Add new model provider Novita AI (#7582) (#9527)

* Add new model provider Novita AI (#7582) * feat: add new model provider Novita AI * feat: use deepseek r1 model for examples in Novita AI docs * fix: fix tests * fix: fix tests for novita * fix: fix novita transformation * ci: fix ci yaml * fix: fix novita transformation and test (#10056) --------- Co-authored-by: Jason <ggbbddjm@gmail.com>
2025-12-06 11:33:26 +08:00 · 2025-05-12 21:49:30 -07:00
parent be9ce96a64
commit d37cc63250
22 changed files with 498 additions and 63 deletions
--- a/.env.example
+++ b/.env.example
@@ -20,10 +20,12 @@ REPLICATE_API_TOKEN = ""
 ANTHROPIC_API_KEY = ""
 # Infisical
 INFISICAL_TOKEN = ""
+# Novita AI
+NOVITA_API_KEY = ""
 # INFINITY
 INFINITY_API_KEY = ""

 # Development Configs
 LITELLM_MASTER_KEY = "sk-1234"
 DATABASE_URL = "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
-STORE_MODEL_IN_DB = "True"
+STORE_MODEL_IN_DB = "True"
--- a/README.md
+++ b/README.md
@@ -332,6 +332,7 @@ curl 'http://0.0.0.0:4000/key/generate' \
 | [xinference [Xorbits Inference]](https://docs.litellm.ai/docs/providers/xinference) |                                                         |                                                                                 |                                                                                     |                                                                                   | ✅                                                                             |                                                                         |
 | [FriendliAI](https://docs.litellm.ai/docs/providers/friendliai)                              | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
 | [Galadriel](https://docs.litellm.ai/docs/providers/galadriel)                              | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |
+| [Novita AI](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link)                     | ✅                                                       | ✅                                                                               | ✅                                                                                   | ✅                                                                                 |                                                                               |                                                                         |

 [**Read the Docs**](https://docs.litellm.ai/docs/)

--- a/cookbook/LiteLLM_NovitaAI_Cookbook.ipynb
+++ b/cookbook/LiteLLM_NovitaAI_Cookbook.ipynb
@@ -0,0 +1,97 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "iFEmsVJI_2BR"
+      },
+      "source": [
+        "# LiteLLM NovitaAI Cookbook"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cBlUhCEP_xj4"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install litellm"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "p-MQqWOT_1a7"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "os.environ['NOVITA_API_KEY'] = \"\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Ze8JqMqWAARO"
+      },
+      "outputs": [],
+      "source": [
+        "from litellm import completion\n",
+        "response = completion(\n",
+        "            model=\"novita/deepseek/deepseek-r1\",\n",
+        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
+        ")\n",
+        "response"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-LnhELrnAM_J"
+      },
+      "outputs": [],
+      "source": [
+        "response = completion(\n",
+        "            model=\"novita/deepseek/deepseek-r1\",\n",
+        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
+        ")\n",
+        "response"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dJBOUYdwCEn1"
+      },
+      "outputs": [],
+      "source": [
+        "response = completion(\n",
+        "            model=\"mistralai/mistral-7b-instruct\",\n",
+        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
+        ")\n",
+        "response"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}
--- a/cookbook/LiteLLM_OpenRouter.ipynb
+++ b/cookbook/LiteLLM_OpenRouter.ipynb
@@ -1,27 +1,13 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
  "cells": [
    {
      "cell_type": "markdown",
-      "source": [
-        "# LiteLLM OpenRouter Cookbook"
-      ],
      "metadata": {
        "id": "iFEmsVJI_2BR"
-      }
+      },
+      "source": [
+        "# LiteLLM OpenRouter Cookbook"
+      ]
    },
    {
      "cell_type": "code",
@@ -36,27 +22,20 @@
    },
    {
      "cell_type": "code",
+      "execution_count": 14,
+      "metadata": {
+        "id": "p-MQqWOT_1a7"
+      },
+      "outputs": [],
      "source": [
        "import os\n",
        "\n",
        "os.environ['OPENROUTER_API_KEY'] = \"\""
-      ],
-      "metadata": {
-        "id": "p-MQqWOT_1a7"
-      },
-      "execution_count": 14,
-      "outputs": []
+      ]
    },
    {
      "cell_type": "code",
-      "source": [
-        "from litellm import completion\n",
-        "response = completion(\n",
-        "            model=\"openrouter/google/palm-2-chat-bison\",\n",
-        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
-        ")\n",
-        "response"
-      ],
+      "execution_count": 11,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
@@ -64,10 +43,8 @@
        "id": "Ze8JqMqWAARO",
        "outputId": "64f3e836-69fa-4f8e-fb35-088a913bbe98"
      },
-      "execution_count": 11,
      "outputs": [
        {
-          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<OpenAIObject id=gen-W8FTMSIEorCp3vG5iYIgNMR4IeBv at 0x7c3dcef1f060> JSON: {\n",
@@ -85,20 +62,23 @@
              "}"
            ]
          },
+          "execution_count": 11,
          "metadata": {},
-          "execution_count": 11
+          "output_type": "execute_result"
        }
+      ],
+      "source": [
+        "from litellm import completion\n",
+        "response = completion(\n",
+        "            model=\"openrouter/google/palm-2-chat-bison\",\n",
+        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
+        ")\n",
+        "response"
      ]
    },
    {
      "cell_type": "code",
-      "source": [
-        "response = completion(\n",
-        "            model=\"openrouter/anthropic/claude-2\",\n",
-        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
-        ")\n",
-        "response"
-      ],
+      "execution_count": 12,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
@@ -106,10 +86,8 @@
        "id": "-LnhELrnAM_J",
        "outputId": "d51c7ab7-d761-4bd1-f849-1534d9df4cd0"
      },
-      "execution_count": 12,
      "outputs": [
        {
-          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<OpenAIObject id=gen-IiuV7ZNimDufVeutBHrl8ajPuzEh at 0x7c3dcea67560> JSON: {\n",
@@ -128,20 +106,22 @@
              "}"
            ]
          },
+          "execution_count": 12,
          "metadata": {},
-          "execution_count": 12
+          "output_type": "execute_result"
        }
+      ],
+      "source": [
+        "response = completion(\n",
+        "            model=\"openrouter/anthropic/claude-2\",\n",
+        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
+        ")\n",
+        "response"
      ]
    },
    {
      "cell_type": "code",
-      "source": [
-        "response = completion(\n",
-        "            model=\"openrouter/meta-llama/llama-2-70b-chat\",\n",
-        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
-        ")\n",
-        "response"
-      ],
+      "execution_count": 13,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
@@ -149,10 +129,8 @@
        "id": "dJBOUYdwCEn1",
        "outputId": "ffa18679-ec15-4dad-fe2b-68665cdf36b0"
      },
-      "execution_count": 13,
      "outputs": [
        {
-          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<OpenAIObject id=gen-PyMd3yyJ0aQsCgIY9R8XGZoAtPbl at 0x7c3dceefcae0> JSON: {\n",
@@ -170,10 +148,32 @@
              "}"
            ]
          },
+          "execution_count": 13,
          "metadata": {},
-          "execution_count": 13
+          "output_type": "execute_result"
        }
+      ],
+      "source": [
+        "response = completion(\n",
+        "            model=\"openrouter/meta-llama/llama-2-70b-chat\",\n",
+        "            messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
+        ")\n",
+        "response"
      ]
    }
-  ]
-}
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}
--- a/docs/my-website/docs/completion/input.md
+++ b/docs/my-website/docs/completion/input.md
@@ -62,6 +62,7 @@ Use `litellm.get_supported_openai_params()` for an updated list of params for ea
 |Databricks| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |  |   | |  |   | | | | | |
 |ClarifAI| ✅ | ✅ | ✅ | |✅ | ✅ |  |   | |  |   | | | | | |
 |Github| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | | | | ✅ |✅ (model dependent)|✅ (model dependent)| | |
+|Novita AI| ✅ | ✅ |  | ✅ | ✅ | ✅ |  | ✅ | ✅ | ✅ | ✅ |  |  | ✅ |  |  |  |  |  |  |  |
 :::note

 By default, LiteLLM raises an exception if the openai param being passed in isn't supported. 
--- a/docs/my-website/docs/index.md
+++ b/docs/my-website/docs/index.md
@@ -208,6 +208,22 @@ response = completion(
 )
 ```

+</TabItem>
+<TabItem value="novita" label="Novita AI">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables. Visit https://novita.ai/settings/key-management to get your API key
+os.environ["NOVITA_API_KEY"] = "novita-api-key"
+
+response = completion(
+  model="novita/deepseek/deepseek-r1",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+
 </TabItem>

 </Tabs>
@@ -411,6 +427,23 @@ response = completion(
 )
 ```

+</TabItem>
+<TabItem value="novita" label="Novita AI">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables. Visit https://novita.ai/settings/key-management to get your API key
+os.environ["NOVITA_API_KEY"] = "novita_api_key"
+
+response = completion(
+  model="novita/deepseek/deepseek-r1",
+  messages = [{ "content": "Hello, how are you?","role": "user"}],
+  stream=True,
+)
+```
+
 </TabItem>

 </Tabs>
--- a/docs/my-website/docs/providers/novita.md
+++ b/docs/my-website/docs/providers/novita.md
@@ -0,0 +1,39 @@
+# Novita AI
+LiteLLM supports all models from [Novita AI](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link)
+
+## Usage
+```python
+import os
+from litellm import completion
+os.environ["NOVITA_API_KEY"] = ""
+
+response = completion(
+            model="meta-llama/llama-3.3-70b-instruct",
+            messages=messages,
+        )
+```
+
+## Novita AI Completion Models
+
+🚨 LiteLLM supports ALL Novita AI models, send `model=novita/<your-novita-model>` to send it to Novita AI. See all Novita AI models [here](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link)
+
+| Model Name                | Function Call                                       |
+|---------------------------|-----------------------------------------------------|
+| novita/deepseek/deepseek-r1 | `completion('novita/deepseek/deepseek-r1', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/deepseek/deepseek_v3 | `completion('novita/deepseek/deepseek_v3', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.3-70b-instruct | `completion('novita/meta-llama/llama-3.3-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.1-8b-instruct | `completion('novita/meta-llama/llama-3.1-8b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.1-8b-instruct-max | `completion('novita/meta-llama/llama-3.1-8b-instruct-max', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.1-70b-instruct | `completion('novita/meta-llama/llama-3.1-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3-8b-instruct | `completion('novita/meta-llama/llama-3-8b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3-70b-instruct | `completion('novita/meta-llama/llama-3-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.2-1b-instruct | `completion('novita/meta-llama/llama-3.2-1b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.2-11b-vision-instruct | `completion('novita/meta-llama/llama-3.2-11b-vision-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.2-3b-instruct | `completion('novita/meta-llama/llama-3.2-3b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/gryphe/mythomax-l2-13b | `completion('novita/gryphe/mythomax-l2-13b', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/google/gemma-2-9b-it | `completion('novita/google/gemma-2-9b-it', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/mistralai/mistral-nemo | `completion('novita/mistralai/mistral-nemo', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/mistralai/mistral-7b-instruct | `completion('novita/mistralai/mistral-7b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/qwen/qwen-2.5-72b-instruct | `completion('novita/qwen/qwen-2.5-72b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/qwen/qwen-2-vl-72b-instruct | `completion('novita/qwen/qwen-2-vl-72b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -354,6 +354,7 @@ const sidebars = {
        "providers/nlp_cloud",
        "providers/replicate",
        "providers/togetherai",
+        "providers/novita",
        "providers/voyage",
        "providers/jina_ai",
        "providers/aleph_alpha",
--- a/docs/my-website/src/pages/completion/input.md
+++ b/docs/my-website/src/pages/completion/input.md
@@ -1,6 +1,6 @@
 # Completion Function - completion()
 The Input params are **exactly the same** as the 
-<a href="https://platform.openai.com/docs/api-reference/chat/create" target="_blank" rel="noopener noreferrer">OpenAI Create chat completion</a>, and let you call **Azure OpenAI, Anthropic, Cohere, Replicate, OpenRouter** models in the same format. 
+<a href="https://platform.openai.com/docs/api-reference/chat/create" target="_blank" rel="noopener noreferrer">OpenAI Create chat completion</a>, and let you call **Azure OpenAI, Anthropic, Cohere, Replicate, OpenRouter, Novita AI** models in the same format. 

 In addition, liteLLM allows you to pass in the following **Optional** liteLLM args:
 `force_timeout`, `azure`, `logger_fn`, `verbose`
--- a/docs/my-website/src/pages/completion/supported.md
+++ b/docs/my-website/src/pages/completion/supported.md
@@ -70,4 +70,28 @@ All the text models from [OpenRouter](https://openrouter.ai/docs) are supported
 | google/palm-2-chat-bison | `completion('google/palm-2-chat-bison', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OR_API_KEY']`       |
 | google/palm-2-codechat-bison | `completion('google/palm-2-codechat-bison', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OR_API_KEY']`       |
 | meta-llama/llama-2-13b-chat | `completion('meta-llama/llama-2-13b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OR_API_KEY']`       |
-| meta-llama/llama-2-70b-chat | `completion('meta-llama/llama-2-70b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OR_API_KEY']`       |
+| meta-llama/llama-2-70b-chat | `completion('meta-llama/llama-2-70b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OR_API_KEY']`       |
+
+## Novita AI Completion Models
+
+🚨 LiteLLM supports ALL Novita AI models, send `model=novita/<your-novita-model>` to send it to Novita AI. See all Novita AI models [here](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link)
+
+| Model Name       | Function Call                              | Required OS Variables                |
+|------------------|--------------------------------------------|--------------------------------------|
+| novita/deepseek/deepseek-r1 | `completion('novita/deepseek/deepseek-r1', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/deepseek/deepseek_v3 | `completion('novita/deepseek/deepseek_v3', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.3-70b-instruct | `completion('novita/meta-llama/llama-3.3-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.1-8b-instruct | `completion('novita/meta-llama/llama-3.1-8b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.1-8b-instruct-max | `completion('novita/meta-llama/llama-3.1-8b-instruct-max', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.1-70b-instruct | `completion('novita/meta-llama/llama-3.1-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3-8b-instruct | `completion('novita/meta-llama/llama-3-8b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3-70b-instruct | `completion('novita/meta-llama/llama-3-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.2-1b-instruct | `completion('novita/meta-llama/llama-3.2-1b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.2-11b-vision-instruct | `completion('novita/meta-llama/llama-3.2-11b-vision-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/meta-llama/llama-3.2-3b-instruct | `completion('novita/meta-llama/llama-3.2-3b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/gryphe/mythomax-l2-13b | `completion('novita/gryphe/mythomax-l2-13b', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/google/gemma-2-9b-it | `completion('novita/google/gemma-2-9b-it', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/mistralai/mistral-nemo | `completion('novita/mistralai/mistral-nemo', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/mistralai/mistral-7b-instruct | `completion('novita/mistralai/mistral-7b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/qwen/qwen-2.5-72b-instruct | `completion('novita/qwen/qwen-2.5-72b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
+| novita/qwen/qwen-2-vl-72b-instruct | `completion('novita/qwen/qwen-2-vl-72b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
--- a/docs/my-website/src/pages/index.md
+++ b/docs/my-website/src/pages/index.md
@@ -194,6 +194,22 @@ response = completion(
 )
 ```

+</TabItem>
+<TabItem value="novita" label="Novita AI">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables. Visit https://novita.ai/settings/key-management to get your API key
+os.environ["NOVITA_API_KEY"] = "novita-api-key"
+
+response = completion(
+  model="novita/deepseek/deepseek-r1",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+
 </TabItem>

 </Tabs>
@@ -347,7 +363,23 @@ response = completion(
 ```

 </TabItem>
+<TabItem value="novita" label="Novita AI">

+```python
+from litellm import completion
+import os
+
+## set ENV variables. Visit https://novita.ai/settings/key-management to get your API key
+os.environ["NOVITA_API_KEY"] = "novita_api_key"
+
+response = completion(
+  model="novita/deepseek/deepseek-r1",
+  messages = [{ "content": "Hello, how are you?","role": "user"}],
+  stream=True,
+)
+```
+
+</TabItem>
 </Tabs>

 ### Exception handling 
--- a/litellm/init.py
+++ b/litellm/init.py
@@ -199,6 +199,7 @@ baseten_key: Optional[str] = None
 llama_api_key: Optional[str] = None
 aleph_alpha_key: Optional[str] = None
 nlp_cloud_key: Optional[str] = None
+novita_api_key: Optional[str] = None
 snowflake_key: Optional[str] = None
 common_cloud_provider_auth_params: dict = {
    "params": ["project", "region_name", "token"],
@@ -440,12 +441,12 @@ anyscale_models: List = []
 cerebras_models: List = []
 galadriel_models: List = []
 sambanova_models: List = []
+novita_models: List = []
 assemblyai_models: List = []
 snowflake_models: List = []
 llama_models: List = []
 nscale_models: List = []

-
 def is_bedrock_pricing_only_model(key: str) -> bool:
    """
    Excludes keys with the pattern 'bedrock/<region>/<model>'. These are in the model_prices_and_context_window.json file for pricing purposes only.
@@ -599,6 +600,8 @@ def add_known_models():
            galadriel_models.append(key)
        elif value.get("litellm_provider") == "sambanova_models":
            sambanova_models.append(key)
+        elif value.get("litellm_provider") == "novita":
+            novita_models.append(key)
        elif value.get("litellm_provider") == "assemblyai":
            assemblyai_models.append(key)
        elif value.get("litellm_provider") == "jina_ai":
@@ -678,6 +681,7 @@ model_list = (
    + galadriel_models
    + sambanova_models
    + azure_text_models
+    + novita_models
    + assemblyai_models
    + jina_ai_models
    + snowflake_models
@@ -737,6 +741,7 @@ models_by_provider: dict = {
    "cerebras": cerebras_models,
    "galadriel": galadriel_models,
    "sambanova": sambanova_models,
+    "novita": novita_models,
    "assemblyai": assemblyai_models,
    "jina_ai": jina_ai_models,
    "snowflake": snowflake_models,
@@ -878,6 +883,7 @@ from .llms.bedrock.messages.invoke_transformations.anthropic_claude3_transformat
 from .llms.together_ai.chat import TogetherAIConfig
 from .llms.together_ai.completion.transformation import TogetherAITextCompletionConfig
 from .llms.cloudflare.chat.transformation import CloudflareChatConfig
+from .llms.novita.chat.transformation import NovitaConfig
 from .llms.deprecated_providers.palm import (
    PalmConfig,
 )  # here to prevent breaking changes
--- a/litellm/constants.py
+++ b/litellm/constants.py
@@ -161,6 +161,7 @@ LITELLM_CHAT_PROVIDERS = [
    "llamafile",
    "lm_studio",
    "galadriel",
+    "novita",
    "meta_llama",
    "nscale",
 ]
@@ -255,6 +256,7 @@ openai_compatible_providers: List = [
    "llamafile",
    "lm_studio",
    "galadriel",
+    "novita",
    "meta_llama",
    "nscale",
 ]
--- a/litellm/litellm_core_utils/get_llm_provider_logic.py
+++ b/litellm/litellm_core_utils/get_llm_provider_logic.py
@@ -604,6 +604,13 @@ def _get_openai_compatible_provider_info(  # noqa: PLR0915
            or "https://api.galadriel.com/v1"
        )  # type: ignore
        dynamic_api_key = api_key or get_secret_str("GALADRIEL_API_KEY")
+    elif custom_llm_provider == "novita":
+        api_base = (
+            api_base
+            or get_secret("NOVITA_API_BASE")
+            or "https://api.novita.ai/v3/openai"
+        )  # type: ignore
+        dynamic_api_key = api_key or get_secret_str("NOVITA_API_KEY")
    elif custom_llm_provider == "snowflake":
        api_base = (
            api_base
--- a/litellm/litellm_core_utils/get_supported_openai_params.py
+++ b/litellm/litellm_core_utils/get_supported_openai_params.py
@@ -155,6 +155,8 @@ def get_supported_openai_params(  # noqa: PLR0915
        return litellm.GoogleAIStudioGeminiConfig().get_supported_openai_params(
            model=model
        )
+    elif custom_llm_provider == "novita":
+        return litellm.NovitaConfig().get_supported_openai_params(model=model)
    elif custom_llm_provider == "vertex_ai" or custom_llm_provider == "vertex_ai_beta":
        if request_type == "chat_completion":
            if model.startswith("mistral"):
--- a/litellm/llms/novita/chat/transformation.py
+++ b/litellm/llms/novita/chat/transformation.py
@@ -0,0 +1,33 @@
+"""
+Support for OpenAI's `/v1/chat/completions` endpoint. 
+
+Calls done in OpenAI/openai.py as Novita AI is openai-compatible.
+
+Docs: https://novita.ai/docs/guides/llm-api
+"""
+
+from typing import List, Optional
+
+from ....types.llms.openai import AllMessageValues
+from ...openai.chat.gpt_transformation import OpenAIGPTConfig
+
+
+class NovitaConfig(OpenAIGPTConfig):
+    def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> dict:
+        if api_key is None:
+            raise ValueError(
+                "Missing Novita AI API Key - A call is being made to novita but no key is set either in the environment variables or via params"
+            )
+        headers["Authorization"] = f"Bearer {api_key}"
+        headers["Content-Type"] = "application/json"
+        headers["X-Novita-Source"] = "litellm"
+        return headers
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -3328,7 +3328,6 @@ async def aembedding(*args, **kwargs) -> EmbeddingResponse:
            response = init_response
        elif asyncio.iscoroutine(init_response):
            response = await init_response  # type: ignore
-
        if (
            response is not None
            and isinstance(response, EmbeddingResponse)
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -2151,6 +2151,7 @@ class LlmProviders(str, Enum):
    GALADRIEL = "galadriel"
    INFINITY = "infinity"
    DEEPGRAM = "deepgram"
+    NOVITA = "novita"
    AIOHTTP_OPENAI = "aiohttp_openai"
    LANGFUSE = "langfuse"
    HUMANLOOP = "humanloop"
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -2091,6 +2091,9 @@ def register_model(model_cost: Union[str, dict]):  # noqa: PLR0915
        elif value.get("litellm_provider") == "bedrock":
            if key not in litellm.bedrock_models:
                litellm.bedrock_models.append(key)
+        elif value.get("litellm_provider") == "novita":
+            if key not in litellm.novita_models:
+                litellm.novita_models.append(key)
    return model_cost


@@ -4943,6 +4946,11 @@ def validate_environment(  # noqa: PLR0915
            else:
                missing_keys.append("CLOUDFLARE_API_KEY")
                missing_keys.append("CLOUDFLARE_API_BASE")
+        elif custom_llm_provider == "novita":
+            if "NOVITA_API_KEY" in os.environ:
+                keys_in_environment = True
+            else:
+                missing_keys.append("NOVITA_API_KEY")
    else:
        ## openai - chatcompletion + text completion
        if (
@@ -5025,6 +5033,11 @@ def validate_environment(  # noqa: PLR0915
                keys_in_environment = True
            else:
                missing_keys.append("NLP_CLOUD_API_KEY")
+        elif model in litellm.novita_models:
+            if "NOVITA_API_KEY" in os.environ:
+                keys_in_environment = True
+            else:
+                missing_keys.append("NOVITA_API_KEY")

    if api_key is not None:
        new_missing_keys = []
@@ -6366,6 +6379,8 @@ class ProviderConfigManager:
            return litellm.TritonConfig()
        elif litellm.LlmProviders.PETALS == provider:
            return litellm.PetalsConfig()
+        elif litellm.LlmProviders.NOVITA == provider:
+            return litellm.NovitaConfig()
        elif litellm.LlmProviders.BEDROCK == provider:
            bedrock_route = BedrockModelInfo.get_bedrock_route(model)
            bedrock_invoke_provider = litellm.BedrockLLM.get_bedrock_invoke_provider(
--- a/poetry.lock
+++ b/poetry.lock
@@ -3808,7 +3808,7 @@ crt = ["botocore[crt] (>=1.33.2,<2.0a.0)"]
 name = "six"
 version = "1.17.0"
 description = "Python 2 and 3 compatibility utilities"
-optional = true
+optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
 groups = ["main"]
 markers = "extra == \"extra-proxy\" or extra == \"proxy\""
--- a/tests/litellm/llms/novita/chat/test_transformation.py
+++ b/tests/litellm/llms/novita/chat/test_transformation.py
@@ -0,0 +1,69 @@
+"""
+Unit tests for Novita AI configuration.
+
+These tests validate the NovitaConfig class which extends OpenAIGPTConfig.
+Novita AI is an OpenAI-compatible provider with a few customizations.
+"""
+
+import os
+import sys
+from typing import Dict, List, Optional
+from unittest.mock import patch
+
+import pytest
+
+sys.path.insert(
+    0, os.path.abspath("../../../../..")
+)  # Adds the parent directory to the system path
+
+from litellm.llms.novita.chat.transformation import NovitaConfig
+
+
+class TestNovitaConfig:
+    """Test class for NovitaConfig functionality"""
+
+    def test_validate_environment(self):
+        """Test that validate_environment adds correct headers"""
+        config = NovitaConfig()
+        headers = {}
+        api_key = "fake-novita-key"
+        
+        result = config.validate_environment(
+            headers=headers,
+            model="novita/meta-llama/llama-3.3-70b-instruct",
+            messages=[{"role": "user", "content": "Hello"}],
+            optional_params={},
+            litellm_params={},
+            api_key=api_key,
+            api_base="https://api.novita.ai/v3/openai"
+        )
+        
+        # Verify headers
+        assert result["Authorization"] == f"Bearer {api_key}"
+        assert result["Content-Type"] == "application/json"
+        assert result["X-Novita-Source"] == "litellm"
+
+    def test_missing_api_key(self):
+        """Test error handling when API key is missing"""
+        config = NovitaConfig()
+        
+        with pytest.raises(ValueError) as excinfo:
+            config.validate_environment(
+                headers={},
+                model="novita/meta-llama/llama-3.3-70b-instruct",
+                messages=[{"role": "user", "content": "Hello"}],
+                optional_params={},
+                litellm_params={},
+                api_key=None,
+                api_base="https://api.novita.ai/v3/openai"
+            )
+        
+        assert "Missing Novita AI API Key" in str(excinfo.value)
+
+    def test_inheritance(self):
+        """Test proper inheritance from OpenAIGPTConfig"""
+        config = NovitaConfig()
+        
+        from litellm.llms.openai.chat.gpt_transformation import OpenAIGPTConfig
+        assert isinstance(config, OpenAIGPTConfig)
+        assert hasattr(config, "get_supported_openai_params") 
--- a/tests/local_testing/test_completion.py
+++ b/tests/local_testing/test_completion.py
@@ -4394,6 +4394,77 @@ def test_humanloop_completion(monkeypatch):
        messages=[{"role": "user", "content": "Tell me a joke."}],
    )

+def test_completion_novita_ai():
+    litellm.set_verbose = True
+    messages = [
+        {"role": "system", "content": "You're a good bot"},
+        {
+            "role": "user",
+            "content": "Hey",
+        },
+    ]
+    
+    from openai import OpenAI
+    openai_client = OpenAI(api_key="fake-key")
+    
+    with patch.object(
+        openai_client.chat.completions, "create", new=MagicMock()
+    ) as mock_call:
+        try:
+            completion(
+                model="novita/meta-llama/llama-3.3-70b-instruct",
+                messages=messages,
+                client=openai_client,
+                api_base="https://api.novita.ai/v3/openai",
+            )
+            
+            mock_call.assert_called_once()
+            
+            # Verify model is passed correctly
+            assert mock_call.call_args.kwargs["model"] == "meta-llama/llama-3.3-70b-instruct"
+            # Verify messages are passed correctly
+            assert mock_call.call_args.kwargs["messages"] == messages
+            
+        except Exception as e:
+            pytest.fail(f"Error occurred: {e}")
+
+
+@pytest.mark.parametrize(
+    "api_key", ["my-bad-api-key"]
+)
+def test_completion_novita_ai_dynamic_params(api_key):
+    try:
+        litellm.set_verbose = True
+        messages = [
+            {"role": "system", "content": "You're a good bot"},
+            {
+                "role": "user",
+                "content": "Hey",
+            },
+        ]
+        
+        from openai import OpenAI
+        openai_client = OpenAI(api_key="fake-key")
+        
+        with patch.object(
+            openai_client.chat.completions, "create", side_effect=Exception("Invalid API key")
+        ) as mock_call:
+            try:
+                completion(
+                    model="novita/meta-llama/llama-3.3-70b-instruct",
+                    messages=messages,
+                    api_key=api_key,
+                    client=openai_client,
+                    api_base="https://api.novita.ai/v3/openai",
+                )
+                pytest.fail(f"This call should have failed!")
+            except Exception as e:
+                # This should fail with the mocked exception
+                assert "Invalid API key" in str(e)
+                
+            mock_call.assert_called_once()
+    except Exception as e:
+        pytest.fail(f"Unexpected error: {e}")

 def test_deepseek_reasoning_content_completion():
    try: