GITBOOK-483: docs: add 2 kimi2 and minimax m2

Author: techpro-aimlapi

docs/SUMMARY.md

@@ -75,6 +75,7 @@
   * [MiniMax](api-references/text-models-llm/MiniMax/README.md)
     * [text-01](api-references/text-models-llm/MiniMax/text-01.md)
     * [m1](api-references/text-models-llm/minimax/m1.md)
+    * [m2](api-references/text-models-llm/minimax/m2.md)
   * [Mistral AI](api-references/text-models-llm/Mistral-AI/README.md)
     * [codestral-2501](api-references/text-models-llm/Mistral-AI/codestral-2501.md)
     * [mistral-nemo](api-references/text-models-llm/Mistral-AI/mistral-nemo.md)
@@ -83,6 +84,7 @@
     * [Mixtral-8x7B-Instruct](api-references/text-models-llm/Mistral-AI/Mixtral-8x7B-Instruct-v0.1.md)
   * [Moonshot](api-references/text-models-llm/moonshot/README.md)
     * [kimi-k2-preview](api-references/text-models-llm/moonshot/kimi-k2-preview.md)
+    * [kimi-k2-turbo-preview](api-references/text-models-llm/moonshot/kimi-k2-turbo-preview.md)
   * [NousResearch](api-references/text-models-llm/nousresearch/README.md)
     * [hermes-4-405b](api-references/text-models-llm/nousresearch/hermes-4-405b.md)
   * [NVIDIA](api-references/text-models-llm/NVIDIA/README.md)
@@ -176,6 +178,7 @@
     * [Stable Diffusion v3.5 Large](api-references/image-models/Stability-AI/stable-diffusion-v35-large.md)
   * [Tencent](api-references/image-models/tencent/README.md)
     * [Hunyuan Image V3](api-references/image-models/tencent/hunyuan-image-v3-text-to-image.md)
+    * [Hunyuan Part](api-references/image-models/tencent/hunyuan-part.md)
   * [Topaz Labs](api-references/image-models/topaz-labs/README.md)
     * [Sharpen](api-references/image-models/topaz-labs/sharpen.md)
     * [Sharpen Generative](api-references/image-models/topaz-labs/sharpen-generative.md)
@@ -202,6 +205,7 @@
     * [Seedance 1.0 pro (Text-to-Video)](api-references/video-models/bytedance/seedance-1.0-pro-text-to-video.md)
     * [Seedance 1.0 pro (Image-to-Video)](api-references/video-models/bytedance/seedance-1.0-pro-image-to-video.md)
     * [OmniHuman](api-references/video-models/bytedance/omnihuman.md)
+    * [OmniHuman 1.5](api-references/video-models/bytedance/omnihuman-1.5.md)
   * [Google](api-references/video-models/google/README.md)
     * [Veo 2 (Text-to-Video)](api-references/video-models/google/veo2-text-to-video.md)
     * [Veo 2 (Image-to-Video)](api-references/video-models/google/veo2-image-to-video.md)

docs/api-references/image-models/tencent/hunyuan-image-v3-text-to-image.md

@@ -1,15 +1,15 @@
 # Hunyuan Image V3
 
 {% columns %}
-{% column width="75%" %}
+{% column width="66.66666666666666%" %}
 {% hint style="info" %}
 This documentation is valid for the following list of our models:
 
 * `hunyuan/hunyuan-image-v3-text-to-image`
 {% endhint %}
 {% endcolumn %}
 
-{% column width="25%" %}
+{% column width="33.33333333333334%" %}
 <a href="https://aimlapi.com/app/?model=hunyuan/hunyuan-image-v3-text-to-image&#x26;mode=image" class="button primary">Try in Playground</a>
 {% endcolumn %}
 {% endcolumns %}

docs/api-references/image-models/tencent/hunyuan-part.md

@@ -0,0 +1,129 @@
+---
+hidden: true
+noIndex: true
+---
+
+# Hunyuan Part
+
+{% columns %}
+{% column width="66.66666666666666%" %}
+{% hint style="info" %}
+This documentation is valid for the following list of our models:
+
+* `tencent/hunyuan-part`
+{% endhint %}
+{% endcolumn %}
+
+{% column width="33.33333333333334%" %}
+<a href="https://aimlapi.com/app/?model=hunyuan/hunyuan-image-v3-text-to-image&#x26;mode=image" class="button primary">Try in Playground</a>
+{% endcolumn %}
+{% endcolumns %}
+
+## Model Overview
+
+An advanced capabilities of Hunyuan Image 3.0 to generate compelling visuals that seamlessly enhance and communicate your written content.
+
+## Setup your API Key
+
+If you don’t have an API key for the AI/ML API yet, feel free to use our [Quickstart guide](https://docs.aimlapi.com/quickstart/setting-up).
+
+## API Schema
+
+{% openapi-operation spec="hunyuan-image-v3-text-to-image" path="/v1/images/generations" method="post" %}
+[OpenAPI hunyuan-image-v3-text-to-image](https://raw.githubusercontent.com/aimlapi/api-docs/refs/heads/main/docs/api-references/image-models/Tencent/hunyuan-image-v3-text-to-image.json)
+{% endopenapi-operation %}
+
+## Quick Example
+
+Let's generate an image using a simple prompt.
+
+{% tabs %}
+{% tab title="Python" %}
+{% code overflow="wrap" %}
+```python
+import requests
+import json
+
+def main():
+    response = requests.post(
+        "https://api.aimlapi.com/v1/images/generations",
+        headers={
+            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
+            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
+            "Content-Type": "application/json",
+        },
+        json={
+            "prompt": "A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.",
+            "model": "hunyuan/hunyuan-image-v3-text-to-image",
+            "image_size": "landscape_16_9"
+        }
+    )
+
+    data = response.json()
+    print(json.dumps(data, indent=2, ensure_ascii=False))
+
+if __name__ == "__main__":
+    main()
+```
+{% endcode %}
+{% endtab %}
+
+{% tab title="JS" %}
+{% code overflow="wrap" %}
+```javascript
+async function main() {
+  const response = await fetch('https://api.aimlapi.com/v1/images/generations', {
+    method: 'POST',
+    headers: {
+      // Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
+      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
+      'Content-Type': 'application/json',
+    },
+    body: JSON.stringify({
+      model: 'hunyuan/hunyuan-image-v3-text-to-image',
+      prompt: 'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses. Realistic photo.',
+      image_size: 'landscape_16_9'
+    }),
+  });
+
+  const data = await response.json();
+  console.log(data);
+}
+
+main();
+```
+{% endcode %}
+{% endtab %}
+{% endtabs %}
+
+<details>
+
+<summary>Response</summary>
+
+{% code overflow="wrap" %}
+```json5
+{
+    "data": [
+        {
+            "url": "https://v3b.fal.media/files/b/lion/JdrvNguTlt29LmURRbKKN.png",
+            "content_type": "image/png",
+            "file_name": null,
+            "file_size": null,
+            "width": 1280,
+            "height": 768
+        }
+    ],
+    "meta": {
+        "usage": {
+            "tokens_used": 210000
+        }
+    }
+}
+```
+{% endcode %}
+
+</details>
+
+We obtained the following 1280x768 image by running this code example:
+
+<figure><img src="https://v3b.fal.media/files/b/lion/JdrvNguTlt29LmURRbKKN.png" alt=""><figcaption><p>A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.</p></figcaption></figure>

docs/api-references/model-database.md

@@ -0,0 +1,144 @@
+# m2
+
+<table data-header-hidden data-full-width="true"><thead><tr><th width="546.4443969726562" valign="top"></th><th width="202.666748046875" valign="top"></th></tr></thead><tbody><tr><td valign="top"><div data-gb-custom-block data-tag="hint" data-style="info" class="hint hint-info"><p>This documentation is valid for the following list of our models:</p><ul><li><code>minimax/m2</code></li></ul></div></td><td valign="top"><a href="https://aimlapi.com/app/?model=minimax/m2&#x26;mode=chat" class="button primary">Try in Playground</a></td></tr></tbody></table>
+
+## Model Overview
+
+A high-performance language model optimized for coding and autonomous agent workflows.
+
+## How to Make a Call
+
+<details>
+
+<summary>Step-by-Step Instructions</summary>
+
+### :digit\_one:  Setup You Can’t Skip
+
+:black\_small\_square:  [**Create an Account**](https://aimlapi.com/app/sign-up): Visit the AI/ML API website and create an account (if you don’t have one yet).\
+:black\_small\_square:  [**Generate an API Key**](https://aimlapi.com/app/keys): After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.
+
+### :digit\_two:  Copy the code example
+
+At the bottom of this page, you'll find [a code example](m2.md#code-example) that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.
+
+### :digit\_three:  Modify the code example
+
+:black\_small\_square:  Replace `<YOUR_AIMLAPI_KEY>` with your actual AI/ML API key from your account.\
+:black\_small\_square:  Insert your question or request into the `content` field—this is what the model will respond to.
+
+### :digit\_four:  <sup><sub><mark style="background-color:yellow;">(Optional)<mark style="background-color:yellow;"><sub></sup> Adjust other optional parameters if needed
+
+Only `model` and `messages` are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding [API schema](m2.md#api-schema), which lists all available parameters along with notes on how to use them.
+
+### :digit\_five:  Run your modified code
+
+Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.
+
+{% hint style="success" %}
+If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our [Quickstart guide](../../../quickstart/setting-up.md).
+{% endhint %}
+
+</details>
+
+## API Schema
+
+{% openapi-operation spec="m2" path="/v1/chat/completions" method="post" %}
+[OpenAPI m2](https://raw.githubusercontent.com/aimlapi/api-docs/refs/heads/main/docs/api-references/text-models-llm/MiniMax/m2.json)
+{% endopenapi-operation %}
+
+## Code Example
+
+{% tabs %}
+{% tab title="Python" %}
+{% code overflow="wrap" %}
+```python
+import requests
+import json  # for getting a structured output with indentation 
+
+response = requests.post(
+    "https://api.aimlapi.com/v1/chat/completions",
+    headers={
+        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
+        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
+        "Content-Type":"application/json"
+    },
+    json={
+        "model":"minimax/m2",
+        "messages":[
+            {
+                "role":"user",
+                "content":"Hello"  # insert your prompt here, instead of Hello
+            }
+        ]
+    }
+)
+
+data = response.json()
+print(json.dumps(data, indent=2, ensure_ascii=False))
+```
+{% endcode %}
+{% endtab %}
+
+{% tab title="JavaScript" %}
+{% code overflow="wrap" %}
+```javascript
+async function main() {
+  const response = await fetch('https://api.aimlapi.com/v1/chat/completions', {
+    method: 'POST',
+    headers: {
+      // insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>
+      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
+      'Content-Type': 'application/json',
+    },
+    body: JSON.stringify({
+      model: 'minimax/m2',
+      messages:[
+          {
+              role:'user',
+              content: 'Hello'  // insert your prompt here, instead of Hello
+          }
+      ],
+    }),
+  });
+
+  const data = await response.json();
+  console.log(JSON.stringify(data, null, 2));
+}
+
+main();
+```
+{% endcode %}
+{% endtab %}
+{% endtabs %}
+
+<details>
+
+<summary>Response</summary>
+
+{% code overflow="wrap" %}
+```json5
+{
+  "id": "0557b8f7fa197172a75531a82ae6c887",
+  "object": "chat.completion",
+  "choices": [
+    {
+      "index": 0,
+      "finish_reason": "stop",
+      "message": {
+        "role": "assistant",
+        "content": "<think>\nThe user says \"Hello\". This is a simple greeting. There's no request. According to policy, we respond politely, perhaps ask how we can help. So answer \"Hello! How can I assist you today?\" Should keep tone friendly.\n\nThus final answer.\n</think>\n\nHello! How can I help you today?"
+      }
+    }
+  ],
+  "created": 1762166263,
+  "model": "MiniMax-M2",
+  "usage": {
+    "prompt_tokens": 26,
+    "completion_tokens": 159,
+    "total_tokens": 185
+  }
+}
+```
+{% endcode %}
+
+</details>

docs/api-references/text-models-llm/README.md

@@ -1,10 +1,12 @@
 # kimi-k2-preview
 
-<table data-header-hidden data-full-width="true"><thead><tr><th width="546.4443969726562" valign="top"></th><th width="202.666748046875" valign="top"></th></tr></thead><tbody><tr><td valign="top"><div data-gb-custom-block data-tag="hint" data-style="info" class="hint hint-info"><p>This documentation is valid for the following model:  <br> <code>moonshot/kimi-k2-preview</code></p></div></td><td valign="top"><a href="https://aimlapi.com/app/?model=moonshot/kimi-k2-preview&#x26;mode=chat" class="button primary">Try in Playground</a></td></tr></tbody></table>
+<table data-header-hidden data-full-width="true"><thead><tr><th width="546.4443969726562" valign="top"></th><th width="202.666748046875" valign="top"></th></tr></thead><tbody><tr><td valign="top"><div data-gb-custom-block data-tag="hint" data-style="info" class="hint hint-info"><p>This documentation is valid for the following list of our models:</p><ul><li> <code>moonshot/kimi-k2-preview</code> </li><li><code>moonshot/kimi-k2-0905-preview</code> </li></ul></div></td><td valign="top"><a href="https://aimlapi.com/app/?model=moonshot/kimi-k2-preview&#x26;mode=chat" class="button primary">Try in Playground</a> <br><a href="https://aimlapi.com/app/?model=moonshot/kimi-k2-0905-preview&#x26;mode=chat" class="button primary">Try in Playground</a></td></tr></tbody></table>
 
 ## Model Overview
 
-A mixture-of-experts model with strong reasoning, coding, and agentic capabilities.
+`moonshot/kimi-k2-preview` (July 2025) is a mixture-of-experts model with strong reasoning, coding, and agentic capabilities.
+
+`moonshot/kimi-k2-0905-preview` (September 2025) is an upgraded version with improved grounding, better instruction following, and a stronger focus on coding and agentic tasks. The memory has doubled from 128k to a decent 256k tokens.
 
 ## How to Make a Call
 
@@ -63,7 +65,7 @@ response = requests.post(
         "Content-Type":"application/json"
     },
     json={
-        "model":"moonshot/kimi-k2-preview",
+        "model":"moonshot/kimi-k2-0905-preview",
         "messages":[
             {
                 "role":"user",
@@ -91,7 +93,7 @@ async function main() {
       'Content-Type': 'application/json',
     },
     body: JSON.stringify({
-      model: 'moonshot/kimi-k2-preview',
+      model: 'moonshot/kimi-k2-0905-preview',
       messages:[
           {
               role:'user',
@@ -118,7 +120,7 @@ main();
 {% code overflow="wrap" %}
 ```json5
 {
-  "id": "chatcmpl-6881021ed173a2ae63fab92b",
+  "id": "chatcmpl-6908c55b7589dac387b2bd3b",
   "object": "chat.completion",
   "choices": [
     {
@@ -130,12 +132,12 @@ main();
       }
     }
   ],
-  "created": 1753285150,
-  "model": "kimi-k2-0711-preview",
+  "created": 1762182491,
+  "model": "kimi-k2-0905-preview",
   "usage": {
-    "prompt_tokens": 11,
+    "prompt_tokens": 3,
     "completion_tokens": 53,
-    "total_tokens": 64
+    "total_tokens": 56
   }
 }
 ```
@@ -170,7 +172,7 @@ def search_impl(arguments: Dict[str, Any]) -> Any:
 def chat(messages):
     url = f"{BASE_URL}/chat/completions"
     payload = {
-        "model": "moonshot/kimi-k2-preview",
+        "model": "moonshot/kimi-k2-0905-preview",
         "messages": messages,
         "temperature": 0.6,
         "tools": [