modelmix 5.0.5 → 5.0.6

package/README.md

@@ -175,17 +175,20 @@ Here's a comprehensive list of available methods:
 | `grok43()`          | Grok       | grok-4.3                     | [\$1.25/\$2.50][6]       |
 | `grok420multiAgent()`| Grok      | grok-4.20-multi-agent-0309   | [\$1.25/\$2.50][6]       |
 | `grok420()`         | Grok       | grok-4.20-0309 (†)           | [\$1.25/\$2.50][6]       |
+| `qwen35397b()`      | OpenRouter | qwen/qwen3.5-397b-a17b       | [\$0.385/\$2.45][14]     |
 | `qwen36plus()`      | Fireworks  | qwen3p6-plus                 | [\$0.50/\$3.00][10]      |
 | `qwen37plus()`      | Fireworks  | models/qwen3p7-plus          | [\$0.40/\$1.60][10]      |
-| `qwen38max()`       | OpenRouter | qwen/qwen3.8-max             | [\$2.00/\$6.00][12]      |
+| `qwen38max()`       | Fireworks  | qwen3p8-2p4t-a95b            | [\$2.00/\$6.00][10]      |
 | `deepseekV4Flash()` | Fireworks  | models/deepseek-v4-flash      | [\$0.14/\$0.28][10]      |
-| `deepseekV4Pro()`   | Fireworks  | models/deepseek-v4-pro       | [\$1.74/\$3.48][10]      |
+| `deepseekV4Pro()`   | Fireworks  | models/deepseek-v4-pro-0813  | [\$1.32/\$3.96][12]      |
 | `GLM52()`           | Together   | zai-org/GLM-5.2              | [\$1.40/\$4.40][7]       |
 | `GLM51()`           | Fireworks  | models/glm-5p1               | [\$1.05/\$3.50][10]      |
 | `minimaxM3()`       | MiniMax    | MiniMax-M3                   | [\$0.30/\$1.20][9]       |
 | `minimaxM27()`      | MiniMax    | MiniMax-M2.7                 | [\$0.30/\$1.20][9]       |
 | `sonar()`           | Perplexity | sonar                        | [\$1.00/\$1.00][4]       |
 | `sonarPro()`        | Perplexity | sonar-pro                    | [\$3.00/\$15.00][4]      |
+| `hermes470b()`      | OpenRouter | nousresearch/hermes-4-70b    | [\$0.13/\$0.40][13]      |
+| `hermes4405b()`     | OpenRouter | nousresearch/hermes-4-405b   | [\$1.00/\$3.00][13]      |
 | `hermes3()`         | Lambda     | Hermes-3-Llama-3.1-405B-FP8  | [\$0.80/\$0.80][8]       |
 | `kimiK3()`          | Moonshot   | kimi-k3                      | [\$3.00/\$15.00][11]     |
 | `kimiK25()`         | Together   | Kimi-K2.5                    | [\$0.50/\$2.80][7]       |
@@ -204,7 +207,9 @@ Gemini 3.7 Flash and 3.6 Flash use Google's introductory standard pricing throug
 [9]: https://platform.minimax.io/docs/api-reference/anthropic-api-compatible-cache#supported-models-and-pricing "MiniMax Pricing"
 [10]: https://fireworks.ai/pricing#serverless-pricing "Fireworks Pricing"
 [11]: https://platform.kimi.ai/docs/guide/kimi-k3-pricing "Kimi K3 Pricing"
-[12]: https://openrouter.ai/qwen/qwen3.8-max "OpenRouter Pricing"
+[12]: https://fireworks.ai/models/deepseek-ai/deepseek-v4-pro-0813 "DeepSeek V4 Pro 0813 Pricing"
+[13]: https://openrouter.ai/nousresearch "Nous Research Models on OpenRouter"
+[14]: https://openrouter.ai/qwen/qwen3.5-397b-a17b "Qwen3.5 397B A17B on OpenRouter"
 
 Each method accepts optional `options`, `config`, and (for multi-provider methods) `mix` parameters to customize behavior.  
 

package/demo/short.js

@@ -14,6 +14,9 @@ const mmix = await ModelMix.new(setup)
     .gemini37flash() // (fallback 2) Google gemini-3.7-flash
     .gpt41nano() // (fallback 3) OpenAI gpt-4.1-nano
     .grok46() // (fallback 4) Grok grok-4.6
+    .qwen35397b() // (fallback 5) OpenRouter qwen/qwen3.5-397b-a17b
+    .hermes470b() // (fallback 6) OpenRouter nousresearch/hermes-4-70b
+    .hermes4405b() // (fallback 7) OpenRouter nousresearch/hermes-4-405b
     .addText("What's your name?");
 
 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 = {
+    'accounts/fireworks/models/qwen3p8-2p4t-a95b': ['none', 'low', 'medium', 'high'],
     'grok-4.6': ['low', 'medium', 'high', 'xhigh'],
     'gpt-5': ['minimal', 'low', 'medium', 'high'],
     'gpt-5-mini': ['minimal', 'low', 'medium', 'high'],

package/index.d.ts

@@ -504,9 +504,12 @@ export declare class ModelMix {
 
   // Multi-provider
   qwen3(args?: ModelAttachArgs): this;
+  qwen35397b(args?: ModelAttachArgs): this;
   qwen36plus(args?: ModelAttachArgs): this;
   qwen37plus(args?: ModelAttachArgs): this;
   qwen38max(args?: ModelAttachArgs): this;
+  hermes470b(args?: ModelAttachArgs): this;
+  hermes4405b(args?: ModelAttachArgs): this;
   hermes3(args?: ModelAttachArgs): this;
   kimiK26(args?: ModelAttachArgs): this;
   kimiK27Code(args?: ModelAttachArgs): this;

package/index.js

@@ -362,6 +362,7 @@ const MODEL_PRICING = {
     // Fireworks
     'accounts/fireworks/models/deepseek-v4-flash': { input: 0.14, output: 0.28 },
     'accounts/fireworks/models/deepseek-v4-pro': { input: 1.74, output: 3.48 },
+    'accounts/fireworks/models/deepseek-v4-pro-0813': { input: 1.32, cachedInput: 0.044, output: 3.96 },
     'deepseek-ai/DeepSeek-V4-Flash': { input: 0.14, output: 0.28 },
     'deepseek-ai/DeepSeek-V4-Pro': { input: 2.10, output: 4.40 },
     'deepseek/deepseek-v4-flash': { input: 0.09, output: 0.18 },
@@ -369,10 +370,12 @@ const MODEL_PRICING = {
     'accounts/fireworks/models/glm-5p1': { input: 1.05, output: 3.50 },
     'zai-org/GLM-5.2': { input: 1.40, output: 4.40 },
     'accounts/fireworks/models/kimi-k2p5': { input: 0.50, output: 2.80 },
+    'qwen/qwen3.5-397b-a17b': { input: 0.385, output: 2.45 },
     'accounts/fireworks/models/qwen3p6-plus': { input: 0.50, output: 3.00 },
     'Qwen/Qwen3.6-Plus': { input: 0.50, output: 3.00 },
     'accounts/fireworks/models/qwen3p7-plus': { input: 0.40, output: 1.60 },
     'qwen/qwen3.7-plus': { input: 0.32, output: 1.28 },
+    'accounts/fireworks/models/qwen3p8-2p4t-a95b': { input: 2.00, cachedInput: 0.25, output: 6.00 },
     'qwen/qwen3.8-max': { input: 2.00, output: 6.00 },
     // MiniMax
     'MiniMax-M2.5': { input: 0.30, output: 1.20 },
@@ -384,7 +387,10 @@ const MODEL_PRICING = {
     // Perplexity
     'sonar': { input: 1.00, output: 1.00 },
     'sonar-pro': { input: 3.00, output: 15.00 },
-    // Hermes3 (Lambda/OpenRouter)
+    // Hermes 4 (OpenRouter)
+    'nousresearch/hermes-4-70b': { input: 0.13, output: 0.40 },
+    'nousresearch/hermes-4-405b': { input: 1.00, output: 3.00 },
+    // Hermes 3 (Lambda/OpenRouter)
     'Hermes-3-Llama-3.1-405B-FP8': { input: 0.80, output: 0.80 },
     'nousresearch/hermes-3-llama-3.1-405b:free': { input: 0, output: 0 },
     // Qwen3 (Together/Cerebras)
@@ -412,7 +418,8 @@ const CHAIN_MODEL_SHORTCUTS = new Set([
     'gemini37flash', 'gemini36flash', 'gemini35flash', 'gemini35flashLite',
     'gemini31flashLite', 'gemini25pro', 'sonarPro', 'sonar',
     'grok46', 'grok45', 'grok43', 'grok420multiAgent', 'grok420',
-    'qwen3', 'qwen36plus', 'qwen37plus', 'qwen38max', 'hermes3',
+    'qwen3', 'qwen35397b', 'qwen36plus', 'qwen37plus', 'qwen38max',
+    'hermes470b', 'hermes4405b', 'hermes3',
     'kimiK26', 'kimiK27Code', 'kimiK3', 'kimiK25',
     'minimaxM25', 'minimaxM27', 'minimaxM3', 'mimo25', 'mimo25pro',
     'deepseekV4Pro', 'deepseekV4Flash', 'GLM51', 'GLM52'
@@ -1090,6 +1097,10 @@ class ModelMix {
         return this;
     }
 
+    qwen35397b({ options = {}, config = {} } = {}) {
+        return this.attach('qwen/qwen3.5-397b-a17b', new MixOpenRouter({ options, config }));
+    }
+
     qwen36plus({ options = {}, config = {}, mix = { fireworks: true } } = {}) {
         mix = { ...this.mix, ...mix };
         if (mix.fireworks) this.attach('accounts/fireworks/models/qwen3p6-plus', new MixFireworks({ options, config }));
@@ -1104,12 +1115,21 @@ class ModelMix {
         return this;
     }
 
-    qwen38max({ options = {}, config = {}, mix = { openrouter: true } } = {}) {
+    qwen38max({ options = {}, config = {}, mix = { fireworks: true } } = {}) {
         mix = { ...this.mix, ...mix };
+        if (mix.fireworks) this.attach('accounts/fireworks/models/qwen3p8-2p4t-a95b', new MixFireworks({ options, config }));
         if (mix.openrouter) this.attach('qwen/qwen3.8-max', new MixOpenRouter({ options, config }));
         return this;
     }
 
+    hermes470b({ options = {}, config = {} } = {}) {
+        return this.attach('nousresearch/hermes-4-70b', new MixOpenRouter({ options, config }));
+    }
+
+    hermes4405b({ options = {}, config = {} } = {}) {
+        return this.attach('nousresearch/hermes-4-405b', new MixOpenRouter({ options, config }));
+    }
+
     hermes3({ options = {}, config = {}, mix = {} } = {}) {
         mix = { ...this.mix, ...mix };
         if (mix.lambda) this.attach('Hermes-3-Llama-3.1-405B-FP8', new MixLambda({ options, config }));
@@ -1191,7 +1211,7 @@ class ModelMix {
     deepseekV4Pro({ options = {}, config = {}, mix = { fireworks: true } } = {}) {
         mix = { ...this.mix, ...mix };
         if (mix.nvidia) this.attach('deepseek-ai/deepseek-v4-pro', new MixNVIDIA({ options, config }));
-        if (mix.fireworks) this.attach('accounts/fireworks/models/deepseek-v4-pro', new MixFireworks({ options, config }));
+        if (mix.fireworks) this.attach('accounts/fireworks/models/deepseek-v4-pro-0813', new MixFireworks({ options, config }));
         if (mix.openrouter) this.attach('deepseek/deepseek-v4-pro', new MixOpenRouter({ options, config }));
         if (mix.together) this.attach('deepseek-ai/DeepSeek-V4-Pro', new MixTogether({ options, config }));
         return this;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "modelmix",
-  "version": "5.0.5",
+  "version": "5.0.6",
   "description": "🧬 Reliable interface with automatic fallback for AI LLMs.",
   "main": "index.js",
   "types": "index.d.ts",

package/skills/modelmix/SKILL.md

@@ -177,13 +177,13 @@ Use `.effort(n)` (or `config.effort`) to enable Anthropic thinking — e.g. `.ef
 `minimaxM25()` `minimaxM27()` `minimaxM3()`
 
 ### Fireworks
-`qwen36plus()` `qwen37plus()` `deepseekV4Flash()` `deepseekV4Pro()` `kimiK26()`
+`qwen36plus()` `qwen37plus()` `qwen38max()` `deepseekV4Flash()` `deepseekV4Pro()` `kimiK26()`
 
 ### Cerebras
 `GLM46()`
 
 ### OpenRouter
-`qwen38max()` `GLM45()`
+`qwen35397b()` `hermes470b()` `hermes4405b()` `qwen38max()` `GLM45()`
 
 ### Multi-provider (auto-fallback across free/paid tiers)
 `hermes3()` `kimiK25()`

package/test/deepseek.test.js

@@ -7,7 +7,12 @@ describe('DeepSeek Model Registration Tests', () => {
         model.deepseekV4Pro({ mix: { fireworks: true, openrouter: false } });
 
         expect(model.models).to.have.length(1);
-        expect(model.models[0].key).to.equal('accounts/fireworks/models/deepseek-v4-pro');
+        expect(model.models[0].key).to.equal('accounts/fireworks/models/deepseek-v4-pro-0813');
+        expect(ModelMix.calculateCost('accounts/fireworks/models/deepseek-v4-pro-0813', {
+            input: 1_000_000,
+            cached: 250_000,
+            output: 1_000_000
+        })).to.be.closeTo(4.961, 1e-10);
     });
 
     it('should register Together DeepSeek V4 Pro when together mix is enabled', () => {

package/test/effort.test.js

@@ -81,6 +81,12 @@ describe('Unified effort scale', () => {
             expect(mapEffort('openai', 10, 'gpt-oss-120b')).to.deep.equal({ reasoning_effort: 'low' });
         });
 
+        it('clamps Fireworks Qwen 3.8 Max to its supported reasoning levels', () => {
+            const key = 'accounts/fireworks/models/qwen3p8-2p4t-a95b';
+            expect(mapEffort('openai', 0, key)).to.deep.equal({ reasoning_effort: 'none' });
+            expect(mapEffort('openai', 100, key)).to.deep.equal({ reasoning_effort: 'high' });
+        });
+
         it('maps Anthropic adaptive models to thinking + output_config.effort', () => {
             expect(mapEffort('anthropic', 10, 'claude-opus-5')).to.deep.equal({
                 thinking: { type: 'adaptive', display: 'summarized' },
@@ -178,6 +184,10 @@ describe('Unified effort scale', () => {
                 reasoning_effort: 'max',
                 thinking: { type: 'enabled' }
             });
+            expect(mapEffort('openai', 100, 'accounts/fireworks/models/deepseek-v4-pro-0813')).to.deep.equal({
+                reasoning_effort: 'max',
+                thinking: { type: 'enabled' }
+            });
             // No adaptive control on DeepSeek → no-op
             expect(mapEffort('openai', -1, 'deepseek/deepseek-v4-flash')).to.equal(null);
         });

package/test/hermes.test.js

@@ -0,0 +1,37 @@
+const { expect } = require('chai');
+const { ModelMix, MixOpenRouter } = require('../index.js');
+
+describe('Hermes Model Registration Tests', () => {
+    it('should register Hermes 4 70B through OpenRouter', () => {
+        const model = ModelMix.new().hermes470b();
+
+        expect(model.models).to.have.length(1);
+        expect(model.models[0].key).to.equal('nousresearch/hermes-4-70b');
+        expect(model.models[0].provider).to.be.instanceOf(MixOpenRouter);
+        expect(ModelMix.calculateCost('nousresearch/hermes-4-70b', {
+            input: 1_000_000,
+            output: 1_000_000
+        })).to.equal(0.53);
+    });
+
+    it('should register Hermes 4 405B through OpenRouter', () => {
+        const model = ModelMix.new().hermes4405b();
+
+        expect(model.models).to.have.length(1);
+        expect(model.models[0].key).to.equal('nousresearch/hermes-4-405b');
+        expect(model.models[0].provider).to.be.instanceOf(MixOpenRouter);
+        expect(ModelMix.calculateCost('nousresearch/hermes-4-405b', {
+            input: 1_000_000,
+            output: 1_000_000
+        })).to.equal(4);
+    });
+
+    it('should support both Hermes 4 shortcuts in chain()', () => {
+        const model = ModelMix.new().chain('hermes470b', 'hermes4405b');
+
+        expect(model.models.map(({ key }) => key)).to.deep.equal([
+            'nousresearch/hermes-4-70b',
+            'nousresearch/hermes-4-405b'
+        ]);
+    });
+});

package/test/qwen.test.js

@@ -1,5 +1,5 @@
 const { expect } = require('chai');
-const { ModelMix } = require('../index.js');
+const { ModelMix, MixOpenRouter } = require('../index.js');
 
 describe('Qwen Model Registration Tests', () => {
     it('should register Fireworks Qwen 3.6 Plus by default', () => {
@@ -38,15 +38,45 @@ describe('Qwen Model Registration Tests', () => {
         expect(model.models[0].key).to.equal('qwen/qwen3.7-plus');
     });
 
-    it('should register OpenRouter Qwen 3.8 Max by default', () => {
+    it('should register Fireworks Qwen 3.8 Max before the OpenRouter fallback by default', () => {
         const model = ModelMix.new();
         model.qwen38max();
 
+        expect(model.models.map(({ key }) => key)).to.deep.equal([
+            'accounts/fireworks/models/qwen3p8-2p4t-a95b',
+            'qwen/qwen3.8-max'
+        ]);
+        expect(ModelMix.calculateCost('accounts/fireworks/models/qwen3p8-2p4t-a95b', {
+            input: 1_000_000,
+            cached: 250_000,
+            output: 1_000_000
+        })).to.equal(7.5625);
+    });
+
+    it('should register only OpenRouter Qwen 3.8 Max when Fireworks is disabled', () => {
+        const model = ModelMix.new();
+        model.qwen38max({ mix: { fireworks: false, openrouter: true } });
+
         expect(model.models).to.have.length(1);
         expect(model.models[0].key).to.equal('qwen/qwen3.8-max');
-        expect(ModelMix.calculateCost('qwen/qwen3.8-max', {
+    });
+
+    it('should register Qwen 3.5 397B A17B through OpenRouter', () => {
+        const model = ModelMix.new().qwen35397b();
+
+        expect(model.models).to.have.length(1);
+        expect(model.models[0].key).to.equal('qwen/qwen3.5-397b-a17b');
+        expect(model.models[0].provider).to.be.instanceOf(MixOpenRouter);
+        expect(ModelMix.calculateCost('qwen/qwen3.5-397b-a17b', {
             input: 1_000_000,
             output: 1_000_000
-        })).to.equal(8.00);
+        })).to.equal(2.835);
+    });
+
+    it('should support Qwen 3.5 397B A17B in chain()', () => {
+        const model = ModelMix.new().chain('qwen35397b');
+
+        expect(model.models).to.have.length(1);
+        expect(model.models[0].key).to.equal('qwen/qwen3.5-397b-a17b');
     });
 });