modelmix 5.0.1 → 5.0.2

package/README.md

@@ -70,7 +70,7 @@ const model = await ModelMix.new(setup)
     .sonnet5() // (main model) Anthropic claude-sonnet-5
     .gpt56luna() // (fallback 2) OpenAI gpt-5.6-luna
     .gemini36flash({ config: { temperature: 0 } }) // (fallback 3) Google gemini-36-flash
-    .grok43() // (fallback 4) Grok grok-4.3
+    .grok46() // (fallback 4) Grok grok-4.6
     .addText("What's your name?");
 
 console.log(await model.message());
@@ -124,7 +124,7 @@ ModelMix.new().effort(-1).minimaxM3().addText('...').message();
 | DeepSeek V4 | off | `low`↑ | `high`↑ | `high`↑ | `max`↑ | — |
 | MiniMax M3 | off | adaptive | adaptive | adaptive | adaptive | adaptive |
 
-\* Gemini bands: 0–24 / 25–49 / 50–74 / 75–100. DeepSeek `↑` = thinking on; `off` = thinking disabled. MiniMax `off`/`adaptive` = `thinking.disabled` / `thinking.type=adaptive`. Gemini 2.5 maps 0–100 to `thinkingBudget`. Anthropic maps adaptive thinking + `output_config.effort` on Claude 5 / Fable / Opus 4.6+ / Sonnet 4.6+; older models (Sonnet 4.5, Haiku 4.5) get `thinking.type=enabled` + `budget_tokens`. `-1` = provider adaptive/dynamic when available, else no-op. Levels clamp to what each model supports.
+\* Gemini bands: 0–24 / 25–49 / 50–74 / 75–100. DeepSeek `↑` = thinking on; `off` = thinking disabled. MiniMax `off`/`adaptive` = `thinking.disabled` / `thinking.type=adaptive`. Gemini 2.5 maps 0–100 to `thinkingBudget`. Anthropic maps adaptive thinking + `output_config.effort` on Claude 5 / Fable / Opus 4.6+ / Sonnet 4.6+; older models (Sonnet 4.5, Haiku 4.5) get `thinking.type=enabled` + `budget_tokens`. Grok 4.6 clamps 0–39 / 40–59 / 60–79 / 80–100 to `low` / `medium` / `high` / `xhigh`; without effort it uses the native `high` default. `-1` = provider adaptive/dynamic when available, else no-op. Levels clamp to what each model supports.
 
 Migration: former `*think()` shorthands are removed — use `.effort(n).<model>()` (or any 0–100 / `-1`). Kimi: `kimiK25()` / `kimiK26()`. Grok 4.20: `.grok420()` is non-reasoning; `.effort(20+).grok420()` (or `-1`) selects the reasoning model.
 
@@ -192,6 +192,7 @@ Here's a comprehensive list of available methods:
 | `gemini35flash()`    | Google     | gemini-3.5-flash              | [\$0.75/\$4.50][3]       |
 | `gemini35flashLite()`| Google     | gemini-3.5-flash-lite          | [\$0.30/\$2.50][3]       |
 | `gemini31flashLite()`| Google     | gemini-3.1-flash-lite-preview | [\$0.25/\$1.50][3]       |
+| `grok46()`          | Grok       | grok-4.6                     | [\$2.00/\$6.00][6]       |
 | `grok45()`          | Grok       | grok-4.5                     | [\$2.00/\$6.00][6]       |
 | `grok43()`          | Grok       | grok-4.3                     | [\$1.25/\$2.50][6]       |
 | `grok420multiAgent()`| Grok      | grok-4.20-multi-agent-0309   | [\$1.25/\$2.50][6]       |

package/demo/grok.js

@@ -13,9 +13,9 @@ const mmix = new ModelMix({
 });
 
 
-const r = await mmix.grok43()
+const r = await mmix.grok46()
     .addText('hi there!')
     .addText('do you like cats?')
     .raw();
 
-console.log(r);
+console.log(r);

package/demo/images.js

@@ -1,9 +1,9 @@
 import { ModelMix } from '../index.js';
 try { process.loadEnvFile(); } catch {}
 
-const model = ModelMix.new({ config: { max_history: 2, debug: 2 } }).grok43()
+const model = ModelMix.new({ config: { max_history: 2, debug: 2 } }).grok46()
 // model.addImageFromUrl('https://pbs.twimg.com/media/F6-GsjraAAADDGy?format=jpg');
 model.addImage('./img.png');
 model.addText('in one word, which is the main color of the image?');
 
-console.log(await model.json({ color: "string" }));
+console.log(await model.json({ color: "string" }));

package/demo/short.js

@@ -13,7 +13,7 @@ const mmix = await ModelMix.new(setup)
     .gpt56luna() // (fallback 1) OpenAI gpt-5.6-luna
     .gemini36flash({ config: { temperature: 0 } }) // (fallback 2) Google gemini-3.6-flash
     .gpt41nano() // (fallback 3) OpenAI gpt-4.1-nano
-    .grok43() // (fallback 4) Grok grok-4.3
+    .grok46() // (fallback 4) Grok grok-4.6
     .addText("What's your name?");
 
-console.log(await mmix.message());
+console.log(await mmix.message());

package/effort.js

@@ -35,6 +35,7 @@ const GEMINI_BANDS = [
 
 /** Exact model → supported OpenAI reasoning_effort values */
 const OPENAI_MODEL_LEVELS = {
+    'grok-4.6': ['low', 'medium', 'high', 'xhigh'],
     'gpt-5': ['minimal', 'low', 'medium', 'high'],
     'gpt-5-mini': ['minimal', 'low', 'medium', 'high'],
     'gpt-5-nano': ['minimal', 'low', 'medium', 'high'],

package/index.d.ts

@@ -406,6 +406,7 @@ export declare class ModelMix {
   sonar(args?: ModelAttachArgs): this;
 
   // Grok
+  grok46(args?: ModelAttachArgs): this;
   grok45(args?: ModelAttachArgs): this;
   grok43(args?: ModelAttachArgs): this;
   grok420multiAgent(args?: ModelAttachArgs): this;

package/index.js

@@ -259,6 +259,21 @@ const GPT56_LONG_CONTEXT_PRICING = Object.freeze({
     outputMultiplier: 1.5
 });
 
+const GROK46_LONG_CONTEXT_PRICING = Object.freeze({
+    inputThreshold: 200_000,
+    inputMultiplier: 2,
+    outputMultiplier: 2,
+    inclusive: true
+});
+
+function usesLongContextRates(pricing, inputTokens) {
+    const longContext = pricing.longContext;
+    if (!longContext) return false;
+    return longContext.inclusive
+        ? inputTokens >= longContext.inputThreshold
+        : inputTokens > longContext.inputThreshold;
+}
+
 const MODEL_PRICING = {
     // OpenAI
     'gpt-realtime-mini': { input: 0.60, cachedInput: 0.06, output: 2.40 },
@@ -307,6 +322,7 @@ const MODEL_PRICING = {
     'gemini-2.5-flash': { input: 0.30, output: 2.50 },
     'gemini-3.1-flash-lite-preview': { input: 0.25, output: 1.50 },
     // Grok
+    'grok-4.6': { input: 2.00, cachedInput: 0.50, output: 6.00, longContext: GROK46_LONG_CONTEXT_PRICING },
     'grok-4.5': { input: 2.00, output: 6.00 },
     'grok-4.3': { input: 1.25, output: 2.50 },
     'grok-4.20-multi-agent-0309': { input: 1.25, output: 2.50 },
@@ -535,7 +551,7 @@ class ModelMix {
 
         const normalized = ModelMix.normalizeTokenUsage(tokens);
         const longContext = pricing.longContext;
-        const useLongContextRates = longContext && normalized.input > longContext.inputThreshold;
+        const useLongContextRates = usesLongContextRates(pricing, normalized.input);
         const inputMultiplier = useLongContextRates ? longContext.inputMultiplier : 1;
         const outputMultiplier = useLongContextRates ? longContext.outputMultiplier : 1;
         const {
@@ -587,9 +603,8 @@ class ModelMix {
 
         const normalized = ModelMix.normalizeTokenUsage(tokens);
         const longContext = pricing.longContext;
-        const inputMultiplier = longContext && normalized.input > longContext.inputThreshold
-            ? longContext.inputMultiplier
-            : 1;
+        const useLongContextRates = usesLongContextRates(pricing, normalized.input);
+        const inputMultiplier = useLongContextRates ? longContext.inputMultiplier : 1;
         const cachedInputPerMillion = pricing.cachedInput ?? pricing.input;
         const cacheWritePerMillion = pricing.cacheWrite ?? pricing.input;
         const cacheWrite1hPerMillion = pricing.cacheWrite1h ?? cacheWritePerMillion;
@@ -844,6 +859,9 @@ class ModelMix {
         return this.attach('sonar', new MixPerplexity({ options, config }));
     }
 
+    grok46({ options = {}, config = {} } = {}) {
+        return this.attach('grok-4.6', new MixGrok({ options, config }));
+    }
     grok45({ options = {}, config = {} } = {}) {
         return this.attach('grok-4.5', new MixGrok({ options, config }));
     }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "modelmix",
-  "version": "5.0.1",
+  "version": "5.0.2",
   "description": "🧬 Reliable interface with automatic fallback for AI LLMs.",
   "main": "index.js",
   "types": "index.d.ts",

package/skills/modelmix/SKILL.md

@@ -114,7 +114,7 @@ ModelMix.new({ config: { effort: 80 } })
 | DeepSeek V4 | off | `low`↑ | `high`↑ | `high`↑ | `max`↑ | — |
 | MiniMax M3 | off | adaptive | adaptive | adaptive | adaptive | adaptive |
 
-\* Gemini bands: 0–24 / 25–49 / 50–74 / 75–100. 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`. `-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.
+\* Gemini bands: 0–24 / 25–49 / 50–74 / 75–100. 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
 
@@ -130,7 +130,7 @@ Use `.effort(n)` (or `config.effort`) to enable Anthropic thinking — e.g. `.ef
 `gemini3pro()` `gemini3flash()` `gemini36flash()` `gemini35flash()` `gemini35flashLite()` `gemini31flashLite()` `gemini25pro()` `gemini25flash()`
 
 ### Grok
-`grok45()` `grok43()` `grok420multiAgent()` `grok420()`
+`grok46()` `grok45()` `grok43()` `grok420multiAgent()` `grok420()`
 
 ### Perplexity
 `sonar()` `sonarPro()`

package/test/grok.test.js

@@ -2,6 +2,7 @@ const { expect } = require('chai');
 const nock = require('nock');
 const { ModelMix, MixGrok } = require('../index.js');
 const {
+    mapEffort,
     resolveGrok420ModelKey,
     GROK420_ALIAS,
     GROK420_REASONING,
@@ -10,6 +11,7 @@ const {
 
 describe('Grok Model Registration Tests', () => {
     const grokModels = [
+        { method: 'grok46', key: 'grok-4.6' },
         { method: 'grok45', key: 'grok-4.5' },
         { method: 'grok43', key: 'grok-4.3' },
         { method: 'grok420multiAgent', key: 'grok-4.20-multi-agent-0309' },
@@ -25,6 +27,78 @@ describe('Grok Model Registration Tests', () => {
             expect(model.models[0].key).to.equal(grokModel.key);
         });
     }
+
+    it('forwards options and config through grok46()', () => {
+        const options = { reasoning_effort: 'xhigh' };
+        const config = { max_history: 3 };
+        const model = ModelMix.new().grok46({ options, config });
+
+        expect(model.models[0].provider).to.be.instanceOf(MixGrok);
+        expect(model.models[0].provider.options).to.deep.equal(options);
+        expect(model.models[0].provider.config).to.include(config);
+    });
+
+    it('maps unified effort to Grok 4.6 supported levels', () => {
+        expect(mapEffort('openai', 0, 'grok-4.6')).to.deep.equal({ reasoning_effort: 'low' });
+        expect(mapEffort('openai', 39, 'grok-4.6')).to.deep.equal({ reasoning_effort: 'low' });
+        expect(mapEffort('openai', 40, 'grok-4.6')).to.deep.equal({ reasoning_effort: 'medium' });
+        expect(mapEffort('openai', 60, 'grok-4.6')).to.deep.equal({ reasoning_effort: 'high' });
+        expect(mapEffort('openai', 100, 'grok-4.6')).to.deep.equal({ reasoning_effort: 'xhigh' });
+        expect(mapEffort('openai', -1, 'grok-4.6')).to.equal(null);
+    });
+
+    it('sends a supported Grok 4.6 reasoning effort', async () => {
+        const originalApiKey = process.env.XAI_API_KEY;
+        process.env.XAI_API_KEY = 'test-key';
+        const api = nock('https://api.x.ai')
+            .post('/v1/chat/completions', body => {
+                expect(body.model).to.equal('grok-4.6');
+                expect(body.reasoning_effort).to.equal('low');
+                return true;
+            })
+            .reply(200, {
+                choices: [{ message: { content: 'ok' } }],
+                usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 }
+            });
+
+        try {
+            const response = await ModelMix.new()
+                .effort(0)
+                .grok46({ config: { apiKey: 'test-key' } })
+                .addText('Hi')
+                .message();
+
+            expect(response).to.equal('ok');
+            api.done();
+        } finally {
+            if (originalApiKey === undefined) delete process.env.XAI_API_KEY;
+            else process.env.XAI_API_KEY = originalApiKey;
+        }
+    });
+
+    it('calculates Grok 4.6 cache and long-context costs', () => {
+        expect(ModelMix.calculateCostBreakdown('grok-4.6', {
+            input: 1_000_000,
+            output: 1_000_000,
+            cached: 1_000_000
+        })).to.deep.equal({
+            uncachedInput: 0,
+            cachedInput: 1,
+            cacheWrite: 0,
+            cacheWrite5m: 0,
+            cacheWrite1h: 0,
+            output: 12,
+            total: 13
+        });
+        expect(ModelMix.calculateCost('grok-4.6', {
+            input: 199_999,
+            output: 1_000_000
+        })).to.equal(6.399998);
+        expect(ModelMix.calculateCost('grok-4.6', {
+            input: 200_000,
+            output: 1_000_000
+        })).to.equal(12.8);
+    });
 });
 
 describe('Grok 4.20 effort → model resolution', () => {

package/test/live.mcp.js

@@ -233,8 +233,8 @@ describe('Live MCP Integration Tests', function () {
 
     describe('Advanced MCP Tool Integration', function () {
 
-        it('should use multiple MCP tools with Grok 4.3', async function () {
-            const model = ModelMix.new(setup).grok43();
+        it('should use multiple MCP tools with Grok 4.6', async function () {
+            const model = ModelMix.new(setup).grok46();
 
             // Add multiple tools
             model.addTools([

package/test/live.test.js

@@ -193,7 +193,7 @@ describe('Live Integration Tests', function () {
         });
 
         const grokSeriesTests = [
-            { name: 'Grok 4.3', factory: (m) => m.grok43(), token: 'grok43' },
+            { name: 'Grok 4.6', factory: (m) => m.grok46(), token: 'grok46' },
             { name: 'Grok 4.20 reasoning', factory: (m) => m.effort(50).grok420(), token: 'grok420' },
             { name: 'Grok 4.20 non-reasoning', factory: (m) => m.grok420(), token: 'grok420nr' }
         ];
@@ -216,8 +216,8 @@ describe('Live Integration Tests', function () {
 
     describe('Image Processing with JSON Output', function () {
 
-        it('should process images and return JSON with Grok 4.3', async function () {
-            const model = ModelMix.new(setup).grok43();
+        it('should process images and return JSON with Grok 4.6', async function () {
+            const model = ModelMix.new(setup).grok46();
 
             model.addImageFromUrl(blueSquareBase64)
                 .addText('Analyze this image and provide details in JSON format.');
@@ -228,7 +228,7 @@ describe('Live Integration Tests', function () {
                 description: "string"
             });
 
-            console.log(`Grok 4.3 image JSON result:`, result);
+            console.log(`Grok 4.6 image JSON result:`, result);
 
             expect(result).to.be.an('object');
             expect(result).to.have.property('color');
@@ -263,8 +263,8 @@ describe('Live Integration Tests', function () {
             expect(result.features).to.be.an('array');
         });
 
-        it('should return structured JSON with Grok 4.3', async function () {
-            const model = ModelMix.new(setup).grok43();
+        it('should return structured JSON with Grok 4.6', async function () {
+            const model = ModelMix.new(setup).grok46();
 
             model.addText('Generate information about a fictional technology.');
 
@@ -275,7 +275,7 @@ describe('Live Integration Tests', function () {
                 power: "1000 qubits"
             });
 
-            console.log(`Grok 4.3 JSON result:`, result);
+            console.log(`Grok 4.6 JSON result:`, result);
 
             expect(result).to.be.an('object');
             expect(result).to.have.property('name');