.6 and GPT-6 prompt caching
 
-GPT-5.6 supports implicit or explicit caching through `prompt_cache_options`. Put the explicit breakpoint at the end of the stable prefix; the provider only caches prompts with at least 1,024 tokens.
+GPT-5.6 and the GPT-6 models (Astra, Sol, and Luna) support implicit or explicit caching through `prompt_cache_options`. Put the explicit breakpoint at the end of the stable prefix; the provider only caches prompts with at least 1,024 tokens.
 
 ```javascript
 const model = ModelMix.new()
@@ -854,16 +857,18 @@ console.log(result.tokens.cached, result.tokens.cacheWrite, result.tokens.cost);
 
 The provider-neutral `cache: { breakpoint: true }` option is accepted by `addTextFromFile()`, `addImage()`, `addImageFromUrl()`, and `addImageFromBuffer()`. Responses-native `input_text`, `input_image`, and `input_file` blocks preserve the native `prompt_cache_breakpoint` field when supplied directly through `options.messages`.
 
-GPT-5.6 uses `prompt_cache_options.ttl`; `prompt_cache_retention` remains available for earlier OpenAI models. ModelMix rejects the incompatible control instead of silently dropping it. For GPT-5.6 requests over 272K input tokens, the cost calculation applies the documented 2× input and 1.5× output multipliers to the complete request, including cache reads and writes.
+GPT-5.6 and GPT-6 use `prompt_cache_options.ttl`; `prompt_cache_retention` remains available for earlier OpenAI models. ModelMix rejects the incompatible control instead of silently dropping it. For GPT-5.6 requests over 272K input tokens, the cost calculation applies the documented 2× input and 1.5× output multipliers to the complete request, including cache reads and writes.
 
 GPT-5.6 prices per 1M tokens:
 
 | Model | Input | Cached input | Cache write | Output |
 | --- | ---: | ---: | ---: | ---: |
-| `gpt-5.6-sol` | $5.00 | $0.50 | $6.25 | $30.00 |
+| `gpt-5.6-sol` | $4.00 | $0.40 | $5.00 | $20.00 |
 | `gpt-5.6-terra` | $2.00 | $0.20 | $2.50 | $12.00 |
 | `gpt-5.6-luna` | $0.20 | $0.02 | $0.25 | $1.20 |
 
+GPT-5.6 Sol's $4.00 input and $20.00 output rates are promotional and available at least through November 21, 2026.
+
 ### Cross-provider cache fallback
 
 Neutral breakpoints are translated at the last moment by each provider adapter. Native request policies remain scoped to their model, so they cannot leak into a fallback request:
@@ -885,7 +890,7 @@ const model = ModelMix.new()
   .addText('Answer this variable request.');
 ```
 
-GPT-5.6 receives `prompt_cache_breakpoint`; Anthropic receives `cache_control`; older OpenAI models and providers without an equivalent omit the marker. When a neutral explicit breakpoint is present for Anthropic, its model-scoped `cache_control` becomes that block's policy instead of adding an automatic breakpoint after the variable suffix.
+GPT-5.6 and GPT-6 receive `prompt_cache_breakpoint`; Anthropic receives `cache_control`; older OpenAI models and providers without an equivalent omit the marker. When a neutral explicit breakpoint is present for Anthropic, its model-scoped `cache_control` becomes that block's policy instead of adding an automatic breakpoint after the variable suffix.
 
 ## 🔧 Model Context Protocol (MCP) Integration
 
@@ -1055,7 +1060,7 @@ Pass `mix` to `benchmark()` to select providers for the criteria model, particip
 
 JSON parsing accepts a Markdown code block or a lone closing triple-backtick delimiter after valid JSON. Other extra content, malformed JSON, and invalid evaluation scores remain errors.
 
-Run `node demo/benchmark.js` for a complete five-model comparison. It allows up to 32,768 output tokens per call, prints intermediate progress, a final ranking and error details, then saves each response as Markdown together with the full JSON report under `demo/results/`.
+Run `node demo/benchmark.js` for a complete model comparison. It allows up to 32,768 output tokens per call, prints intermediate progress, a final ranking and error details, then saves each response as Markdown together with the full JSON report under `demo/results/`.
 
 ### Recursive Language Model plugin
 

package/demo/benchmark.js

@@ -11,16 +11,13 @@ const { benchmark } = benchmarkPlugin;
 const task = await readFile(process.argv[2] || new URL('./prompts/story.txt', import.meta.url), 'utf8');
 
 const models = [
-    // 'opus50@20',
-    'gpt6astra@0',
-    'gpt6astra@20',
+    'gpt6sol@40',
+    'gpt6luna@40',
     'gpt56sol@40',
-    // 'gemini38flash@20',
-    // 'grok46@20',
-    'deepseekV41Flash@60'
+    'gpt56luna@40'
 ];
 
-console.log(`Running benchmark: ${models.length} models, 26 sequential model calls.`);
+console.log(`Running benchmark: ${models.length} models, 17 sequential model calls.`);
 
 const report = await ModelMix.new({
     config: { debug: 1 },

package/demo/package-lock.json

@@ -0,0 +1,516 @@
+{
+  "name": "demo",
+  "version": "1.0.0",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "name": "demo",
+      "version": "1.0.0",
+      "license": "ISC",
+      "dependencies": {
+        "dotenv": "^17.2.3",
+        "isolated-vm": "^6.0.2",
+        "lemonlog": "^1.1.4",
+        "pathmix": "^1.0.0"
+      }
+    },
+    ".api/apis/pplx": {
+      "name": "@api/pplx",
+      "version": "0.1.0",
+      "extraneous": true,
+      "dependencies": {
+        "api": "^6.1.1",
+        "json-schema-to-ts": "^2.8.0-beta.0",
+        "oas": "^20.10.3"
+      }
+    },
+    "node_modules/base64-js": {
+      "version": "1.5.1",
+      "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
+      "integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ],
+      "license": "MIT"
+    },
+    "node_modules/bl": {
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/bl/-/bl-4.1.0.tgz",
+      "integrity": "sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==",
+      "license": "MIT",
+      "dependencies": {
+        "buffer": "^5.5.0",
+        "inherits": "^2.0.4",
+        "readable-stream": "^3.4.0"
+      }
+    },
+    "node_modules/buffer": {
+      "version": "5.7.1",
+      "resolved": "https://registry.npmjs.org/buffer/-/buffer-5.7.1.tgz",
+      "integrity": "sha512-EHcyIPBQ4BSGlvjB16k5KgAJ27CIsHY/2JBmCRReo48y9rQ3MaUzWX3KVlBa4U7MyX02HdVj0K7C3WaB3ju7FQ==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "base64-js": "^1.3.1",
+        "ieee754": "^1.1.13"
+      }
+    },
+    "node_modules/chownr": {
+      "version": "1.1.4",
+      "resolved": "https://registry.npmjs.org/chownr/-/chownr-1.1.4.tgz",
+      "integrity": "sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==",
+      "license": "ISC"
+    },
+    "node_modules/debug": {
+      "version": "4.4.1",
+      "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.1.tgz",
+      "integrity": "sha512-KcKCqiftBJcZr++7ykoDIEwSa3XWowTfNPo92BYxjXiyYEVrUQh2aLyhxBCwww+heortUFxEJYcRzosstTEBYQ==",
+      "license": "MIT",
+      "dependencies": {
+        "ms": "^2.1.3"
+      },
+      "engines": {
+        "node": ">=6.0"
+      },
+      "peerDependenciesMeta": {
+        "supports-color": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/decompress-response": {
+      "version": "6.0.0",
+      "resolved": "https://registry.npmjs.org/decompress-response/-/decompress-response-6.0.0.tgz",
+      "integrity": "sha512-aW35yZM6Bb/4oJlZncMH2LCoZtJXTRxES17vE3hoRiowU2kWHaJKFkSBDnDR+cm9J+9QhXmREyIfv0pji9ejCQ==",
+      "license": "MIT",
+      "dependencies": {
+        "mimic-response": "^3.1.0"
+      },
+      "engines": {
+        "node": ">=10"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
+    "node_modules/deep-extend": {
+      "version": "0.6.0",
+      "resolved": "https://registry.npmjs.org/deep-extend/-/deep-extend-0.6.0.tgz",
+      "integrity": "sha512-LOHxIOaPYdHlJRtCQfDIVZtfw/ufM8+rVj649RIHzcm/vGwQRXFt6OPqIFWsm2XEMrNIEtWR64sY1LEKD2vAOA==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=4.0.0"
+      }
+    },
+    "node_modules/detect-libc": {
+      "version": "2.1.2",
+      "resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.1.2.tgz",
+      "integrity": "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ==",
+      "license": "Apache-2.0",
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/dotenv": {
+      "version": "17.2.3",
+      "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.3.tgz",
+      "integrity": "sha512-JVUnt+DUIzu87TABbhPmNfVdBDt18BLOWjMUFJMSi/Qqg7NTYtabbvSNJGOJ7afbRuv9D/lngizHtP7QyLQ+9w==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=12"
+      },
+      "funding": {
+        "url": "https://dotenvx.com"
+      }
+    },
+    "node_modules/end-of-stream": {
+      "version": "1.4.5",
+      "resolved": "https://registry.npmjs.org/end-of-stream/-/end-of-stream-1.4.5.tgz",
+      "integrity": "sha512-ooEGc6HP26xXq/N+GCGOT0JKCLDGrq2bQUZrQ7gyrJiZANJ/8YDTxTpQBXGMn+WbIQXNVpyWymm7KYVICQnyOg==",
+      "license": "MIT",
+      "dependencies": {
+        "once": "^1.4.0"
+      }
+    },
+    "node_modules/expand-template": {
+      "version": "2.0.3",
+      "resolved": "https://registry.npmjs.org/expand-template/-/expand-template-2.0.3.tgz",
+      "integrity": "sha512-XYfuKMvj4O35f/pOXLObndIRvyQ+/+6AhODh+OKWj9S9498pHHn/IMszH+gt0fBCRWMNfk1ZSp5x3AifmnI2vg==",
+      "license": "(MIT OR WTFPL)",
+      "engines": {
+        "node": ">=6"
+      }
+    },
+    "node_modules/fs-constants": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/fs-constants/-/fs-constants-1.0.0.tgz",
+      "integrity": "sha512-y6OAwoSIf7FyjMIv94u+b5rdheZEjzR63GTyZJm5qh4Bi+2YgwLCcI/fPFZkL5PSixOt6ZNKm+w+Hfp/Bciwow==",
+      "license": "MIT"
+    },
+    "node_modules/github-from-package": {
+      "version": "0.0.0",
+      "resolved": "https://registry.npmjs.org/github-from-package/-/github-from-package-0.0.0.tgz",
+      "integrity": "sha512-SyHy3T1v2NUXn29OsWdxmK6RwHD+vkj3v8en8AOBZ1wBQ/hCAQ5bAQTD02kW4W9tUp/3Qh6J8r9EvntiyCmOOw==",
+      "license": "MIT"
+    },
+    "node_modules/ieee754": {
+      "version": "1.2.1",
+      "resolved": "https://registry.npmjs.org/ieee754/-/ieee754-1.2.1.tgz",
+      "integrity": "sha512-dcyqhDvX1C46lXZcVqCpK+FtMRQVdIMN6/Df5js2zouUsqG7I6sFxitIC+7KYK29KdXOLHdu9zL4sFnoVQnqaA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ],
+      "license": "BSD-3-Clause"
+    },
+    "node_modules/inherits": {
+      "version": "2.0.4",
+      "resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz",
+      "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==",
+      "license": "ISC"
+    },
+    "node_modules/ini": {
+      "version": "1.3.8",
+      "resolved": "https://registry.npmjs.org/ini/-/ini-1.3.8.tgz",
+      "integrity": "sha512-JV/yugV2uzW5iMRSiZAyDtQd+nxtUnjeLt0acNdw98kKLrvuRVyB80tsREOE7yvGVgalhZ6RNXCmEHkUKBKxew==",
+      "license": "ISC"
+    },
+    "node_modules/isolated-vm": {
+      "version": "6.0.2",
+      "resolved": "https://registry.npmjs.org/isolated-vm/-/isolated-vm-6.0.2.tgz",
+      "integrity": "sha512-Qw6AJuagG/VJuh2AIcSWmQPsAArti/L+lKhjXU+lyhYkbt3J57XZr+ZjgfTnOr4NJcY1r3f8f0eePS7MRGp+pg==",
+      "hasInstallScript": true,
+      "license": "ISC",
+      "dependencies": {
+        "prebuild-install": "^7.1.3"
+      },
+      "engines": {
+        "node": ">=22.0.0"
+      }
+    },
+    "node_modules/lemonlog": {
+      "version": "1.1.4",
+      "resolved": "https://registry.npmjs.org/lemonlog/-/lemonlog-1.1.4.tgz",
+      "integrity": "sha512-NWcXK7Nl+K5E0xxzcux9ktR9hiRSSjK0xpFbuAm/qy/wg5TuIYGfg+lIDWthVvFscrSsYCPLyPk/AvxY+w7n6A==",
+      "license": "MIT",
+      "dependencies": {
+        "debug": "^4.1.1"
+      }
+    },
+    "node_modules/mimic-response": {
+      "version": "3.1.0",
+      "resolved": "https://registry.npmjs.org/mimic-response/-/mimic-response-3.1.0.tgz",
+      "integrity": "sha512-z0yWI+4FDrrweS8Zmt4Ej5HdJmky15+L2e6Wgn3+iK5fWzb6T3fhNFq2+MeTRb064c6Wr4N/wv0DzQTjNzHNGQ==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=10"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
+    "node_modules/minimist": {
+      "version": "1.2.8",
+      "resolved": "https://registry.npmjs.org/minimist/-/minimist-1.2.8.tgz",
+      "integrity": "sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==",
+      "license": "MIT",
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/mkdirp-classic": {
+      "version": "0.5.3",
+      "resolved": "https://registry.npmjs.org/mkdirp-classic/-/mkdirp-classic-0.5.3.tgz",
+      "integrity": "sha512-gKLcREMhtuZRwRAfqP3RFW+TK4JqApVBtOIftVgjuABpAtpxhPGaDcfvbhNvD0B8iD1oUr/txX35NjcaY6Ns/A==",
+      "license": "MIT"
+    },
+    "node_modules/ms": {
+      "version": "2.1.3",
+      "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
+      "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="
+    },
+    "node_modules/napi-build-utils": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/napi-build-utils/-/napi-build-utils-2.0.0.tgz",
+      "integrity": "sha512-GEbrYkbfF7MoNaoh2iGG84Mnf/WZfB0GdGEsM8wz7Expx/LlWf5U8t9nvJKXSp3qr5IsEbK04cBGhol/KwOsWA==",
+      "license": "MIT"
+    },
+    "node_modules/node-abi": {
+      "version": "3.85.0",
+      "resolved": "https://registry.npmjs.org/node-abi/-/node-abi-3.85.0.tgz",
+      "integrity": "sha512-zsFhmbkAzwhTft6nd3VxcG0cvJsT70rL+BIGHWVq5fi6MwGrHwzqKaxXE+Hl2GmnGItnDKPPkO5/LQqjVkIdFg==",
+      "license": "MIT",
+      "dependencies": {
+        "semver": "^7.3.5"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/once": {
+      "version": "1.4.0",
+      "resolved": "https://registry.npmjs.org/once/-/once-1.4.0.tgz",
+      "integrity": "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w==",
+      "license": "ISC",
+      "dependencies": {
+        "wrappy": "1"
+      }
+    },
+    "node_modules/pathmix": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/pathmix/-/pathmix-1.0.0.tgz",
+      "integrity": "sha512-oLbvoOKuyV6TjkKLEYqH5O+q+d+qZwtRNzMrBI93IsCYN0liDw8W8aZq3BPvIaF4jJU+igeO/1p6lCwFfy8E5Q==",
+      "license": "ISC",
+      "engines": {
+        "node": ">=16.0.0"
+      }
+    },
+    "node_modules/prebuild-install": {
+      "version": "7.1.3",
+      "resolved": "https://registry.npmjs.org/prebuild-install/-/prebuild-install-7.1.3.tgz",
+      "integrity": "sha512-8Mf2cbV7x1cXPUILADGI3wuhfqWvtiLA1iclTDbFRZkgRQS0NqsPZphna9V+HyTEadheuPmjaJMsbzKQFOzLug==",
+      "license": "MIT",
+      "dependencies": {
+        "detect-libc": "^2.0.0",
+        "expand-template": "^2.0.3",
+        "github-from-package": "0.0.0",
+        "minimist": "^1.2.3",
+        "mkdirp-classic": "^0.5.3",
+        "napi-build-utils": "^2.0.0",
+        "node-abi": "^3.3.0",
+        "pump": "^3.0.0",
+        "rc": "^1.2.7",
+        "simple-get": "^4.0.0",
+        "tar-fs": "^2.0.0",
+        "tunnel-agent": "^0.6.0"
+      },
+      "bin": {
+        "prebuild-install": "bin.js"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/pump": {
+      "version": "3.0.3",
+      "resolved": "https://registry.npmjs.org/pump/-/pump-3.0.3.tgz",
+      "integrity": "sha512-todwxLMY7/heScKmntwQG8CXVkWUOdYxIvY2s0VWAAMh/nd8SoYiRaKjlr7+iCs984f2P8zvrfWcDDYVb73NfA==",
+      "license": "MIT",
+      "dependencies": {
+        "end-of-stream": "^1.1.0",
+        "once": "^1.3.1"
+      }
+    },
+    "node_modules/rc": {
+      "version": "1.2.8",
+      "resolved": "https://registry.npmjs.org/rc/-/rc-1.2.8.tgz",
+      "integrity": "sha512-y3bGgqKj3QBdxLbLkomlohkvsA8gdAiUQlSBJnBhfn+BPxg4bc62d8TcBW15wavDfgexCgccckhcZvywyQYPOw==",
+      "license": "(BSD-2-Clause OR MIT OR Apache-2.0)",
+      "dependencies": {
+        "deep-extend": "^0.6.0",
+        "ini": "~1.3.0",
+        "minimist": "^1.2.0",
+        "strip-json-comments": "~2.0.1"
+      },
+      "bin": {
+        "rc": "cli.js"
+      }
+    },
+    "node_modules/readable-stream": {
+      "version": "3.6.2",
+      "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-3.6.2.tgz",
+      "integrity": "sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA==",
+      "license": "MIT",
+      "dependencies": {
+        "inherits": "^2.0.3",
+        "string_decoder": "^1.1.1",
+        "util-deprecate": "^1.0.1"
+      },
+      "engines": {
+        "node": ">= 6"
+      }
+    },
+    "node_modules/safe-buffer": {
+      "version": "5.2.1",
+      "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.2.1.tgz",
+      "integrity": "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ],
+      "license": "MIT"
+    },
+    "node_modules/semver": {
+      "version": "7.7.3",
+      "resolved": "https://registry.npmjs.org/semver/-/semver-7.7.3.tgz",
+      "integrity": "sha512-SdsKMrI9TdgjdweUSR9MweHA4EJ8YxHn8DFaDisvhVlUOe4BF1tLD7GAj0lIqWVl+dPb/rExr0Btby5loQm20Q==",
+      "license": "ISC",
+      "bin": {
+        "semver": "bin/semver.js"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/simple-concat": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/simple-concat/-/simple-concat-1.0.1.tgz",
+      "integrity": "sha512-cSFtAPtRhljv69IK0hTVZQ+OfE9nePi/rtJmw5UjHeVyVroEqJXP1sFztKUy1qU+xvz3u/sfYJLa947b7nAN2Q==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ],
+      "license": "MIT"
+    },
+    "node_modules/simple-get": {
+      "version": "4.0.1",
+      "resolved": "https://registry.npmjs.org/simple-get/-/simple-get-4.0.1.tgz",
+      "integrity": "sha512-brv7p5WgH0jmQJr1ZDDfKDOSeWWg+OVypG99A/5vYGPqJ6pxiaHLy8nxtFjBA7oMa01ebA9gfh1uMCFqOuXxvA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "decompress-response": "^6.0.0",
+        "once": "^1.3.1",
+        "simple-concat": "^1.0.0"
+      }
+    },
+    "node_modules/string_decoder": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.3.0.tgz",
+      "integrity": "sha512-hkRX8U1WjJFd8LsDJ2yQ/wWWxaopEsABU1XfkM8A+j0+85JAGppt16cr1Whg6KIbb4okU6Mql6BOj+uup/wKeA==",
+      "license": "MIT",
+      "dependencies": {
+        "safe-buffer": "~5.2.0"
+      }
+    },
+    "node_modules/strip-json-comments": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/strip-json-comments/-/strip-json-comments-2.0.1.tgz",
+      "integrity": "sha512-4gB8na07fecVVkOI6Rs4e7T6NOTki5EmL7TUduTs6bu3EdnSycntVJ4re8kgZA+wx9IueI2Y11bfbgwtzuE0KQ==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
+    "node_modules/tar-fs": {
+      "version": "2.1.4",
+      "resolved": "https://registry.npmjs.org/tar-fs/-/tar-fs-2.1.4.tgz",
+      "integrity": "sha512-mDAjwmZdh7LTT6pNleZ05Yt65HC3E+NiQzl672vQG38jIrehtJk/J3mNwIg+vShQPcLF/LV7CMnDW6vjj6sfYQ==",
+      "license": "MIT",
+      "dependencies": {
+        "chownr": "^1.1.1",
+        "mkdirp-classic": "^0.5.2",
+        "pump": "^3.0.0",
+        "tar-stream": "^2.1.4"
+      }
+    },
+    "node_modules/tar-stream": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/tar-stream/-/tar-stream-2.2.0.tgz",
+      "integrity": "sha512-ujeqbceABgwMZxEJnk2HDY2DlnUZ+9oEcb1KzTVfYHio0UE6dG71n60d8D2I4qNvleWrrXpmjpt7vZeF1LnMZQ==",
+      "license": "MIT",
+      "dependencies": {
+        "bl": "^4.0.3",
+        "end-of-stream": "^1.4.1",
+        "fs-constants": "^1.0.0",
+        "inherits": "^2.0.3",
+        "readable-stream": "^3.1.1"
+      },
+      "engines": {
+        "node": ">=6"
+      }
+    },
+    "node_modules/tunnel-agent": {
+      "version": "0.6.0",
+      "resolved": "https://registry.npmjs.org/tunnel-agent/-/tunnel-agent-0.6.0.tgz",
+      "integrity": "sha512-McnNiV1l8RYeY8tBgEpuodCC1mLUdbSN+CYBL7kJsJNInOP8UjDDEwdk6Mw60vdLLrr5NHKZhMAOSrR2NZuQ+w==",
+      "license": "Apache-2.0",
+      "dependencies": {
+        "safe-buffer": "^5.0.1"
+      },
+      "engines": {
+        "node": "*"
+      }
+    },
+    "node_modules/util-deprecate": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz",
+      "integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==",
+      "license": "MIT"
+    },
+    "node_modules/wrappy": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz",
+      "integrity": "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==",
+      "license": "ISC"
+    }
+  }
+}

package/effort.js

@@ -43,6 +43,8 @@ const GLM53_BANDS = [
 /** Exact model → supported OpenAI reasoning_effort values */
 const OPENAI_MODEL_LEVELS = {
     'gpt-6-astra': ['low', 'medium', 'high', 'xhigh', 'max'],
+    'gpt-6-sol': ['none', 'low', 'medium', 'high', 'xhigh', 'max'],
+    'gpt-6-luna': ['none', 'low', 'medium', 'high', 'xhigh', 'max'],
     'gpt-5.6-sol': ['none', 'low', 'medium', 'high', 'xhigh', 'max'],
     'gpt-5.6-terra': ['none', 'low', 'medium', 'high', 'xhigh', 'max'],
     'gpt-5.6-luna': ['none', 'low', 'medium', 'high', 'xhigh', 'max'],

package/index.d.ts

@@ -457,6 +457,8 @@ export declare class ModelMix {
   gpt55(args?: ModelAttachArgs): this;
   gpt55pro(args?: ModelAttachArgs): this;
   gpt6astra(args?: ModelAttachArgs): this;
+  gpt6sol(args?: ModelAttachArgs): this;
+  gpt6luna(args?: ModelAttachArgs): this;
   gpt56sol(args?: ModelAttachArgs): this;
   gpt56terra(args?: ModelAttachArgs): this;
   gpt56luna(args?: ModelAttachArgs): this;

package/index.js

@@ -499,6 +499,12 @@ class ModelMix {
     gpt6astra(args = {}) {
         return this._attachOpenAIWithOpenRouter('gpt-6-astra', MixOpenAIResponses, args);
     }
+    gpt6sol(args = {}) {
+        return this._attachOpenAIWithOpenRouter('gpt-6-sol', MixOpenAIResponses, args);
+    }
+    gpt6luna(args = {}) {
+        return this._attachOpenAIWithOpenRouter('gpt-6-luna', MixOpenAIResponses, args);
+    }
     gpt56sol(args = {}) {
         return this._attachOpenAIWithOpenRouter('gpt-5.6-sol', MixOpenAIResponses, args);
     }

package/lib/model-chain.js

@@ -3,7 +3,7 @@ const { normalizeEffort } = require('../effort');
 const CHAIN_MODEL_SHORTCUTS = new Set([
     'gpt5', 'gpt5mini', 'gpt5nano',
     'gpt51', 'gpt52', 'gpt54', 'gpt54mini', 'gpt54nano', 'gpt54pro',
-    'gpt6astra', 'gpt55', 'gpt55pro', 'gpt56sol', 'gpt56terra', 'gpt56luna',
+    'gpt6astra', 'gpt6sol', 'gpt6luna', 'gpt55', 'gpt55pro', 'gpt56sol', 'gpt56terra', 'gpt56luna',
     'gptRealtime', 'gptRealtimeMini', 'gpt53codex', 'gpt53chat', 'gptOss',
     'fable51', 'fable50', 'fable5', 'opus55', 'opus50', 'opus5', 'opus48', 'opus47', 'opus46',
     'sonnet50', 'sonnet5', 'sonnet46', 'sonnet45', 'haiku45',

package/lib/providers/openai-options.js

@@ -3,7 +3,7 @@ function normalizeOpenAIOptions(options) {
         delete options.max_tokens;
         delete options.temperature;
     }
-    if (options.model?.includes('gpt-5') || /^(?:openai\/)?gpt-6-astra(?:-|$)/.test(options.model || '')) {
+    if (options.model?.includes('gpt-5') || /^(?:openai\/)?gpt-6(?:-|$)/.test(options.model || '')) {
         if (options.max_tokens) {
             options.max_completion_tokens = options.max_tokens;
             delete options.max_tokens;

package/lib/providers/openai.js

@@ -11,6 +11,12 @@ const {
     validateProviderExecution
 } = require('../abort-signal');
 
+/** Explicit prompt cache controls belong to the documented "GPT-5.6 and later" family. */
+function isGPT56OrLater(model) {
+    if (typeof model !== 'string') return false;
+    return model.startsWith('gpt-5.6') || /^(?:openai\/)?gpt-6(?:-|$)/.test(model);
+}
+
 function createOpenAIProviders({
     ModelMix,
     MixCustom,
@@ -38,9 +44,8 @@ function createOpenAIProviders({
         }
     
         static buildResponsesRequest(options = {}, config = {}) {
-            const isGPT56 = typeof options.model === 'string' && options.model.startsWith('gpt-5.6');
             const input = MixOpenAIResponses.messagesToResponsesInput(options.messages, {
-                translateNeutralCache: isGPT56
+                translateNeutralCache: isGPT56OrLater(options.model)
             });
             if (config.system) {
                 input.unshift({ role: 'developer', content: [{ type: 'input_text', text: config.system }] });
@@ -106,7 +111,7 @@ function createOpenAIProviders({
         }
     
         static validatePromptCaching(options, input) {
-            const isGPT56 = typeof options.model === 'string' && options.model.startsWith('gpt-5.6');
+            const supportsCacheControls = isGPT56OrLater(options.model);
             const cacheOptions = options.prompt_cache_options;
             const breakpoints = input.flatMap(message => Array.isArray(message.content)
                 ? message.content
@@ -114,14 +119,14 @@ function createOpenAIProviders({
                     .map(block => block.prompt_cache_breakpoint)
                 : []);
     
-            if (isGPT56 && options.prompt_cache_retention !== undefined) {
-                throw new Error('GPT-5.6 does not support prompt_cache_retention; use prompt_cache_options.ttl instead.');
+            if (supportsCacheControls && options.prompt_cache_retention !== undefined) {
+                throw new Error('GPT-5.6 and later models do not support prompt_cache_retention; use prompt_cache_options.ttl instead.');
             }
-            if (!isGPT56 && cacheOptions !== undefined) {
-                throw new Error('prompt_cache_options is only supported by GPT-5.6 models.');
+            if (!supportsCacheControls && cacheOptions !== undefined) {
+                throw new Error('prompt_cache_options is only supported by GPT-5.6 and later models.');
             }
-            if (!isGPT56 && breakpoints.length > 0) {
-                throw new Error('prompt_cache_breakpoint is only supported by GPT-5.6 models.');
+            if (!supportsCacheControls && breakpoints.length > 0) {
+                throw new Error('prompt_cache_breakpoint is only supported by GPT-5.6 and later models.');
             }
             if (cacheOptions !== undefined) {
                 if (!isPlainObject(cacheOptions)) {

package/lib/token-usage.js

@@ -22,9 +22,11 @@ function usesLongContextRates(pricing, inputTokens) {
 const MODEL_PRICING = {
     // OpenAI
     'gpt-6-astra': { input: 10.00, cachedInput: 1.00, cacheWrite: 12.50, output: 50.00, longContext: OPENAI_LONG_CONTEXT_PRICING },
+    'gpt-6-sol': { input: 2.00, cachedInput: 0.20, cacheWrite: 2.50, output: 10.00, longContext: OPENAI_LONG_CONTEXT_PRICING },
+    'gpt-6-luna': { input: 0.10, cachedInput: 0.01, cacheWrite: 0.125, output: 0.50, longContext: OPENAI_LONG_CONTEXT_PRICING },
     'gpt-realtime-mini': { input: 0.60, cachedInput: 0.06, output: 2.40 },
     'gpt-realtime': { input: 4.00, cachedInput: 0.40, output: 16.00 },
-    'gpt-5.6-sol': { input: 5.00, cachedInput: 0.50, cacheWrite: 6.25, output: 30.00, longContext: OPENAI_LONG_CONTEXT_PRICING },
+    'gpt-5.6-sol': { input: 4.00, cachedInput: 0.40, cacheWrite: 5.00, output: 20.00, longContext: OPENAI_LONG_CONTEXT_PRICING },
     'gpt-5.6-terra': { input: 2.00, cachedInput: 0.20, cacheWrite: 2.50, output: 12.00, longContext: OPENAI_LONG_CONTEXT_PRICING },
     'gpt-5.6-luna': { input: 0.20, cachedInput: 0.02, cacheWrite: 0.25, output: 1.20, longContext: OPENAI_LONG_CONTEXT_PRICING },
     'gpt-5.5-pro': { input: 30.00, output: 180.00 },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "modelmix",
-  "version": "5.2.3",
+  "version": "5.3.0",
   "description": "🧬 Reliable interface with automatic fallback for AI LLMs.",
   "main": "index.js",
   "types": "index.d.ts",
@@ -82,5 +82,6 @@
     "test:benchmark": "mocha plugins/benchmark/test/**/*.test.js --timeout 10000 --require test/setup.js",
     "test:rlm": "mocha plugins/rlm/test/**/*.test.js --timeout 10000 --require test/setup.js",
     "test:offline": "mocha test/abort.test.js test/json.test.js test/fallback.test.js test/templates.test.js test/images.test.js test/bottleneck.test.js test/tokens.test.js test/history.test.js test/anthropic.test.js test/effort.test.js test/grok.test.js test/google.test.js test/moderation.test.js test/plugins.test.js plugins/skills/test/**/*.test.js plugins/benchmark/test/**/*.test.js plugins/rlm/test/**/*.test.js --timeout 10000 --require test/setup.js"
-  }
-}
+  },
+  "packageManager": "pnpm@12.4.1"
+}

package/skills/modelmix/SKILL.md

@@ -164,7 +164,7 @@ ModelMix.new({ config: { effort: 80 } })
 | DeepSeek V4 | off | `low`↑ | `high`↑ | `high`↑ | `max`↑ | — |
 | MiniMax M3 | off | adaptive | adaptive | adaptive | adaptive | adaptive |
 
-\* GPT-6 Astra maps 0–39 / 40–59 / 60–79 / 80–99 / 100 to `low` / `medium` / `high` / `xhigh` / `max`. GPT-5.6 maps `100` to `max`; 80–99 remains `xhigh`. Qwen 3.8 27B and Flash map 0–39 / 40–79 / 80–100 to `low` / `medium` / `xhigh`; Qwen 3.8 Flash is the managed production version based on Flash-Next. GLM 5.3 and GLM 5.3 Flash require reasoning and map those bands to `low` / `high` / `max`. Gemini bands: 0–24 / 25–49 / 50–74 / 75–100. Gemini 3.8 Flash and 3.7 Flash support only `low` / `medium` / `high`, so the first two bands clamp to `low`; `-1` keeps their native `medium` default. DeepSeek `↑` = thinking on; `off` = thinking disabled. MiniMax `off`/`adaptive` = `thinking.disabled` / `thinking.type=adaptive`. Gemini 2.5 maps 0–100 to `thinkingBudget`. Anthropic: adaptive + `output_config.effort` on Claude 5 / Fable / Opus 4.6+ / Sonnet 4.6+; Sonnet 4.5 / Haiku 4.5 use `thinking.type=enabled` + `budget_tokens`. Grok 4.6 maps 0–39 / 40–59 / 60–79 / 80–100 to `low` / `medium` / `high` / `xhigh`; without effort it uses native `high`. `-1` = adaptive/dynamic when available, else no-op. Levels clamp per model. Former `*think()` methods are removed — use `.effort(n).<model>()`. Kimi: `kimiK25()` / `kimiK26()`. Grok 4.20: `.grok420()` non-reasoning; `.effort(20+|-1).grok420()` selects reasoning.
+\* GPT-6 Astra maps 0–39 / 40–59 / 60–79 / 80–99 / 100 to `low` / `medium` / `high` / `xhigh` / `max`. GPT-6 Sol, GPT-6 Luna, and GPT-5.6 map `100` to `max` and keep `xhigh` for 80–99, with OpenAI's `none` band at 0–19. Qwen 3.8 27B and Flash map 0–39 / 40–79 / 80–100 to `low` / `medium` / `xhigh`; Qwen 3.8 Flash is the managed production version based on Flash-Next. GLM 5.3 and GLM 5.3 Flash require reasoning and map those bands to `low` / `high` / `max`. Gemini bands: 0–24 / 25–49 / 50–74 / 75–100. Gemini 3.8 Flash and 3.7 Flash support only `low` / `medium` / `high`, so the first two bands clamp to `low`; `-1` keeps their native `medium` default. DeepSeek `↑` = thinking on; `off` = thinking disabled. MiniMax `off`/`adaptive` = `thinking.disabled` / `thinking.type=adaptive`. Gemini 2.5 maps 0–100 to `thinkingBudget`. Anthropic: adaptive + `output_config.effort` on Claude 5 / Fable / Opus 4.6+ / Sonnet 4.6+; Sonnet 4.5 / Haiku 4.5 use `thinking.type=enabled` + `budget_tokens`. Grok 4.6 maps 0–39 / 40–59 / 60–79 / 80–100 to `low` / `medium` / `high` / `xhigh`; without effort it uses native `high`. `-1` = adaptive/dynamic when available, else no-op. Levels clamp per model. Former `*think()` methods are removed — use `.effort(n).<model>()`. Kimi: `kimiK25()` / `kimiK26()`. Grok 4.20: `.grok420()` non-reasoning; `.effort(20+|-1).grok420()` selects reasoning.
 
 ## Available Model Shorthands
 
@@ -172,7 +172,7 @@ ModelMix.new({ config: { effort: 80 } })
 
 Use `ModerationMix.new().openai()` with `.raw()` to classify text and images through OpenAI's Moderations endpoint. Read the results from `raw.moderation`. `ModerationMix` accepts moderation providers as ordered fallbacks, rejects generative providers, and does not generate text or support streaming.
 
-`gpt6astra()` `gpt56sol()` `gpt56terra()` `gpt56luna()` `gpt55()` `gpt55pro()` `gpt54()` `gpt54mini()` `gpt54nano()` `gpt54pro()` `gpt53codex()` `gpt53chat()` `gpt52()` `gpt51()` `gpt5()` `gpt5mini()` `gpt5nano()` `gptRealtime()` `gptRealtimeMini()` `gptOss()`
+`gpt6astra()` `gpt6sol()` `gpt6luna()` `gpt56sol()` `gpt56terra()` `gpt56luna()` `gpt55()` `gpt55pro()` `gpt54()` `gpt54mini()` `gpt54nano()` `gpt54pro()` `gpt53codex()` `gpt53chat()` `gpt52()` `gpt51()` `gpt5()` `gpt5mini()` `gpt5nano()` `gptRealtime()` `gptRealtimeMini()` `gptOss()`
 
 Every textual GPT-5 and GPT-6 shortcut registers only the official OpenAI model by default. Pass `mix: { openrouter: true }` to `ModelMix.new()` or to an individual shortcut to append its `openai/*` OpenRouter route as a fallback. `gpt53chat()` uses `gpt-5.3-chat-latest` officially and `openai/gpt-5.3-chat` through OpenRouter. Both API keys are required when that fallback is enabled. Realtime shortcuts remain official-only.
 
@@ -411,7 +411,7 @@ console.log(model.lastRaw.think);    // reasoning content (if available)
 console.log(model.lastRaw.response); // raw API response
 ```
 
-### GPT-5.6 explicit prompt caching
+### GPT-5.6 and GPT-6 explicit prompt caching
 
 ```javascript
 const model = ModelMix.new()
@@ -434,9 +434,9 @@ const model = ModelMix.new()
 const result = await model.raw();
 ```
 
-`cache: { breakpoint: true }` is provider-neutral: GPT-5.6 receives `prompt_cache_breakpoint`, Anthropic receives `cache_control`, and unsupported providers omit it. Keep native request policies inside each model shorthand so they do not leak across fallbacks. Anthropic usage separates `cacheWrite5m` and `cacheWrite1h`; `cacheWrite` stays as their compatible aggregate.
+`cache: { breakpoint: true }` is provider-neutral: GPT-5.6 and GPT-6 receive `prompt_cache_breakpoint`, Anthropic receives `cache_control`, and unsupported providers omit it. Keep native request policies inside each model shorthand so they do not leak across fallbacks. Anthropic usage separates `cacheWrite5m` and `cacheWrite1h`; `cacheWrite` stays as their compatible aggregate.
 
-GPT-5.6 replaces `prompt_cache_retention` with `prompt_cache_options.ttl`. Explicit breakpoints also work on image methods and Responses-native `input_text`, `input_image`, and `input_file` blocks. Prompts need at least 1,024 tokens to be cached. Requests over 272K input tokens use 2× input and 1.5× output prices for the complete request; ModelMix applies these multipliers to `cost`, `costBreakdown`, and cache economics.
+GPT-5.6 and GPT-6 replace `prompt_cache_retention` with `prompt_cache_options.ttl`. Explicit breakpoints also work on image methods and Responses-native `input_text`, `input_image`, and `input_file` blocks. Prompts need at least 1,024 tokens to be cached. Requests over 272K input tokens use 2× input and 1.5× output prices for the complete request; ModelMix applies these multipliers to `cost`, `costBreakdown`, and cache economics.
 
 ### Add images
 

package/test/effort.test.js

@@ -90,6 +90,15 @@ describe('Unified effort scale', () => {
             }
         });
 
+        it('maps GPT-6 Sol and Luna effort from none to max', () => {
+            for (const model of ['gpt-6-sol', 'gpt-6-luna']) {
+                for (const [effort, level] of [[0, 'none'], [20, 'low'], [40, 'medium'], [60, 'high'], [99, 'xhigh'], [100, 'max']]) {
+                    expect(mapEffort('openai', effort, model)).to.deep.equal({ reasoning_effort: level });
+                }
+                expect(mapEffort('openai', 100, `openai/${model}`)).to.deep.equal({ reasoning_effort: 'max' });
+            }
+        });
+
         it('sets OpenAI adaptive only when supported (otherwise no-op)', () => {
             expect(mapEffort('openai', -1)).to.equal(null);
             expect(mapEffort('openai', -1, 'gpt-5.2')).to.equal(null);

package/test/fallback.test.js

@@ -115,6 +115,8 @@ describe('Provider Fallback Chain Tests', () => {
             expect(ModelMix.new().mix.openrouter).to.equal(false);
             const shortcuts = [
                 ['gpt6astra', 'gpt-6-astra', 'openai/gpt-6-astra', MixOpenAIResponses],
+                ['gpt6sol', 'gpt-6-sol', 'openai/gpt-6-sol', MixOpenAIResponses],
+                ['gpt6luna', 'gpt-6-luna', 'openai/gpt-6-luna', MixOpenAIResponses],
                 ['gpt5', 'gpt-5', 'openai/gpt-5', MixOpenAI],
                 ['gpt5mini', 'gpt-5-mini', 'openai/gpt-5-mini', MixOpenAI],
                 ['gpt5nano', 'gpt-5-nano', 'openai/gpt-5-nano', MixOpenAI],
@@ -232,6 +234,48 @@ describe('Provider Fallback Chain Tests', () => {
             expect(openRouterRequest).to.not.have.property('temperature');
         });
 
+        it('should fallback from the official GPT-6 Sol and Luna endpoints to OpenRouter', async () => {
+            const cases = [
+                ['gpt6sol', 'gpt-6-sol', 'Hello from GPT-6 Sol through OpenRouter!'],
+                ['gpt6luna', 'gpt-6-luna', 'Hello from GPT-6 Luna through OpenRouter!']
+            ];
+
+            for (const [shortcut, officialKey, content] of cases) {
+                let openRouterRequest;
+                const instance = ModelMix.new().effort(100);
+                instance[shortcut]({ mix: { openrouter: true } }).addText('Hello');
+
+                nock('https://api.openai.com')
+                    .post('/v1/responses', body => {
+                        expect(body.model).to.equal(officialKey);
+                        expect(body.reasoning).to.deep.equal({ effort: 'max' });
+                        expect(body.max_output_tokens).to.equal(8192);
+                        expect(body).to.not.have.property('temperature');
+                        return true;
+                    })
+                    .reply(503, { error: 'Service unavailable' });
+
+                nock('https://openrouter.ai')
+                    .post('/api/v1/chat/completions', body => {
+                        openRouterRequest = body;
+                        return true;
+                    })
+                    .reply(200, {
+                        choices: [{
+                            message: {
+                                role: 'assistant',
+                                content
+                            }
+                        }]
+                    });
+
+                expect(await instance.message()).to.equal(content);
+                expect(openRouterRequest.model).to.equal(`openai/${officialKey}`);
+                expect(openRouterRequest.max_completion_tokens).to.equal(8192);
+                expect(openRouterRequest).to.not.have.property('temperature');
+            }
+        });
+
         it('should keep the default fable51 chain on Anthropic', () => {
             model.chain('fable51@80');
 

package/test/tokens.test.js

@@ -252,29 +252,35 @@ describe('Token Usage Tracking', () => {
         ]);
     });
 
-    it('should translate neutral cache breakpoints for GPT-5.6 and filter them for older models', async function () {
+    it('should translate neutral cache breakpoints for GPT-5.6 and GPT-6 and filter them for older models', async function () {
         const breakpoint = { mode: 'explicit' };
         const model = ModelMix.new()
             .addText('Stable text', { role: 'developer', cache: { breakpoint: true } })
             .addImageFromUrl('data:image/png;base64,AAAA', { cache: { breakpoint: true } });
         const messages = await model.prepareMessages();
-        const gpt56Request = MixOpenAIResponses.buildResponsesRequest({
-            model: 'gpt-5.6-luna',
-            messages,
-            prompt_cache_options: { mode: 'explicit', ttl: '30m' }
-        });
-        const olderRequest = MixOpenAIResponses.buildResponsesRequest({
-            model: 'gpt-5.4',
-            messages
-        });
 
         expect(messages[0].content[0]).to.deep.include({ cache: { breakpoint: true } });
         expect(messages[0].content[0]).to.not.have.property('prompt_cache_breakpoint');
-        expect(gpt56Request.input[0].content[0].prompt_cache_breakpoint).to.deep.equal(breakpoint);
-        expect(gpt56Request.input[1].content[0]).to.deep.equal({
-            type: 'input_image',
-            image_url: 'data:image/png;base64,AAAA',
-            prompt_cache_breakpoint: breakpoint
+
+        for (const key of ['gpt-5.6-luna', 'gpt-6-astra', 'gpt-6-sol', 'gpt-6-luna']) {
+            const request = MixOpenAIResponses.buildResponsesRequest({
+                model: key,
+                messages,
+                prompt_cache_options: { mode: 'explicit', ttl: '30m' }
+            });
+
+            expect(request.prompt_cache_options).to.deep.equal({ mode: 'explicit', ttl: '30m' });
+            expect(request.input[0].content[0].prompt_cache_breakpoint).to.deep.equal(breakpoint);
+            expect(request.input[1].content[0]).to.deep.equal({
+                type: 'input_image',
+                image_url: 'data:image/png;base64,AAAA',
+                prompt_cache_breakpoint: breakpoint
+            });
+        }
+
+        const olderRequest = MixOpenAIResponses.buildResponsesRequest({
+            model: 'gpt-5.4',
+            messages
         });
         expect(olderRequest.input[0].content[0]).to.not.have.property('cache');
         expect(olderRequest.input[0].content[0]).to.not.have.property('prompt_cache_breakpoint');
@@ -347,6 +353,12 @@ describe('Token Usage Tracking', () => {
             prompt_cache_retention: '24h'
         })).to.throw('prompt_cache_options.ttl');
 
+        expect(() => MixOpenAIResponses.buildResponsesRequest({
+            model: 'gpt-6-sol',
+            messages: [{ role: 'user', content: 'Hi' }],
+            prompt_cache_retention: '24h'
+        })).to.throw('prompt_cache_options.ttl');
+
         expect(() => MixOpenAIResponses.buildResponsesRequest({
             model: 'gpt-5.4',
             messages: [{ role: 'user', content: 'Hi' }],
@@ -417,6 +429,35 @@ describe('Token Usage Tracking', () => {
         }
     });
 
+    it('should register GPT-6 Sol and Luna shortcuts with OpenAI Responses provider', function () {
+        const model = ModelMix.new({ mix: { openrouter: true } })
+            .gpt6sol()
+            .gpt6luna();
+
+        expect(model.models.map(({ key }) => key)).to.deep.equal([
+            'gpt-6-sol',
+            'openai/gpt-6-sol',
+            'gpt-6-luna',
+            'openai/gpt-6-luna'
+        ]);
+        expect(model.models[0].provider).to.be.instanceOf(MixOpenAIResponses);
+        expect(model.models[1].provider).to.be.instanceOf(MixOpenRouter);
+        expect(model.models[2].provider).to.be.instanceOf(MixOpenAIResponses);
+        expect(model.models[3].provider).to.be.instanceOf(MixOpenRouter);
+    });
+
+    it('should account for GPT-6 Sol and Luna cache usage and the long-context boundary', function () {
+        const tokens = { input: 272_000, cached: 100_000, cacheWrite: 20_000, output: 1_000 };
+        for (const key of ['gpt-6-sol', 'openai/gpt-6-sol']) {
+            expect(ModelMix.calculateCost(key, tokens)).to.be.closeTo(0.384, 1e-10);
+            expect(ModelMix.calculateCost(key, { ...tokens, input: 272_001 })).to.be.closeTo(0.763004, 1e-10);
+        }
+        for (const key of ['gpt-6-luna', 'openai/gpt-6-luna']) {
+            expect(ModelMix.calculateCost(key, tokens)).to.be.closeTo(0.0192, 1e-10);
+            expect(ModelMix.calculateCost(key, { ...tokens, input: 272_001 })).to.be.closeTo(0.0381502, 1e-10);
+        }
+    });
+
     it('should register GPT-5.6 shortcuts with OpenAI Responses provider', function () {
         const model = ModelMix.new({ mix: { openrouter: true } })
             .gpt56sol()
@@ -437,8 +478,8 @@ describe('Token Usage Tracking', () => {
         expect(model.models[3].provider).to.be.instanceOf(MixOpenRouter);
         expect(model.models[4].provider).to.be.instanceOf(MixOpenAIResponses);
         expect(model.models[5].provider).to.be.instanceOf(MixOpenRouter);
-        expect(ModelMix.calculateCost('gpt-5.6-sol', { input: 1_000_000, output: 1_000_000 })).to.equal(55);
-        expect(ModelMix.calculateCost('openai/gpt-5.6-sol', { input: 1_000_000, output: 1_000_000 })).to.equal(55);
+        expect(ModelMix.calculateCost('gpt-5.6-sol', { input: 1_000_000, output: 1_000_000 })).to.equal(38);
+        expect(ModelMix.calculateCost('openai/gpt-5.6-sol', { input: 1_000_000, output: 1_000_000 })).to.equal(38);
         expect(ModelMix.calculateCost('gpt-5.6-terra', { input: 1_000_000, output: 1_000_000 })).to.equal(22);
         expect(ModelMix.calculateCost('gpt-5.6-luna', { input: 1_000_000, output: 1_000_000 })).to.equal(2.2);
         expect(ModelMix.calculateCost('openai/gpt-5.3-chat', { input: 1_000_000, output: 1_000_000 })).to.equal(15.75);

package/.gitignore

@@ -1,138 +0,0 @@
-# Logs
-logs
-*.log
-npm-debug.log*
-yarn-debug.log*
-yarn-error.log*
-lerna-debug.log*
-.pnpm-debug.log*
-
-# Diagnostic reports (https://nodejs.org/api/report.html)
-report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
-
-# Runtime data
-pids
-*.pid
-*.seed
-*.pid.lock
-
-# Directory for instrumented libs generated by jscoverage/JSCover
-lib-cov
-
-# Coverage directory used by tools like istanbul
-coverage
-*.lcov
-
-# nyc test coverage
-.nyc_output
-
-# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
-.grunt
-
-# Bower dependency directory (https://bower.io/)
-bower_components
-
-# node-waf configuration
-.lock-wscript
-
-# Compiled binary addons (https://nodejs.org/api/addons.html)
-build/Release
-
-# Dependency directories
-node_modules/
-jspm_packages/
-
-# Snowpack dependency directory (https://snowpack.dev/)
-web_modules/
-
-# TypeScript cache
-*.tsbuildinfo
-
-# Optional npm cache directory
-.npm
-
-# Optional eslint cache
-.eslintcache
-
-# Optional stylelint cache
-.stylelintcache
-
-# Microbundle cache
-.rpt2_cache/
-.rts2_cache_cjs/
-.rts2_cache_es/
-.rts2_cache_umd/
-
-# Optional REPL history
-.node_repl_history
-
-# Output of 'npm pack'
-*.tgz
-
-# Yarn Integrity file
-.yarn-integrity
-
-# dotenv environment variable files
-.env
-.env.development.local
-.env.test.local
-.env.production.local
-.env.local
-
-# parcel-bundler cache (https://parceljs.org/)
-.cache
-.parcel-cache
-
-# Next.js build output
-.next
-out
-
-# Nuxt.js build / generate output
-.nuxt
-dist
-
-# Gatsby files
-.cache/
-# Comment in the public line in if your project uses Gatsby and not Next.js
-# https://nextjs.org/blog/next-9-1#public-directory-support
-# public
-
-# vuepress build output
-.vuepress/dist
-
-# vuepress v2.x temp and cache directory
-.temp
-.cache
-
-# Docusaurus cache and generated files
-.docusaurus
-
-# Serverless directories
-.serverless/
-
-# FuseBox cache
-.fusebox/
-
-# DynamoDB Local files
-.dynamodb/
-
-# TernJS port file
-.tern-port
-
-# Stores VSCode versions used for testing VSCode extensions
-.vscode-test
-
-# yarn v2
-.yarn/cache
-.yarn/unplugged
-.yarn/build-state.yml
-.yarn/install-state.gz
-.pnp.*
-
-.DS_Store
-demo/jailbreak.mjs
-CLAUDE.md
-demo/jailbreak.js
-/demo/lab
-/demo/results
-/.pnpm-store/