modelmix 5.0.5 → 5.1.1

package/README.md

@@ -15,9 +15,9 @@ Ever found yourself wanting to integrate AI models into your projects but worrie
 - [Token Usage Tracking](#-token-usage-tracking)
 - [Prompt Caching](#-prompt-caching)
 - [Model Context Protocol (MCP) Integration](#-model-context-protocol-mcp-integration)
-- [Enabling Debug Mode](#-enabling-debug-mode)
-- [Bottleneck Integration](#-bottleneck-integration)
 - [Retry (Opt-In)](#-retry-optin)
+- [Bottleneck Integration](#-bottleneck-integration)
+- [Enabling Debug Mode](#-enabling-debug-mode)
 - [Instance Plugins](#-instance-plugins)
 - [ModelMix Class Overview](#-modelmix-class-overview)
 - [Contributing](#-contributing)
@@ -136,60 +136,59 @@ This pattern allows you to:
 ## ⚡️ Shorthand Methods
 
 ModelMix provides convenient shorthand methods for quickly accessing different AI models.
-Here's a comprehensive list of available methods:
-
-| Method              | Provider   | Model                        | Price (I/O) per 1 M tokens |
-| ------------------- | ---------- | ---------------------------- | -------------------------- |
-| `gpt56sol()`        | OpenAI     | gpt-5.6-sol                  | [\$5.00/\$30.00][1]      |
-| `gpt56terra()`      | OpenAI     | gpt-5.6-terra                | [\$2.00/\$12.00][1]      |
-| `gpt56luna()`       | OpenAI     | gpt-5.6-luna                 | [\$0.20/\$1.20][1]       |
-| `gpt55()`           | OpenAI     | gpt-5.5                      | [\$5.00/\$30.00][1]      |
-| `gpt54()`           | OpenAI     | gpt-5.4                      | [\$2.50/\$15.00][1]      |
-| `gpt54mini()`       | OpenAI     | gpt-5.4-mini                 | [\$0.75/\$4.50][1]       |
-| `gpt54nano()`       | OpenAI     | gpt-5.4-nano                 | [\$0.20/\$1.25][1]       |
-| `gpt53codex()`      | OpenAI     | gpt-5.3-codex                | [\$1.25/\$14.00][1]      |
-| `gpt52()`           | OpenAI     | gpt-5.2                      | [\$1.75/\$14.00][1]      |
-| `gpt51()`           | OpenAI     | gpt-5.1                      | [\$1.25/\$10.00][1]      |
-| `gpt5mini()`        | OpenAI     | gpt-5-mini                   | [\$0.25/\$2.00][1]       |
-| `gpt5nano()`        | OpenAI     | gpt-5-nano                   | [\$0.05/\$0.40][1]       |
-| `gpt41()`           | OpenAI     | gpt-4.1                      | [\$2.00/\$8.00][1]       |
-| `gpt41mini()`       | OpenAI     | gpt-4.1-mini                 | [\$0.40/\$1.60][1]       |
-| `gpt41nano()`       | OpenAI     | gpt-4.1-nano                 | [\$0.10/\$0.40][1]       |
-| `gptOss()`          | Together   | gpt-oss-120B                 | [\$0.15/\$0.60][7]       |
-| `fable5()`          | Anthropic  | claude-fable-5               | [\$10.00/\$50.00][2]     |
-| `opus5()`           | Anthropic  | claude-opus-5                | [\$5.00/\$25.00][2]      |
-| `opus48()`          | Anthropic  | claude-opus-4-8              | [\$5.00/\$25.00][2]      |
-| `opus47()`          | Anthropic  | claude-opus-4-7              | [\$5.00/\$25.00][2]      |
-| `opus46()`          | Anthropic  | claude-opus-4-6              | [\$5.00/\$25.00][2]      |
-| `sonnet5()`         | Anthropic  | claude-sonnet-5              | [\$3.00/\$15.00][2]      |
-| `sonnet46()`        | Anthropic  | claude-sonnet-4-6            | [\$3.00/\$15.00][2]      |
-| `haiku45()`         | Anthropic  | claude-haiku-4-5-20251001    | [\$1.00/\$5.00][2]       |
-| `gemini31pro()`     | Google     | gemini-3.1-pro-preview       | [\$2.00/\$12.00][3]      |
-| `gemini37flash()`   | Google     | gemini-3.7-flash             | [\$0.75/\$3.75][3]       |
-| `gemini36flash()`   | Google     | gemini-3.6-flash             | [\$0.75/\$3.75][3]       |
-| `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]       |
-| `grok420()`         | Grok       | grok-4.20-0309 (†)           | [\$1.25/\$2.50][6]       |
-| `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]      |
-| `deepseekV4Flash()` | Fireworks  | models/deepseek-v4-flash      | [\$0.14/\$0.28][10]      |
-| `deepseekV4Pro()`   | Fireworks  | models/deepseek-v4-pro       | [\$1.74/\$3.48][10]      |
-| `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]      |
-| `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]       |
-| `kimiK26()`         | Fireworks  | models/kimi-k2p6             | [\$0.95/\$4.00][10]      |
+
+| Method | Provider | Model | Input / 1M | Output / 1M |
+| --- | --- | --- | ---: | ---: |
+| `gpt56sol()` | OpenAI | gpt-5.6-sol | [\$5.00][1] | [\$30.00][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] |
+| `gpt54()` | OpenAI | gpt-5.4 | [\$2.50][1] | [\$15.00][1] |
+| `gpt54mini()` | OpenAI | gpt-5.4-mini | [\$0.75][1] | [\$4.50][1] |
+| `gpt54nano()` | OpenAI | gpt-5.4-nano | [\$0.20][1] | [\$1.25][1] |
+| `gpt53codex()` | OpenAI | gpt-5.3-codex | [\$1.25][1] | [\$14.00][1] |
+| `gpt52()` | OpenAI | gpt-5.2 | [\$1.75][1] | [\$14.00][1] |
+| `gpt51()` | OpenAI | gpt-5.1 | [\$1.25][1] | [\$10.00][1] |
+| `gpt5mini()` | OpenAI | gpt-5-mini | [\$0.25][1] | [\$2.00][1] |
+| `gpt5nano()` | OpenAI | gpt-5-nano | [\$0.05][1] | [\$0.40][1] |
+| `gptOss()` | Together | gpt-oss-120B | [\$0.15][7] | [\$0.60][7] |
+| `fable5()` | Anthropic | claude-fable-5 | [\$10.00][2] | [\$50.00][2] |
+| `opus5()` | Anthropic | claude-opus-5 | [\$5.00][2] | [\$25.00][2] |
+| `opus48()` | Anthropic | claude-opus-4-8 | [\$5.00][2] | [\$25.00][2] |
+| `opus47()` | Anthropic | claude-opus-4-7 | [\$5.00][2] | [\$25.00][2] |
+| `opus46()` | Anthropic | claude-opus-4-6 | [\$5.00][2] | [\$25.00][2] |
+| `sonnet5()` | Anthropic | claude-sonnet-5 | [\$3.00][2] | [\$15.00][2] |
+| `sonnet46()` | Anthropic | claude-sonnet-4-6 | [\$3.00][2] | [\$15.00][2] |
+| `haiku45()` | Anthropic | claude-haiku-4-5-20251001 | [\$1.00][2] | [\$5.00][2] |
+| `gemini31pro()` | Google | gemini-3.1-pro-preview | [\$2.00][3] | [\$12.00][3] |
+| `gemini37flash()` | Google | gemini-3.7-flash | [\$0.75][3] | [\$3.75][3] |
+| `gemini36flash()` | Google | gemini-3.6-flash | [\$0.75][3] | [\$3.75][3] |
+| `gemini35flash()` | Google | gemini-3.5-flash | [\$0.75][3] | [\$4.50][3] |
+| `gemini35flashLite()` | Google | gemini-3.5-flash-lite | [\$0.30][3] | [\$2.50][3] |
+| `gemini31flashLite()` | Google | gemini-3.1-flash-lite-preview | [\$0.25][3] | [\$1.50][3] |
+| `grok46()` | Grok | grok-4.6 | [\$2.00][6] | [\$6.00][6] |
+| `grok45()` | Grok | grok-4.5 | [\$2.00][6] | [\$6.00][6] |
+| `grok43()` | Grok | grok-4.3 | [\$1.25][6] | [\$2.50][6] |
+| `grok420multiAgent()` | Grok | grok-4.20-multi-agent-0309 | [\$1.25][6] | [\$2.50][6] |
+| `grok420()` | Grok | grok-4.20-0309 (†) | [\$1.25][6] | [\$2.50][6] |
+| `qwen35397b()` | OpenRouter | qwen/qwen3.5-397b-a17b | [\$0.385][14] | [\$2.45][14] |
+| `qwen36plus()` | Fireworks | qwen3p6-plus | [\$0.50][10] | [\$3.00][10] |
+| `qwen37plus()` | Fireworks | models/qwen3p7-plus | [\$0.40][10] | [\$1.60][10] |
+| `qwen38max()` | Fireworks | qwen3p8-2p4t-a95b | [\$2.00][10] | [\$6.00][10] |
+| `deepseekV4Flash()` | Fireworks | models/deepseek-v4-flash | [\$0.14][10] | [\$0.28][10] |
+| `deepseekV4Pro()` | Fireworks | models/deepseek-v4-pro-0813 | [\$1.32][12] | [\$3.96][12] |
+| `GLM52()` | Together | zai-org/GLM-5.2 | [\$1.40][7] | [\$4.40][7] |
+| `GLM51()` | Fireworks | models/glm-5p1 | [\$1.05][10] | [\$3.50][10] |
+| `minimaxM3()` | MiniMax | MiniMax-M3 | [\$0.30][9] | [\$1.20][9] |
+| `minimaxM27()` | MiniMax | MiniMax-M2.7 | [\$0.30][9] | [\$1.20][9] |
+| `sonar()` | Perplexity | sonar | [\$1.00][4] | [\$1.00][4] |
+| `sonarPro()` | Perplexity | sonar-pro | [\$3.00][4] | [\$15.00][4] |
+| `hermes470b()` | OpenRouter | nousresearch/hermes-4-70b | [\$0.13][13] | [\$0.40][13] |
+| `hermes4405b()` | OpenRouter | nousresearch/hermes-4-405b | [\$1.00][13] | [\$3.00][13] |
+| `hermes3()` | Lambda | Hermes-3-Llama-3.1-405B-FP8 | [\$0.80][8] | [\$0.80][8] |
+| `kimiK3()` | Moonshot | kimi-k3 | [\$3.00][11] | [\$15.00][11] |
+| `kimiK25()` | Together | Kimi-K2.5 | [\$0.50][7] | [\$2.80][7] |
+| `kimiK26()` | Fireworks | models/kimi-k2p6 | [\$0.95][10] | [\$4.00][10] |
 
 Gemini 3.7 Flash and 3.6 Flash use Google's introductory standard pricing through December 31, 2026; standard rates double on January 1, 2027.
 
@@ -204,7 +203,9 @@ 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.  
 
@@ -244,6 +245,7 @@ ModelMix.new().effort(-1).minimaxM3().addText('...').message();
 ### Provider-specific behavior
 
 - **Gemini:** Gemini 3+ uses bands 0–24 / 25–49 / 50–74 / 75–100. Gemini 3.7 Flash clamps these bands to `low` / `low` / `medium` / `high`; `-1` leaves its native `medium` default unchanged. Gemini 2.5 maps 0–100 to `thinkingBudget`.
+- **GPT-5.6:** `100` maps to `max`; 80–99 remains `xhigh`.
 - **DeepSeek:** `↑` means thinking is enabled; `off` means it is disabled.
 - **MiniMax:** `off` maps to `thinking.disabled`; `adaptive` maps to `thinking.type=adaptive`.
 - **Anthropic:** Claude 5, Fable, Opus 4.6+, and Sonnet 4.6+ use adaptive thinking with `output_config.effort`. Sonnet 4.5 and Haiku 4.5 use `thinking.type=enabled` with `budget_tokens`.
@@ -836,56 +838,6 @@ This simple integration allows your model to:
 
 The Model Context Protocol makes it easy to add any capability to your models, from web search to code execution, database queries, or custom functions. All with just a few lines of code!
 
-## 🐛 Enabling Debug Mode
-
-To activate debug mode in ModelMix and view detailed request information, follow these two steps:
-
-1. In the ModelMix constructor, include a `debug` level in the configuration:
-
-   ```javascript
-   const mix = ModelMix.new({
-     config: {
-       debug: 4 // 0=silent, 1=minimal, 2=summary, 3=full (no truncate), 4=verbose (raw details)
-       // ... other configuration options ...
-     }
-   });
-   ```
-
-2. When running your script from the command line, use the `DEBUG=ModelMix*` prefix:
-
-   ```
-   DEBUG=ModelMix* node your_script.js
-   ```
-
-When you run your script this way, you'll see detailed information about the requests in the console, including the configuration and options used for each AI model request.
-
-This information is valuable for debugging and understanding how ModelMix is processing your requests.
-
-## 🚦 Bottleneck Integration
-
-ModelMix now uses Bottleneck for efficient rate limiting of API requests. This integration helps prevent exceeding API rate limits and ensures smooth operation when working with multiple models or high request volumes.
-
-### How it works:
-
-1. **Configuration**: Bottleneck is configured in the ModelMix constructor. You can customize the settings or use the default configuration:
-
-```javascript
-const setup = {
-    config: {
-        bottleneck: {
-            maxConcurrent: 8,     // Maximum number of concurrent requests
-            minTime: 500          // Minimum time between requests (in ms)
-        }
-    }
-};
-```
-
-2. **Rate Limiting**: When you make a request using any of the attached models, Bottleneck automatically manages the request flow based on the configured settings.
-
-3. **Automatic Queueing**: If the rate limit is reached, Bottleneck will automatically queue subsequent requests and process them as capacity becomes available.
-
-This integration ensures that your application respects API rate limits while maximizing throughput, providing a robust solution for managing multiple AI model interactions.
-
 ## 🔁 Retry (Opt-In)
 
 ModelMix supports optional intra-model retries for transient HTTP failures. When enabled, it retries the same provider before moving to fallback models.
@@ -909,6 +861,35 @@ Behavior summary:
 - If retry is enabled, ModelMix retries the same model only for configured transient status codes.
 - After retries are exhausted (or for non-retryable errors), ModelMix continues with normal fallback chain.
 
+## 🚦 Bottleneck Integration
+
+ModelMix uses Bottleneck for efficient rate limiting of API requests.
+
+```javascript
+const setup = {
+    config: {
+        bottleneck: {
+            maxConcurrent: 8,
+            minTime: 500
+        }
+    }
+};
+```
+
+Attached models share this limiter, which queues requests when capacity is exhausted.
+
+## 🐛 Enabling Debug Mode
+
+Set `config.debug` to `0` (silent), `1` (minimal), `2` (summary), `3` (full), or `4` (verbose raw details), then run with `DEBUG=ModelMix*`:
+
+```javascript
+const mix = ModelMix.new({ config: { debug: 4 } });
+```
+
+```bash
+DEBUG=ModelMix* node your-script.js
+```
+
 ## 🔌 Instance Plugins
 
 Plugins wrap one ModelMix instance without changing global behavior. They run in registration order after templates are rendered and before provider-specific request conversion:
@@ -953,7 +934,7 @@ The separately publishable `@modelmix/rlm` workspace package keeps document pars
 const { ModelMix } = require('modelmix');
 const { rlm } = require('@modelmix/rlm');
 
-const fast = ModelMix.new().gpt41mini();
+const fast = ModelMix.new().gpt5nano();
 
 const result = await ModelMix.new()
     .gpt56luna()

package/RLM_PLUGIN_SPEC.md

@@ -204,14 +204,14 @@ Proposed configuration:
 ```js
 const workers = {
     fast: {
-        model: ModelMix.new().gpt41nano(),
+        model: ModelMix.new().gpt5nano(),
         intelligence: 1,
         cost: 1,
         speed: 5,
         description: 'Extraction, classification, and simple transformations'
     },
     balanced: {
-        model: ModelMix.new().gpt41mini(),
+        model: ModelMix.new().gpt5nano(),
         intelligence: 3,
         cost: 2,
         speed: 4,

package/demo/fallback.js

@@ -15,7 +15,7 @@ const mmix = new ModelMix({
     }
 });
 
-mmix.sonnet46({ config: { url: 'fail' } }).gpt41nano();
+mmix.sonnet46({ config: { url: 'fail' } }).gpt5nano();
 
 async function main() {
     mmix.addText('hola, como estas?');
@@ -23,4 +23,4 @@ async function main() {
     console.log(response);
 }
 
-main();
+main();

package/demo/gemini.js

@@ -20,8 +20,8 @@ const flash = await mmix.gemini37flash()
 
 console.log(flash);
 
-// Using gemini3pro (Gemini 3 Pro) with custom config
-console.log("\n" + '--------| gemini3pro() with JSON response |--------');
+// Using Gemini 3.1 Pro with custom config
+console.log("\n" + '--------| gemini31pro() with JSON response |--------');
 const pro = mmix.new().gemini31pro();
 
 pro.addText('Give me a fun fact about cats');

package/demo/json.js

@@ -6,7 +6,7 @@ const model = await ModelMix.new({ options: { max_tokens: 10000 }, config: { deb
     // .gptOss()
     // .o4mini()
     // .gpt45()
-    // .gemini25flash()
+    // .gemini37flash()
     .addText("Name and capital of 3 South American countries.")
 
 const jsonResult = await model.json([{
@@ -24,4 +24,4 @@ const jsonResult = await model.json([{
 }], { addNote: true });
 
 console.log(jsonResult);
-console.log(model.lastRaw.tokens);
+console.log(model.lastRaw.tokens);

package/demo/mcp-simple.js

@@ -8,7 +8,7 @@ async function simpleCalculator() {
     console.log('\n=== Smart Calculator ===');
 
     const mmix = ModelMix.new()
-        .gpt41nano()
+        .gpt5nano()
         .setSystem('You are a smart calculator. Use the available tools to perform calculations.');
 
     // Add custom tool for advanced operations
@@ -93,7 +93,7 @@ async function contentGenerator() {
     console.log('\n=== Content Generator ===');
 
     const mmix = ModelMix.new({ config: { debug: 2, max_history: 1 } })
-        .gemini3flash()
+        .gemini37flash()
         .setSystem('You are a creative assistant that can generate different types of content.');
 
     // Tool for generating passwords

package/demo/mcp-tools.js

@@ -9,7 +9,7 @@ async function example1() {
     console.log('\n=== Example 1: Common Tools ===');
     
     const mmix = ModelMix.new({ config: { max_history: 10 } })
-        .gpt41nano();
+        .gpt5nano();
     
     // Add custom tools
     mmix.addTool({
@@ -66,7 +66,7 @@ async function example2() {
     console.log('\n=== Example 2: Custom Tool - Read Files ===');
     
     const mmix = ModelMix.new({ config: { max_history: 10 } })
-        .gpt41nano();
+        .gpt5nano();
 
     // Register custom tool for reading files
     mmix.addTool({
@@ -102,7 +102,7 @@ async function example3() {
     console.log('\n=== Example 3: HTTP Request Tool ===');
     
     const mmix = ModelMix.new({ config: { max_history: 10 } })
-        .gpt41nano();
+        .gpt5nano();
 
     // Register tool for making HTTP requests
     mmix.addTool({
@@ -158,7 +158,7 @@ async function example4() {
     console.log('\n=== Example 4: Multiple Tools Working Together ===');
     
     const mmix = ModelMix.new({ config: { max_history: 10 } })
-        .gpt41nano();
+        .gpt5nano();
 
     // Register multiple tools at once
     mmix.addTools([
@@ -248,7 +248,7 @@ async function example5() {
     console.log('\n=== Example 5: External MCP + Local Tools ===');
     
     const mmix = ModelMix.new({ config: { max_history: 10 } })
-        .gpt41nano();
+        .gpt5nano();
 
     // Add external MCP (if available)
     try {
@@ -341,7 +341,7 @@ async function runExamples() {
         console.log('\n✅ All examples completed');
         
         // Show registered tools
-        const mmix = ModelMix.new().gpt41nano();
+        const mmix = ModelMix.new().gpt5nano();
         mmix.addTool({
             name: "example_tool",
             description: "Example tool for demonstration",

package/demo/mcp.js

@@ -1,7 +1,7 @@
 import { ModelMix } from '../index.js';
 try { process.loadEnvFile(); } catch {}
 
-const mmix = ModelMix.new({ config: { max_history: 10 } }).gpt41nano();
+const mmix = ModelMix.new({ config: { max_history: 10 } }).gpt5nano();
 mmix.setSystem('You are an assistant and today is ' + new Date().toISOString());
 
 // Add web search capability through MCP

package/demo/parallel-strategy.js

@@ -129,7 +129,7 @@ async function genericRLMExample(variableName, variableData, task) {
             }
         } 
     })
-        .gpt41nano()
+        .gpt5nano()
         .setSystem(`You are a Recursive Language Model (RLM) agent.
 
 Data is in the ENVIRONMENT as variables, not in your context. You work programmatically:
@@ -282,7 +282,7 @@ You decide the strategy based on the data and task.`);
                     } 
                 });
                 
-                callMmix.gpt41mini();
+                callMmix.gpt5nano();
                 
                 if (call.system_prompt) {
                     callMmix.setSystem(call.system_prompt);
@@ -376,7 +376,7 @@ You decide the strategy based on the data and task.`);
                 max_history: 10
             } 
         })
-            .gpt41nano();
+            .gpt5nano();
         
         if (system_prompt) {
             recursiveMmix.setSystem(system_prompt);

package/demo/parallel.js

@@ -14,7 +14,7 @@ const mix = new ModelMix({
     }
 })
 
-mix.gpt41nano();
+mix.gpt5nano();
 
 // Function to create a promise that resolves after a random time
 const randomDelay = () => new Promise(resolve => setTimeout(resolve, Math.random() * 2000 + 1000));
@@ -48,4 +48,4 @@ async function runExample() {
 }
 
 // Run the example
-runExample().catch(console.error);
+runExample().catch(console.error);

package/demo/repl-powers.js

@@ -12,9 +12,9 @@ async function replPowersExample() {
     console.log('\n=== JavaScript REPL - Potencias de 2 ===\n');
     const gptArgs = { options: { reasoning_effort: "none", verbosity: null } };
     const mmix = ModelMix.new({ config: { debug: 2, max_history: 10 } })
-        .gpt41nano()
+        .gpt5nano()
         .gpt52(gptArgs)
-        .gemini3flash()
+        .gemini37flash()
         .setSystem('You are a helpful assistant with access to a JavaScript REPL. When you use the REPL and get results, always show them to the user in your response.');
 
     // Variable para capturar el resultado de la herramienta
@@ -74,4 +74,3 @@ try {
 } catch (error) {
     console.error('❌ Error:', error);
 }
-

package/demo/rlm-basic.js

@@ -36,7 +36,7 @@ async function basicRLM() {
     console.log('🎯 Query: "Find top Engineering talents with Python skills"\n');
 
     const mmix = ModelMix.new({ config: { debug: false, max_history: 20 } })
-        .gpt41nano()
+        .gpt5nano()
         .setSystem(`You are an RLM (Recursive Language Model). 
         
 Instead of reading all data at once, you:
@@ -135,7 +135,7 @@ Be strategic: think about what information you need and query only that.`);
 
         // Create a focused recursive call
         const subMmix = ModelMix.new({ config: { debug: false } })
-            .gpt41nano()
+            .gpt5nano()
             .setSystem(`Solve this focused sub-task concisely. Recursion level: ${recursionCount}`);
 
         subMmix.addText(`Context: ${context}\n\nTask: ${task}`);

package/demo/rlm-fast.js

@@ -50,7 +50,7 @@ async function createIvmContext(isolate, contextData, mmixInstance) {
     await jail.set('__mmixCallback', new ivm.Reference(async (system, message, outputJson) => {
         const output = JSON.parse(outputJson);
         const result = await mmixInstance.new()
-            .gpt41nano()
+            .gpt5nano()
             .setSystem(system)
             .addText(message)
             .json(output, output);
@@ -209,8 +209,8 @@ async function demo() {
     // Create base mmix instance for the callbacks
     const model = ModelMix.new({ config: { debug: 2, bottleneck: {} } })
         .gpt52({ options: { reasoning_effort: 'none', verbosity: null } })
-        .gpt41nano()
-        .gemini3flash();
+        .gpt5nano()
+        .gemini37flash();
 
     // Run the IVM task
     const result = await runIvmWithMmix({

package/demo/rlm-simple.js

@@ -105,9 +105,9 @@ async function rlmExample() {
 
     const gptArgs = { options: { reasoning_effort: "none", verbosity: null } };
     const mmix = ModelMix.new({ config: { debug: false, max_history: 15 } })
-        .gpt41nano()
+        .gpt5nano()
         .gpt52(gptArgs)
-        .gemini3flash()
+        .gemini37flash()
         .setSystem(`You are an RLM (Recursive Language Model) agent. 
         
 KEY PRINCIPLE: Instead of processing the entire document directly, you can:
@@ -216,7 +216,7 @@ Current recursion depth: ${recursionDepth}/${maxDepth}`);
 
         // Crear una nueva instancia para la llamada recursiva
         const recursiveMmix = ModelMix.new({ config: { debug: false } })
-            .gpt41nano()
+            .gpt5nano()
             .setSystem(`You are processing a sub-task. Be concise and direct.
 Recursion depth: ${recursionDepth}/${maxDepth}
 ${document_chunk ? 'Document chunk provided.' : 'No document chunk provided.'}`);

package/demo/short.js

@@ -12,8 +12,11 @@ const mmix = await ModelMix.new(setup)
     .sonnet46() // (main model) Anthropic claude-sonnet-4-6
     .gpt56luna() // (fallback 1) OpenAI gpt-5.6-luna
     .gemini37flash() // (fallback 2) Google gemini-3.7-flash
-    .gpt41nano() // (fallback 3) OpenAI gpt-4.1-nano
+    .gpt5nano() // (fallback 3) OpenAI gpt-5-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/demo/stream.js

@@ -1,7 +1,7 @@
 import { ModelMix } from '../index.js';
 try { process.loadEnvFile(); } catch {}
 
-await ModelMix.new().gpt41nano()
+await ModelMix.new().gpt5nano()
     .addImageFromUrl('https://pbs.twimg.com/media/F6-GsjraAAADDGy?format=jpg')
     .addText('describe')
     .stream((data) => { console.log(data.message); });

package/demo/tokens.js

@@ -26,7 +26,7 @@ console.log('-'.repeat(60));
 const providers = [
     { name: 'OpenAI GPT-5-nano', fn: (m) => m.gpt5nano() },
     { name: 'Anthropic Haiku', fn: (m) => m.haiku45() },
-    { name: 'Google Gemini', fn: (m) => m.gemini25flash() }
+    { name: 'Google Gemini', fn: (m) => m.gemini37flash() }
 ];
 
 const prompt = 'Explain quantum computing in one sentence.';

package/demo/verbose.js

@@ -18,7 +18,7 @@ console.log('──────────────────────
 
 await ModelMix
     .new({ config: { verbose: 0 } })
-    .gpt41nano()
+    .gpt5nano()
     .addText(prompt)
     .message();
 
@@ -33,7 +33,7 @@ console.log('──────────────────────
 
 await ModelMix
     .new({ config: { verbose: 1 } })
-    .gpt41nano()
+    .gpt5nano()
     .addText(prompt)
     .message();
 
@@ -48,7 +48,7 @@ console.log('──────────────────────
 
 await ModelMix
     .new({ config: { verbose: 2 } })
-    .gpt41nano()
+    .gpt5nano()
     .addText(prompt)
     .json({ message: 'string' });
 
@@ -63,7 +63,7 @@ console.log('──────────────────────
 
 await ModelMix
     .new({ config: { verbose: 3 } })
-    .gpt41nano()
+    .gpt5nano()
     .addText(prompt)
     .message();
 
@@ -79,7 +79,7 @@ try {
     const resultFallback = await ModelMix
         .new({ config: { verbose: 2 } })
         .attach('fake-model-that-will-fail', new MixOpenAI())
-        .gpt41nano() // This will be the fallback
+        .gpt5nano() // This will be the fallback
         .addText(prompt)
         .message();
 

package/effort.js

@@ -7,6 +7,7 @@
  */
 
 const OPENAI_LEVELS = ['none', 'low', 'medium', 'high', 'xhigh'];
+const OPENAI_LEVEL_LADDER = [...OPENAI_LEVELS, 'max'];
 const ANTHROPIC_LEVELS = ['low', 'medium', 'high', 'xhigh', 'max'];
 const GEMINI_LEVELS = ['minimal', 'low', 'medium', 'high'];
 
@@ -35,6 +36,10 @@ const GEMINI_BANDS = [
 
 /** Exact model → supported OpenAI reasoning_effort values */
 const OPENAI_MODEL_LEVELS = {
+    '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'],
+    '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'],
@@ -372,8 +377,11 @@ function mapEffort(providerFamily, effort, modelKey) {
         if (modelKey === GROK420_NON_REASONING) {
             return null;
         }
-        const desired = levelFromBands(normalized, OPENAI_BANDS);
-        const level = pickNearestLevel(desired, OPENAI_LEVELS, supportedOpenAILevels(modelKey));
+        const supported = supportedOpenAILevels(modelKey);
+        const desired = normalized === 100 && supported.includes('max')
+            ? 'max'
+            : levelFromBands(normalized, OPENAI_BANDS);
+        const level = pickNearestLevel(desired, OPENAI_LEVEL_LADDER, supported);
         return { reasoning_effort: level };
     }
 

package/index.d.ts

@@ -441,9 +441,6 @@ export declare class ModelMix {
   attach(key: string, provider: MixCustom): this;
 
   // OpenAI
-  gpt41(args?: ModelAttachArgs): this;
-  gpt41mini(args?: ModelAttachArgs): this;
-  gpt41nano(args?: ModelAttachArgs): this;
   gpt5(args?: ModelAttachArgs): this;
   gpt5mini(args?: ModelAttachArgs): this;
   gpt5nano(args?: ModelAttachArgs): this;
@@ -479,16 +476,12 @@ export declare class ModelMix {
   haiku45(args?: ModelAttachArgs): this;
 
   // Google
-  gemini25flash(args?: ModelAttachArgs): this;
   gemini31pro(args?: ModelAttachArgs): this;
-  gemini3pro(args?: ModelAttachArgs): this;
-  gemini3flash(args?: ModelAttachArgs): this;
   gemini37flash(args?: ModelAttachArgs): this;
   gemini36flash(args?: ModelAttachArgs): this;
   gemini35flash(args?: ModelAttachArgs): this;
   gemini35flashLite(args?: ModelAttachArgs): this;
   gemini31flashLite(args?: ModelAttachArgs): this;
-  gemini25pro(args?: ModelAttachArgs): this;
 
   // Perplexity
   sonarPro(args?: ModelAttachArgs): this;
@@ -504,16 +497,18 @@ 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;
   kimiK3(args?: ModelAttachArgs): this;
   kimiK25(args?: ModelAttachArgs): this;
   lmstudio(model?: string, args?: ModelAttachArgs): this;
-  minimaxM25(args?: ModelAttachArgs): this;
   minimaxM27(args?: ModelAttachArgs): this;
   minimaxM3(args?: ModelAttachArgs): this;
   mimo25(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)
@@ -402,19 +408,19 @@ const MODEL_PRICING = {
 };
 
 const CHAIN_MODEL_SHORTCUTS = new Set([
-    'gpt41', 'gpt41mini', 'gpt41nano', 'gpt5', 'gpt5mini', 'gpt5nano',
+    'gpt5', 'gpt5mini', 'gpt5nano',
     'gpt51', 'gpt52', 'gpt54', 'gpt54mini', 'gpt54nano', 'gpt54pro',
     'gpt55', 'gpt55pro', 'gpt56sol', 'gpt56terra', 'gpt56luna',
     'gptRealtime', 'gptRealtimeMini', 'gpt53codex', 'gpt53chat', 'gptOss',
     'fable50', 'fable5', 'opus50', 'opus5', 'opus48', 'opus47', 'opus46',
     'sonnet50', 'sonnet5', 'sonnet46', 'sonnet45', 'haiku45',
-    'gemini25flash', 'gemini31pro', 'gemini3pro', 'gemini3flash',
-    'gemini37flash', 'gemini36flash', 'gemini35flash', 'gemini35flashLite',
-    'gemini31flashLite', 'gemini25pro', 'sonarPro', 'sonar',
+    'gemini31pro', 'gemini37flash', 'gemini36flash', 'gemini35flash',
+    'gemini35flashLite', 'gemini31flashLite', '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',
+    'minimaxM27', 'minimaxM3', 'mimo25', 'mimo25pro',
     'deepseekV4Pro', 'deepseekV4Flash', 'GLM51', 'GLM52'
 ]);
 
@@ -923,15 +929,6 @@ class ModelMix {
         return this;
     }
 
-    gpt41({ options = {}, config = {} } = {}) {
-        return this.attach('gpt-4.1', new MixOpenAI({ options, config }));
-    }
-    gpt41mini({ options = {}, config = {} } = {}) {
-        return this.attach('gpt-4.1-mini', new MixOpenAI({ options, config }));
-    }
-    gpt41nano({ options = {}, config = {} } = {}) {
-        return this.attach('gpt-4.1-nano', new MixOpenAI({ options, config }));
-    }
     gpt5({ options = {}, config = {} } = {}) {
         return this.attach('gpt-5', new MixOpenAI({ options, config }));
     }
@@ -1030,18 +1027,9 @@ class ModelMix {
     haiku45({ options = {}, config = {} } = {}) {
         return this.attach('claude-haiku-4-5-20251001', new MixAnthropic({ options, config }));
     }
-    gemini25flash({ options = {}, config = {} } = {}) {
-        return this.attach('gemini-2.5-flash', new MixGoogle({ options, config }));
-    }
     gemini31pro({ options = {}, config = {} } = {}) {
         return this.attach('gemini-3.1-pro-preview', new MixGoogle({ options, config }));
     }    
-    gemini3pro({ options = {}, config = {} } = {}) {
-        return this.attach('gemini-3-pro-preview', new MixGoogle({ options, config }));
-    }
-    gemini3flash({ options = {}, config = {} } = {}) {
-        return this.attach('gemini-3-flash-preview', new MixGoogle({ options, config }));
-    }
     gemini37flash({ options = {}, config = {} } = {}) {
         return this.attach('gemini-3.7-flash', new MixGoogle({ options, config }));
     }
@@ -1057,9 +1045,6 @@ class ModelMix {
     gemini31flashLite({ options = {}, config = {} } = {}) {
         return this.attach('gemini-3.1-flash-lite-preview', new MixGoogle({ options, config }));
     }
-    gemini25pro({ options = {}, config = {} } = {}) {
-        return this.attach('gemini-2.5-pro', new MixGoogle({ options, config }));
-    }
     sonarPro({ options = {}, config = {} } = {}) {
         return this.attach('sonar-pro', new MixPerplexity({ options, config }));
     }
@@ -1090,6 +1075,10 @@ 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 +1093,21 @@ 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 }));
@@ -1151,12 +1149,6 @@ class ModelMix {
     }
 
 
-    minimaxM25({ options = {}, config = {}, mix = { minimax: true } } = {}) {
-        mix = { ...this.mix, ...mix };
-        if (mix.minimax) this.attach('MiniMax-M2.5', new MixMiniMax({ options, config }));
-        return this;
-    }
-
     minimaxM27({ options = {}, config = {}, mix = { openrouter: true, minimax: true } } = {}) {
         mix = { ...this.mix, ...mix };
         if (mix.nvidia) this.attach('minimaxai/minimax-m2.7', new MixNVIDIA({ options, config }));
@@ -1191,7 +1183,7 @@ 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": "5.1.1",
   "description": "🧬 Reliable interface with automatic fallback for AI LLMs.",
   "main": "index.js",
   "types": "index.d.ts",

package/skills/modelmix/SKILL.md

@@ -86,11 +86,11 @@ Chain shorthand methods to attach providers. First model is primary; others are
 const model = ModelMix.new()
     .sonnet46()        // primary
     .gpt52()           // fallback 1
-    .gemini3flash()    // fallback 2
+    .gemini37flash()   // fallback 2
     .addText("Hello!")
 ```
 
-If `sonnet46` fails, it automatically tries `gpt52`, then `gemini3flash`.
+If `sonnet46` fails, it automatically tries `gpt52`, then `gemini37flash`.
 
 The equivalent `chain()` form accepts public shortcut names directly in the
 same order. Append `@effort` for a per-model unified effort override (`-1` or
@@ -99,7 +99,7 @@ provider default when no chain effort is configured:
 
 ```javascript
 const model = ModelMix.new()
-    .chain('sonnet46', 'gpt52@20', 'gemini3flash@-1')
+    .chain('sonnet46', 'gpt52@20', 'gemini37flash@-1')
     .addText('Hello!');
 ```
 
@@ -143,7 +143,7 @@ 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. Gemini 3.7 Flash supports only `low` / `medium` / `high`, so the first two bands clamp to `low`; `-1` keeps its 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-5.6 maps `100` to `max`; 80–99 remains `xhigh`. Gemini bands: 0–24 / 25–49 / 50–74 / 75–100. Gemini 3.7 Flash supports only `low` / `medium` / `high`, so the first two bands clamp to `low`; `-1` keeps its 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
 
@@ -151,7 +151,7 @@ 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.
 
-`gpt52()` `gpt52chat()` `gpt51()` `gpt5()` `gpt5mini()` `gpt5nano()` `gpt45()` `gpt41()` `gpt41mini()` `gpt41nano()` `o3()` `o4mini()`
+`gpt52()` `gpt52chat()` `gpt51()` `gpt5()` `gpt5mini()` `gpt5nano()` `gpt45()` `o3()` `o4mini()`
 
 ### Anthropic
 `fable50()` `opus50()` `opus48()` `opus47()` `opus46()` `sonnet5()` `sonnet46()` `sonnet45()` `haiku45()`
@@ -159,7 +159,7 @@ Use `ModerationMix.new().openai()` with `.raw()` to classify text and images thr
 Use `.effort(n)` (or `config.effort`) to enable Anthropic thinking — e.g. `.effort(100).opus50()`. `fable5()` and `opus5()` remain available as compatibility aliases.
 
 ### Google
-`gemini3pro()` `gemini3flash()` `gemini37flash()` `gemini36flash()` `gemini35flash()` `gemini35flashLite()` `gemini31flashLite()` `gemini25pro()` `gemini25flash()`
+`gemini31pro()` `gemini37flash()` `gemini36flash()` `gemini35flash()` `gemini35flashLite()` `gemini31flashLite()`
 
 ### Grok
 `grok46()` `grok45()` `grok43()` `grok420multiAgent()` `grok420()`
@@ -174,16 +174,16 @@ Use `.effort(n)` (or `config.effort`) to enable Anthropic thinking — e.g. `.ef
 `kimiK3()` — requires `MOONSHOT_API_KEY`; use `{ mix: { moonshot: false, openrouter: true } }` for OpenRouter.
 
 ### MiniMax
-`minimaxM25()` `minimaxM27()` `minimaxM3()`
+`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()`
@@ -460,7 +460,7 @@ Omit all weights for equal probabilities. Otherwise every option needs a positiv
 const pool = ModelMix.new({ config: { roundRobin: true } })
     .gpt5mini()
     .sonnet45()
-    .gemini3flash();
+    .gemini37flash();
 
 const r1 = await pool.new().addText("Request 1").message();
 const r2 = await pool.new().addText("Request 2").message();

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

@@ -69,6 +69,14 @@ describe('Unified effort scale', () => {
             expect(mapEffort('openai', 10)).to.deep.equal({ reasoning_effort: 'none' });
             expect(mapEffort('openai', 50)).to.deep.equal({ reasoning_effort: 'medium' });
             expect(mapEffort('openai', 90)).to.deep.equal({ reasoning_effort: 'xhigh' });
+            expect(mapEffort('openai', 100)).to.deep.equal({ reasoning_effort: 'xhigh' });
+        });
+
+        it('maps GPT-5.6 maximum unified effort to max', () => {
+            expect(mapEffort('openai', 99, 'gpt-5.6-luna')).to.deep.equal({ reasoning_effort: 'xhigh' });
+            for (const model of ['gpt-5.6-sol', 'gpt-5.6-terra', 'gpt-5.6-luna']) {
+                expect(mapEffort('openai', 100, model)).to.deep.equal({ reasoning_effort: 'max' });
+            }
         });
 
         it('sets OpenAI adaptive only when supported (otherwise no-op)', () => {
@@ -81,6 +89,12 @@ 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 +192,10 @@ 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);
         });
@@ -349,6 +367,14 @@ describe('Unified effort scale', () => {
             expect(request.reasoning).to.deep.equal({ effort: 'none' });
         });
 
+        it('GPT-5.6 Luna .effort(100) sends max reasoning effort', () => {
+            const model = ModelMix.new().effort(100).gpt56luna();
+            const options = { model: 'gpt-5.6-luna', messages: [] };
+            applyUnifiedEffort(options, model.config, 'openai', 'gpt-5.6-luna');
+            const request = MixOpenAIResponses.buildResponsesRequest(options, {});
+            expect(request.reasoning).to.deep.equal({ effort: 'max' });
+        });
+
         it('Anthropic config.effort maps through .effort().opus50()', () => {
             const model = ModelMix.new().effort(100).opus50();
             expect(model.config.effort).to.equal(100);

package/test/fallback.test.js

@@ -60,6 +60,18 @@ describe('Provider Fallback Chain Tests', () => {
                 .to.throw('Invalid chain model at index 0: expected a model shortcut string.');
         });
 
+        it('should reject removed shortcuts from the public chain API', () => {
+            for (const shortcut of [
+                'gpt41', 'gpt41mini', 'gpt41nano',
+                'gemini25flash', 'gemini25pro', 'gemini3pro', 'gemini3flash',
+                'minimaxM25'
+            ]) {
+                expect(model[shortcut]).to.equal(undefined);
+                expect(() => model.chain(shortcut))
+                    .to.throw(`Unknown model shortcut "${shortcut}" in chain().`);
+            }
+        });
+
         it('should use primary provider when available', async () => {
             model.gpt5mini().sonnet46().addText('Hello');
 
@@ -195,7 +207,7 @@ describe('Provider Fallback Chain Tests', () => {
         });
 
         it('should cascade through multiple fallbacks', async () => {
-            model.gpt5mini().sonnet46().gemini3flash().addText('Hello');
+            model.gpt5mini().sonnet46().gemini37flash().addText('Hello');
 
             // Mock failed OpenAI response
             nock('https://api.openai.com')
@@ -279,7 +291,7 @@ describe('Provider Fallback Chain Tests', () => {
         });
 
         it('should fallback from Anthropic to Google', async () => {
-            model.sonnet46().gemini3flash().addText('Test message');
+            model.sonnet46().gemini37flash().addText('Test message');
 
             // Mock Anthropic failure
             nock('https://api.anthropic.com')
@@ -665,7 +677,7 @@ describe('Provider Fallback Chain Tests', () => {
         });
 
         it('should provide detailed error information when all fallbacks fail', async () => {
-            model.gpt5mini().sonnet46().gemini3flash().addText('Test');
+            model.gpt5mini().sonnet46().gemini37flash().addText('Test');
 
             // Mock all providers failing with different errors
             nock('https://api.openai.com')

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/history.test.js

@@ -570,7 +570,7 @@ describe('Conversation History Tests', () => {
             const model = ModelMix.new({
                 config: { debug: false, max_history: 10 }
             });
-            model.gemini3flash();
+            model.gemini37flash();
 
             model.addText('Hello');
             nock('https://generativelanguage.googleapis.com')

package/test/moderation.test.js

@@ -100,7 +100,7 @@ describe('OpenAI moderation', () => {
     it('rejects generative providers from the moderation chain', () => {
         const model = ModerationMix.new();
 
-        expect(() => model.gpt41nano()).to.throw(
+        expect(() => model.gpt5nano({ config: { apiKey: 'test-key' } })).to.throw(
             'ModerationMix only accepts moderation providers.'
         );
     });

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');
     });
 });