diff --git a/docs/providers/azure_ai.md b/docs/providers/azure_ai.md
index 78a135270..0ace05a02 100644
--- a/docs/providers/azure_ai.md
+++ b/docs/providers/azure_ai.md
@@ -307,6 +307,7 @@ LiteLLM supports **ALL** azure ai models. Here's a few examples:
 
 | Model Name               | Function Call                                                                                                                                                      |
 |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| Claude Opus 5 | `completion(model="azure_ai/claude-opus-5", messages)` |
 | Cohere command-r-plus | `completion(model="azure_ai/command-r-plus", messages)` | 
 | Cohere command-r | `completion(model="azure_ai/command-r", messages)` | 
 | mistral-large-latest | `completion(model="azure_ai/mistral-large-latest", messages)` | 
@@ -354,7 +355,7 @@ export AZURE_AI_API_BASE="https://my-resource.services.ai.azure.com/anthropic"
 
 ```yaml
 model_list:
-  - model_name: claude-4-azure
+  - model_name: azure-claude
     litellm_params:
       model: azure_ai/{{anthropic_large}}
       api_key: os.environ/AZURE_AI_API_KEY
@@ -374,11 +375,11 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
   --header 'Content-Type: application/json' \
   --header 'Authorization: Bearer $LITELLM_KEY' \
   --data '{
-    "model": "claude-4-azure",
+    "model": "azure-claude",
     "messages": [
       {
         "role": "user",
-        "content": "How do I use Claude Opus 4 via Azure Anthropic in LiteLLM?"
+        "content": "How do I use Claude Opus via Azure Anthropic in LiteLLM?"
       }
     ],
     "max_tokens": 1024
diff --git a/docs/providers/bedrock.md b/docs/providers/bedrock.md
index 82463cdc7..6d09c01d5 100644
--- a/docs/providers/bedrock.md
+++ b/docs/providers/bedrock.md
@@ -56,7 +56,7 @@ response = completion(
 <TabItem value="proxy" label="PROXY">
 ```yaml
 model_list:
-  - model_name: bedrock-claude-sonnet-4-5
+  - model_name: bedrock-claude-sonnet-5
     litellm_params:
       model: bedrock/us.anthropic.{{anthropic}}
       api_key: os.environ/AWS_BEARER_TOKEN_BEDROCK
@@ -93,7 +93,7 @@ Here's how to call Bedrock with the LiteLLM Proxy Server
 
 ```yaml
 model_list:
-  - model_name: bedrock-claude-sonnet-4-5
+  - model_name: bedrock-claude-sonnet-5
     litellm_params:
       model: bedrock/us.anthropic.{{anthropic}}
       aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
@@ -2020,13 +2020,15 @@ LiteLLM supports ALL Bedrock models.
 
 Here's an example of using a bedrock model with LiteLLM. For a complete list, refer to the [model cost map](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json)
 
-| Model Name                 | Command                                                          |
-|----------------------------|------------------------------------------------------------------|
+| Model Name | Command | Required OS Variables |
+|------------|---------|-----------------------|
+| Anthropic Claude Opus 5 | `completion(model='bedrock/us.anthropic.claude-opus-5', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']` |
+| Amazon Nova 2 Lite | `completion(model='bedrock/amazon.nova-2-lite-v1:0', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` |
 | GPT-OSS 20B | `completion(model='bedrock/converse/openai.gpt-oss-20b-1:0', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` |
 | GPT-OSS 120B | `completion(model='bedrock/converse/openai.gpt-oss-120b-1:0', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` |
 | Deepseek R1    | `completion(model='bedrock/us.deepseek.r1-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
 | Anthropic Claude Sonnet 4.5    | `completion(model='bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
-| Anthropic Claude-V3.5 Sonnet    | `completion(model='bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
+| Anthropic Claude Haiku 4.5 | `completion(model='bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']` |
 | Anthropic Claude-V3  sonnet    | `completion(model='bedrock/anthropic.claude-3-sonnet-20240229-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
 | Anthropic Claude-V3 Haiku     | `completion(model='bedrock/anthropic.claude-3-haiku-20240307-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
 | Anthropic Claude-V3 Opus     | `completion(model='bedrock/anthropic.claude-3-opus-20240229-v1:0', messages=messages)`   | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`           |
diff --git a/docs/providers/cerebras.md b/docs/providers/cerebras.md
index 33bef5e10..571ef63b9 100644
--- a/docs/providers/cerebras.md
+++ b/docs/providers/cerebras.md
@@ -23,19 +23,18 @@ import os
 
 os.environ['CEREBRAS_API_KEY'] = ""
 response = completion(
-    model="cerebras/llama3-70b-instruct",
+    model="cerebras/gpt-oss-120b",
     messages=[
         {
             "role": "user",
             "content": "What's the weather like in Boston today in Fahrenheit? (Write in JSON)",
         }
     ],
-    max_tokens=10,
+    max_tokens=4096,
         
     # The prompt should include JSON if 'json_object' is selected; otherwise, you will get error code 400.
     response_format={ "type": "json_object" },
     seed=123,
-    stop=["\n\n"],
     temperature=0.2,
     top_p=0.9,
     tool_choice="auto",
@@ -52,7 +51,7 @@ import os
 
 os.environ['CEREBRAS_API_KEY'] = ""
 response = completion(
-    model="cerebras/llama3-70b-instruct",
+    model="cerebras/gpt-oss-120b",
     messages=[
         {
             "role": "user",
@@ -60,12 +59,11 @@ response = completion(
         }
     ],
     stream=True,
-    max_tokens=10,
+    max_tokens=4096,
 
     # The prompt should include JSON if 'json_object' is selected; otherwise, you will get error code 400.
     response_format={ "type": "json_object" }, 
     seed=123,
-    stop=["\n\n"],
     temperature=0.2,
     top_p=0.9,
     tool_choice="auto",
diff --git a/docs/providers/cohere.md b/docs/providers/cohere.md
index 1c3181d18..c9fb26b4a 100644
--- a/docs/providers/cohere.md
+++ b/docs/providers/cohere.md
@@ -25,7 +25,7 @@ os.environ["COHERE_API_KEY"] = "cohere key"
 
 # cohere v2 call
 response = completion(
-    model="cohere_chat/command-a-03-2025", 
+    model="cohere_chat/command-a-plus-05-2026",
     messages = [{ "content": "Hello, how are you?","role": "user"}]
 )
 ```
@@ -42,7 +42,7 @@ os.environ["COHERE_API_KEY"] = "cohere key"
 
 # cohere v1 call
 response = completion(
-    model="cohere_chat/v1/command-a-03-2025", 
+    model="cohere_chat/v1/command-a-plus-05-2026",
     messages = [{ "content": "Hello, how are you?","role": "user"}]
 )
 ```
@@ -59,7 +59,7 @@ os.environ["COHERE_API_KEY"] = "cohere key"
 
 # cohere v2 streaming
 response = completion(
-    model="cohere_chat/command-a-03-2025", 
+    model="cohere_chat/command-a-plus-05-2026",
     messages = [{ "content": "Hello, how are you?","role": "user"}],
     stream=True
 )
@@ -79,7 +79,7 @@ os.environ["COHERE_API_KEY"] = "cohere key"
 
 # cohere v1 streaming
 response = completion(
-    model="cohere_chat/v1/command-a-03-2025", 
+    model="cohere_chat/v1/command-a-plus-05-2026",
     messages = [{ "content": "Hello, how are you?","role": "user"}],
     stream=True
 )
@@ -106,18 +106,18 @@ Define the cohere models you want to use in the config.yaml
 **For Cohere v1 models:**
 ```yaml showLineNumbers
 model_list:
-  - model_name: command-a-03-2025 
+  - model_name: command-a-plus-05-2026
     litellm_params:
-      model: cohere_chat/v1/command-a-03-2025
+      model: cohere_chat/v1/command-a-plus-05-2026
       api_key: "os.environ/COHERE_API_KEY"
 ```
 
 **For Cohere v2 models:**
 ```yaml showLineNumbers
 model_list:
-  - model_name: command-a-03-2025-v2
+  - model_name: command-a-plus-05-2026-v2
     litellm_params:
-      model: cohere_chat/command-a-03-2025
+      model: cohere_chat/command-a-plus-05-2026
       api_key: "os.environ/COHERE_API_KEY"
 ```
 
@@ -136,7 +136,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --header 'Authorization: Bearer <your-litellm-api-key>' \
 --data ' {
-      "model": "command-a-03-2025",
+      "model": "command-a-plus-05-2026",
       "messages": [
         {
           "role": "user",
@@ -154,7 +154,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --header 'Authorization: Bearer <your-litellm-api-key>' \
 --data ' {
-      "model": "command-a-03-2025-v2",
+      "model": "command-a-plus-05-2026-v2",
       "messages": [
         {
           "role": "user",
@@ -175,7 +175,7 @@ client = openai.OpenAI(
 )
 
 # request sent to cohere v1 model
-response = client.chat.completions.create(model="command-a-03-2025", messages = [
+response = client.chat.completions.create(model="command-a-plus-05-2026", messages = [
     {
         "role": "user",
         "content": "this is a test request, write a short poem"
@@ -195,7 +195,7 @@ client = openai.OpenAI(
 )
 
 # request sent to cohere v2 model
-response = client.chat.completions.create(model="command-a-03-2025-v2", messages = [
+response = client.chat.completions.create(model="command-a-plus-05-2026-v2", messages = [
     {
         "role": "user",
         "content": "this is a test request, write a short poem"
@@ -211,7 +211,7 @@ print(response)
 ## Supported Models
 | Model Name | Function Call |
 |------------|----------------|
-| command-a-03-2025 | `litellm.completion('command-a-03-2025', messages)` |
+| command-a-plus-05-2026 | `litellm.completion('cohere_chat/command-a-plus-05-2026', messages)` |
 | command-r-plus-08-2024 | `litellm.completion('command-r-plus-08-2024', messages)` |  
 | command-r-08-2024 | `litellm.completion('command-r-08-2024', messages)` |
 | command-r-plus | `litellm.completion('command-r-plus', messages)` |  
@@ -348,4 +348,4 @@ curl http://0.0.0.0:4000/rerank \
 ```
 
 </TabItem>
-</Tabs>
\ No newline at end of file
+</Tabs>
diff --git a/docs/providers/deepinfra.md b/docs/providers/deepinfra.md
index ddf6122ca..1a83196ac 100644
--- a/docs/providers/deepinfra.md
+++ b/docs/providers/deepinfra.md
@@ -29,7 +29,7 @@ import os
 
 os.environ['DEEPINFRA_API_KEY'] = ""
 response = completion(
-    model="deepinfra/meta-llama/Llama-2-70b-chat-hf", 
+    model="deepinfra/moonshotai/Kimi-K3",
     messages=[{"role": "user", "content": "write code for saying hi from LiteLLM"}]
 )
 ```
@@ -41,7 +41,7 @@ import os
 
 os.environ['DEEPINFRA_API_KEY'] = ""
 response = completion(
-    model="deepinfra/meta-llama/Llama-2-70b-chat-hf", 
+    model="deepinfra/moonshotai/Kimi-K3",
     messages=[{"role": "user", "content": "write code for saying hi from LiteLLM"}],
     stream=True
 )
@@ -51,16 +51,14 @@ for chunk in response:
 ```
 
 ## Chat Models
-| Model Name       | Function Call                        |
-|------------------|--------------------------------------|
-| meta-llama/Meta-Llama-3-8B-Instruct  | `completion(model="deepinfra/meta-llama/Meta-Llama-3-8B-Instruct", messages)` | 
-| meta-llama/Meta-Llama-3-70B-Instruct  | `completion(model="deepinfra/meta-llama/Meta-Llama-3-70B-Instruct", messages)` | 
-| meta-llama/Llama-2-70b-chat-hf  | `completion(model="deepinfra/meta-llama/Llama-2-70b-chat-hf", messages)` | 
-| meta-llama/Llama-2-7b-chat-hf  | `completion(model="deepinfra/meta-llama/Llama-2-7b-chat-hf", messages)` | 
-| meta-llama/Llama-2-13b-chat-hf | `completion(model="deepinfra/meta-llama/Llama-2-13b-chat-hf", messages)` | 
-| codellama/CodeLlama-34b-Instruct-hf | `completion(model="deepinfra/codellama/CodeLlama-34b-Instruct-hf", messages)` |
-| mistralai/Mistral-7B-Instruct-v0.1 | `completion(model="deepinfra/mistralai/Mistral-7B-Instruct-v0.1", messages)` | 
-| jondurbin/airoboros-l2-70b-gpt4-1.4.1 | `completion(model="deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1", messages)` |
+
+Use `deepinfra/<model-id>` with a model from the [DeepInfra catalog](https://deepinfra.com/models). These are representative chat models:
+
+| Model | LiteLLM model ID |
+|-------|------------------|
+| GLM-5.3 | `deepinfra/zai-org/GLM-5.3` |
+| Kimi K3 | `deepinfra/moonshotai/Kimi-K3` |
+| GPT OSS 120B | `deepinfra/openai/gpt-oss-120b` |
 
 ## Rerank Endpoint
 
diff --git a/docs/providers/deepseek.md b/docs/providers/deepseek.md
index fbf3942e3..2fc353559 100644
--- a/docs/providers/deepseek.md
+++ b/docs/providers/deepseek.md
@@ -19,7 +19,7 @@ import os
 
 os.environ['DEEPSEEK_API_KEY'] = ""
 response = completion(
-    model="deepseek/deepseek-chat", 
+    model="deepseek/deepseek-v4-pro",
     messages=[
        {"role": "user", "content": "hello from litellm"}
    ],
@@ -34,7 +34,7 @@ import os
 
 os.environ['DEEPSEEK_API_KEY'] = ""
 response = completion(
-    model="deepseek/deepseek-chat", 
+    model="deepseek/deepseek-v4-pro",
     messages=[
        {"role": "user", "content": "hello from litellm"}
    ],
@@ -51,7 +51,7 @@ We support ALL Deepseek models, just set `deepseek/` as a prefix when sending co
 
 | Model Name               | Function Call                                                                                                                                                      |
 |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| deepseek-chat | `completion(model="deepseek/deepseek-chat", messages)` | 
+| deepseek-v4-pro | `completion(model="deepseek/deepseek-v4-pro", messages)` |
 | deepseek-coder | `completion(model="deepseek/deepseek-coder", messages)` | 
 
 
@@ -170,4 +170,4 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
 
 </TabItem>
 
-</Tabs>
\ No newline at end of file
+</Tabs>
diff --git a/docs/providers/fireworks_ai.md b/docs/providers/fireworks_ai.md
index ec7f15fd0..6ac921311 100644
--- a/docs/providers/fireworks_ai.md
+++ b/docs/providers/fireworks_ai.md
@@ -38,7 +38,7 @@ import os
 
 os.environ['FIREWORKS_AI_API_KEY'] = ""
 response = completion(
-    model="fireworks_ai/glm-5p2", 
+    model="fireworks_ai/glm-5p3-flash",
     messages=[
        {"role": "user", "content": "hello from litellm"}
    ],
@@ -46,7 +46,7 @@ response = completion(
 print(response)
 ```
 
-A bare serverless slug like `glm-5p2` is expanded to `accounts/fireworks/models/glm-5p2` for you, so you can pass either the short slug or the full resource id.
+A bare serverless slug like `glm-5p3-flash` is expanded to `accounts/fireworks/models/glm-5p3-flash` for you, so you can pass either the short slug or the full resource id.
 
 ## Sample Usage - Serverless Models - Streaming
 ```python
@@ -55,7 +55,7 @@ import os
 
 os.environ['FIREWORKS_AI_API_KEY'] = ""
 response = completion(
-    model="fireworks_ai/glm-5p2", 
+    model="fireworks_ai/glm-5p3-flash",
     messages=[
        {"role": "user", "content": "hello from litellm"}
    ],
@@ -126,9 +126,9 @@ The full resource id (`fireworks_ai/accounts/fireworks/routers/glm-latest`) is s
 
 ```yaml
 model_list:
-  - model_name: fireworks-glm-5p2
+  - model_name: fireworks-glm-5p3-flash
     litellm_params:
-      model: fireworks_ai/glm-5p2
+      model: fireworks_ai/glm-5p3-flash
       api_key: "os.environ/FIREWORKS_AI_API_KEY"
 ```
 
@@ -148,7 +148,7 @@ litellm --config config.yaml
 curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
-      "model": "fireworks-glm-5p2",
+      "model": "fireworks-glm-5p3-flash",
       "messages": [
         {
           "role": "user",
@@ -169,7 +169,7 @@ client = openai.OpenAI(
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
-response = client.chat.completions.create(model="fireworks-glm-5p2", messages = [
+response = client.chat.completions.create(model="fireworks-glm-5p3-flash", messages = [
     {
         "role": "user",
         "content": "this is a test request, write a short poem"
@@ -193,7 +193,7 @@ from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
     openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
-    model = "fireworks-glm-5p2",
+    model = "fireworks-glm-5p3-flash",
     temperature=0.1
 )
 
@@ -449,7 +449,7 @@ We support ALL Fireworks AI models, just set `fireworks_ai/` as a prefix when se
 
 | Model Name               | Function Call                                                                                                                                                      |
 |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| glm-5p2 | `completion(model="fireworks_ai/glm-5p2", messages)` |
+| glm-5p3-flash | `completion(model="fireworks_ai/glm-5p3-flash", messages)` |
 | deepseek-v4-pro | `completion(model="fireworks_ai/deepseek-v4-pro", messages)` |
 | kimi-k3 | `completion(model="fireworks_ai/kimi-k3", messages)` |
 | qwen3p8-max | `completion(model="fireworks_ai/qwen3p8-max", messages)` |
@@ -611,4 +611,4 @@ curl http://0.0.0.0:4000/rerank \
 
 | Model Name | Function Call |
 |------------|---------------|
-| fireworks/qwen3-reranker-8b | `rerank(model="fireworks_ai/fireworks/qwen3-reranker-8b", query=query, documents=documents)` |
\ No newline at end of file
+| fireworks/qwen3-reranker-8b | `rerank(model="fireworks_ai/fireworks/qwen3-reranker-8b", query=query, documents=documents)` |
diff --git a/docs/providers/gemini.md b/docs/providers/gemini.md
index 7ed2bced8..1b36e2cfc 100644
--- a/docs/providers/gemini.md
+++ b/docs/providers/gemini.md
@@ -19,9 +19,9 @@ import TabItem from '@theme/TabItem';
 :::tip Gemini API vs Vertex AI
 | Model Format | Provider | Auth Required |
 |-------------|----------|---------------|
-| `gemini/gemini-2.0-flash` | Gemini API | `GEMINI_API_KEY` (simple API key) |
-| `vertex_ai/gemini-2.0-flash` | Vertex AI | GCP credentials + project |
-| `gemini-2.0-flash` (no prefix) | Vertex AI | GCP credentials + project |
+| `gemini/{{gemini_flash}}` | Gemini API | `GEMINI_API_KEY` (simple API key) |
+| `vertex_ai/{{gemini_flash}}` | Vertex AI | GCP credentials + project |
+| `{{gemini_flash}}` (no prefix) | Vertex AI | GCP credentials + project |
 
 **If you just want to use an API key** (like OpenAI), use the `gemini/` prefix.
 
@@ -2257,18 +2257,15 @@ response = litellm.completion(
 **We support ALL Gemini models, just set `model=gemini/<any-model-on-gemini>` as a prefix when sending litellm requests**
 
 :::
-| Model Name            | Function Call                                          | Required OS Variables          |
-|-----------------------|--------------------------------------------------------|--------------------------------|
-| gemini-pro            | `completion(model='gemini/gemini-pro', messages)`            | `os.environ['GEMINI_API_KEY']` |
-| gemini-1.5-pro-latest | `completion(model='gemini/gemini-1.5-pro-latest', messages)` | `os.environ['GEMINI_API_KEY']` |
-| gemini-2.0-flash     | `completion(model='gemini/gemini-2.0-flash', messages)`     | `os.environ['GEMINI_API_KEY']` |
-| gemini-2.0-flash-exp     | `completion(model='gemini/gemini-2.0-flash-exp', messages)`     | `os.environ['GEMINI_API_KEY']` |
-| gemini-2.0-flash-lite-preview-02-05	     | `completion(model='gemini/gemini-2.0-flash-lite-preview-02-05', messages)`     | `os.environ['GEMINI_API_KEY']` |
-| gemini-2.5-flash-preview-09-2025     | `completion(model='gemini/gemini-2.5-flash-preview-09-2025', messages)`     | `os.environ['GEMINI_API_KEY']` |
-| gemini-2.5-flash-lite-preview-09-2025     | `completion(model='gemini/gemini-2.5-flash-lite-preview-09-2025', messages)`     | `os.environ['GEMINI_API_KEY']` |
-| gemini-3.1-flash-lite-preview     | `completion(model='gemini/gemini-3.1-flash-lite-preview', messages)`     | `os.environ['GEMINI_API_KEY']` |
-| gemini-flash-latest     | `completion(model='gemini/gemini-flash-latest', messages)`     | `os.environ['GEMINI_API_KEY']` |
-| gemini-flash-lite-latest     | `completion(model='gemini/gemini-flash-lite-latest', messages)`     | `os.environ['GEMINI_API_KEY']` |
+| Model Name | Function Call | Required OS Variables |
+|------------|---------------|-----------------------|
+| gemini-3.8-flash | `completion(model='gemini/gemini-3.8-flash', messages)` | `os.environ['GEMINI_API_KEY']` |
+| gemini-3.1-pro-preview | `completion(model='gemini/gemini-3.1-pro-preview', messages)` | `os.environ['GEMINI_API_KEY']` |
+| gemini-3.1-flash-lite-preview | `completion(model='gemini/gemini-3.1-flash-lite-preview', messages)` | `os.environ['GEMINI_API_KEY']` |
+| gemini-flash-latest | `completion(model='gemini/gemini-flash-latest', messages)` | `os.environ['GEMINI_API_KEY']` |
+| gemini-flash-lite-latest | `completion(model='gemini/gemini-flash-lite-latest', messages)` | `os.environ['GEMINI_API_KEY']` |
+
+This table is a representative selection. See the [Gemini models documentation](https://ai.google.dev/gemini-api/docs/models) for the current catalog.
 
 
 
diff --git a/docs/providers/mistral.md b/docs/providers/mistral.md
index 8355cd246..76144cb0a 100644
--- a/docs/providers/mistral.md
+++ b/docs/providers/mistral.md
@@ -17,7 +17,7 @@ import os
 
 os.environ['MISTRAL_API_KEY'] = ""
 response = completion(
-    model="mistral/mistral-tiny", 
+    model="mistral/mistral-large-2512",
     messages=[
        {"role": "user", "content": "hello from litellm"}
    ],
@@ -32,7 +32,7 @@ import os
 
 os.environ['MISTRAL_API_KEY'] = ""
 response = completion(
-    model="mistral/mistral-tiny", 
+    model="mistral/mistral-large-2512",
     messages=[
        {"role": "user", "content": "hello from litellm"}
    ],
@@ -148,7 +148,7 @@ All models listed here https://docs.mistral.ai/platform/endpoints are supported.
 |----------------|--------------------------------------------------------------|-------------------|
 | Mistral Small  | `completion(model="mistral/mistral-small-latest", messages)` | No |
 | Mistral Medium | `completion(model="mistral/mistral-medium-latest", messages)`| No |
-| Mistral Large 2  | `completion(model="mistral/mistral-large-2407", messages)` | No |
+| Mistral Large 3 | `completion(model="mistral/mistral-large-2512", messages)` | No |
 | Mistral Large Latest  | `completion(model="mistral/mistral-large-latest", messages)` | No |
 | **Magistral Small**  | `completion(model="mistral/magistral-small-2506", messages)` | Yes |
 | **Magistral Medium** | `completion(model="mistral/magistral-medium-2506", messages)`| Yes |
diff --git a/docs/providers/moonshot.md b/docs/providers/moonshot.md
index 9e5e5bec0..f815048f6 100644
--- a/docs/providers/moonshot.md
+++ b/docs/providers/moonshot.md
@@ -53,7 +53,7 @@ messages = [{"content": "Hello, how are you?", "role": "user"}]
 
 # Moonshot call
 response = completion(
-    model="moonshot/moonshot-v1-8k", 
+    model="moonshot/kimi-k3",
     messages=messages
 )
 
@@ -73,7 +73,7 @@ messages = [{"content": "Hello, how are you?", "role": "user"}]
 
 # Moonshot call with streaming
 response = completion(
-    model="moonshot/moonshot-v1-8k", 
+    model="moonshot/kimi-k3",
     messages=messages,
     stream=True
 )
@@ -88,9 +88,9 @@ Add the following to your LiteLLM Proxy configuration file:
 
 ```yaml showLineNumbers title="config.yaml"
 model_list:
-  - model_name: moonshot-v1-8k
+  - model_name: kimi-k3
     litellm_params:
-      model: moonshot/moonshot-v1-8k
+      model: moonshot/kimi-k3
       api_key: os.environ/MOONSHOT_API_KEY
 
   - model_name: moonshot-v1-32k
@@ -126,7 +126,7 @@ client = OpenAI(
 
 # Non-streaming response
 response = client.chat.completions.create(
-    model="moonshot-v1-8k",
+    model="kimi-k3",
     messages=[{"role": "user", "content": "hello from litellm"}]
 )
 
@@ -144,7 +144,7 @@ client = OpenAI(
 
 # Streaming response
 response = client.chat.completions.create(
-    model="moonshot-v1-8k",
+    model="kimi-k3",
     messages=[{"role": "user", "content": "hello from litellm"}],
     stream=True
 )
@@ -163,7 +163,7 @@ import litellm
 
 # Configure LiteLLM to use your proxy
 response = litellm.completion(
-    model="litellm_proxy/moonshot-v1-8k",
+    model="litellm_proxy/kimi-k3",
     messages=[{"role": "user", "content": "hello from litellm"}],
     api_base="http://localhost:4000",
     api_key="your-proxy-api-key"
@@ -177,7 +177,7 @@ import litellm
 
 # Configure LiteLLM to use your proxy with streaming
 response = litellm.completion(
-    model="litellm_proxy/moonshot-v1-8k",
+    model="litellm_proxy/kimi-k3",
     messages=[{"role": "user", "content": "hello from litellm"}],
     api_base="http://localhost:4000",
     api_key="your-proxy-api-key",
@@ -198,7 +198,7 @@ curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer your-proxy-api-key" \
   -d '{
-    "model": "moonshot-v1-8k",
+    "model": "kimi-k3",
     "messages": [{"role": "user", "content": "hello from litellm"}]
   }'
 ```
@@ -208,7 +208,7 @@ curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer your-proxy-api-key" \
   -d '{
-    "model": "moonshot-v1-8k",
+    "model": "kimi-k3",
     "messages": [{"role": "user", "content": "hello from litellm"}],
     "stream": true
   }'
diff --git a/docs/providers/nvidia_nim.md b/docs/providers/nvidia_nim.md
index 9dbfc80f4..2e11a6e85 100644
--- a/docs/providers/nvidia_nim.md
+++ b/docs/providers/nvidia_nim.md
@@ -32,19 +32,18 @@ import os
 
 os.environ['NVIDIA_NIM_API_KEY'] = ""
 response = completion(
-    model="nvidia_nim/meta/llama3-70b-instruct",
+    model="nvidia_nim/nvidia/nemotron-3-super-120b-a12b",
     messages=[
         {
             "role": "user",
             "content": "What's the weather like in Boston today in Fahrenheit?",
         }
     ],
-    temperature=0.2,        # optional
-    top_p=0.9,              # optional
+    temperature=1.0,        # optional
+    top_p=0.95,             # optional
     frequency_penalty=0.1,  # optional
     presence_penalty=0.1,   # optional
-    max_tokens=10,          # optional
-    stop=["\n\n"],          # optional
+    max_tokens=4096,        # optional
 )
 print(response)
 ```
@@ -56,7 +55,7 @@ import os
 
 os.environ['NVIDIA_NIM_API_KEY'] = ""
 response = completion(
-    model="nvidia_nim/meta/llama3-70b-instruct",
+    model="nvidia_nim/nvidia/nemotron-3-super-120b-a12b",
     messages=[
         {
             "role": "user",
@@ -64,12 +63,11 @@ response = completion(
         }
     ],
     stream=True,
-    temperature=0.2,        # optional
-    top_p=0.9,              # optional
+    temperature=1.0,        # optional
+    top_p=0.95,             # optional
     frequency_penalty=0.1,  # optional
     presence_penalty=0.1,   # optional
-    max_tokens=10,          # optional
-    stop=["\n\n"],          # optional
+    max_tokens=4096,        # optional
 )
 
 for chunk in response:
@@ -168,39 +166,11 @@ Here's how to call an Nvidia NIM Endpoint with the LiteLLM Proxy Server
 
 
 
-## Supported Models - 💥 ALL Nvidia NIM Models Supported!
-We support ALL `nvidia_nim` models, just set `nvidia_nim/` as a prefix when sending completion requests
-
-| Model Name | Function Call |
-|------------|---------------|
-| nvidia/nemotron-4-340b-reward | `completion(model="nvidia_nim/nvidia/nemotron-4-340b-reward", messages)` |
-| 01-ai/yi-large | `completion(model="nvidia_nim/01-ai/yi-large", messages)` |
-| aisingapore/sea-lion-7b-instruct | `completion(model="nvidia_nim/aisingapore/sea-lion-7b-instruct", messages)` |
-| databricks/dbrx-instruct | `completion(model="nvidia_nim/databricks/dbrx-instruct", messages)` |
-| google/gemma-7b | `completion(model="nvidia_nim/google/gemma-7b", messages)` |
-| google/gemma-2b | `completion(model="nvidia_nim/google/gemma-2b", messages)` |
-| google/codegemma-1.1-7b | `completion(model="nvidia_nim/google/codegemma-1.1-7b", messages)` |
-| google/codegemma-7b | `completion(model="nvidia_nim/google/codegemma-7b", messages)` |
-| google/recurrentgemma-2b | `completion(model="nvidia_nim/google/recurrentgemma-2b", messages)` |
-| ibm/granite-34b-code-instruct | `completion(model="nvidia_nim/ibm/granite-34b-code-instruct", messages)` |
-| ibm/granite-8b-code-instruct | `completion(model="nvidia_nim/ibm/granite-8b-code-instruct", messages)` |
-| mediatek/breeze-7b-instruct | `completion(model="nvidia_nim/mediatek/breeze-7b-instruct", messages)` |
-| meta/codellama-70b | `completion(model="nvidia_nim/meta/codellama-70b", messages)` |
-| meta/llama2-70b | `completion(model="nvidia_nim/meta/llama2-70b", messages)` |
-| meta/llama3-8b | `completion(model="nvidia_nim/meta/llama3-8b", messages)` |
-| meta/llama3-70b | `completion(model="nvidia_nim/meta/llama3-70b", messages)` |
-| microsoft/phi-3-medium-4k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-medium-4k-instruct", messages)` |
-| microsoft/phi-3-mini-128k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-mini-128k-instruct", messages)` |
-| microsoft/phi-3-mini-4k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-mini-4k-instruct", messages)` |
-| microsoft/phi-3-small-128k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-small-128k-instruct", messages)` |
-| microsoft/phi-3-small-8k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-small-8k-instruct", messages)` |
-| mistralai/codestral-22b-instruct-v0.1 | `completion(model="nvidia_nim/mistralai/codestral-22b-instruct-v0.1", messages)` |
-| mistralai/mistral-7b-instruct | `completion(model="nvidia_nim/mistralai/mistral-7b-instruct", messages)` |
-| mistralai/mistral-7b-instruct-v0.3 | `completion(model="nvidia_nim/mistralai/mistral-7b-instruct-v0.3", messages)` |
-| mistralai/mixtral-8x7b-instruct | `completion(model="nvidia_nim/mistralai/mixtral-8x7b-instruct", messages)` |
-| mistralai/mixtral-8x22b-instruct | `completion(model="nvidia_nim/mistralai/mixtral-8x22b-instruct", messages)` |
-| mistralai/mistral-large | `completion(model="nvidia_nim/mistralai/mistral-large", messages)` |
-| nvidia/nemotron-4-340b-instruct | `completion(model="nvidia_nim/nvidia/nemotron-4-340b-instruct", messages)` |
-| seallms/seallm-7b-v2.5 | `completion(model="nvidia_nim/seallms/seallm-7b-v2.5", messages)` |
-| snowflake/arctic | `completion(model="nvidia_nim/snowflake/arctic", messages)` |
-| upstage/solar-10.7b-instruct | `completion(model="nvidia_nim/upstage/solar-10.7b-instruct", messages)` |
\ No newline at end of file
+## Supported Models
+
+Use `nvidia_nim/<model-id>` with a chat model available on your NVIDIA endpoint. These are representative models from the [NVIDIA model catalog](https://build.nvidia.com/models):
+
+| Model | LiteLLM model ID |
+|-------|------------------|
+| Nemotron 3 Super | `nvidia_nim/nvidia/nemotron-3-super-120b-a12b` |
+| Nemotron 3.5 Lightning | `nvidia_nim/nvidia/nemotron-3.5-lightning-30b-a3b` |
diff --git a/docs/providers/sambanova.md b/docs/providers/sambanova.md
index bf2342357..f7df63496 100644
--- a/docs/providers/sambanova.md
+++ b/docs/providers/sambanova.md
@@ -23,14 +23,14 @@ import os
 
 os.environ['SAMBANOVA_API_KEY'] = ""
 response = completion(
-    model="sambanova/Llama-4-Maverick-17B-128E-Instruct",
+    model="sambanova/MiniMax-M2.7",
     messages=[
         {
             "role": "user",
             "content": "What do you know about SambaNova Systems",
         }
     ],
-    max_tokens=10,
+    max_tokens=4096,
     stop=[],
     temperature=0.2,
     top_p=0.9,
@@ -46,7 +46,7 @@ import os
 
 os.environ['SAMBANOVA_API_KEY'] = ""
 response = completion(
-    model="sambanova/Llama-4-Maverick-17B-128E-Instruct",
+    model="sambanova/MiniMax-M2.7",
     messages=[
         {
             "role": "user",
@@ -54,8 +54,7 @@ response = completion(
         }
     ],
     stream=True,
-    max_tokens=10,
-    response_format={ "type": "json_object" },
+    max_tokens=4096,
     stop=[],
     temperature=0.2,
     top_p=0.9,
diff --git a/docs/providers/togetherai.md b/docs/providers/togetherai.md
index 5f258ae5a..4d215f07a 100644
--- a/docs/providers/togetherai.md
+++ b/docs/providers/togetherai.md
@@ -19,193 +19,23 @@ os.environ["TOGETHERAI_API_KEY"] = "your-api-key"
 
 messages = [{"role": "user", "content": "Write me a poem about the blue sky"}]
 
-completion(model="together_ai/togethercomputer/Llama-2-7B-32K-Instruct", messages=messages)
+completion(model="together_ai/zai-org/GLM-5.3-Flash", messages=messages)
 ```
 
 ## Together AI Models
-liteLLM supports `non-streaming` and `streaming` requests to all models on https://api.together.xyz/
-
-Example TogetherAI Usage - Note: liteLLM supports all models deployed on TogetherAI
-
-
-### Llama LLMs - Chat
-| Model Name                        | Function Call                                                           | Required OS Variables              |
-|-----------------------------------|-------------------------------------------------------------------------|------------------------------------|
-| togethercomputer/llama-2-70b-chat | `completion('together_ai/togethercomputer/llama-2-70b-chat', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
-
-### Llama LLMs - Language / Instruct
-| Model Name                               | Function Call                                                                  | Required OS Variables              |
-|------------------------------------------|--------------------------------------------------------------------------------|------------------------------------|
-| togethercomputer/llama-2-70b             | `completion('together_ai/togethercomputer/llama-2-70b', messages)`             | `os.environ['TOGETHERAI_API_KEY']` |
-| togethercomputer/LLaMA-2-7B-32K          | `completion('together_ai/togethercomputer/LLaMA-2-7B-32K', messages)`          | `os.environ['TOGETHERAI_API_KEY']` |
-| togethercomputer/Llama-2-7B-32K-Instruct | `completion('together_ai/togethercomputer/Llama-2-7B-32K-Instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
-| togethercomputer/llama-2-7b              | `completion('together_ai/togethercomputer/llama-2-7b', messages)`              | `os.environ['TOGETHERAI_API_KEY']` |
-
-### Falcon LLMs
-| Model Name                           | Function Call                                                              | Required OS Variables              |
-|--------------------------------------|----------------------------------------------------------------------------|------------------------------------|
-| togethercomputer/falcon-40b-instruct | `completion('together_ai/togethercomputer/falcon-40b-instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
-| togethercomputer/falcon-7b-instruct  | `completion('together_ai/togethercomputer/falcon-7b-instruct', messages)`  | `os.environ['TOGETHERAI_API_KEY']` |
-
-### Alpaca LLMs
-| Model Name                 | Function Call                                                    | Required OS Variables              |
-|----------------------------|------------------------------------------------------------------|------------------------------------|
-| togethercomputer/alpaca-7b | `completion('together_ai/togethercomputer/alpaca-7b', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
-
-### Other Chat LLMs
-| Model Name                   | Function Call                                                      | Required OS Variables              |
-|------------------------------|--------------------------------------------------------------------|------------------------------------|
-| HuggingFaceH4/starchat-alpha | `completion('together_ai/HuggingFaceH4/starchat-alpha', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
-
-### Code LLMs
-| Model Name                              | Function Call                                                                 | Required OS Variables              |
-|-----------------------------------------|-------------------------------------------------------------------------------|------------------------------------|
-| togethercomputer/CodeLlama-34b          | `completion('together_ai/togethercomputer/CodeLlama-34b', messages)`          | `os.environ['TOGETHERAI_API_KEY']` |
-| togethercomputer/CodeLlama-34b-Instruct | `completion('together_ai/togethercomputer/CodeLlama-34b-Instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
-| togethercomputer/CodeLlama-34b-Python   | `completion('together_ai/togethercomputer/CodeLlama-34b-Python', messages)`   | `os.environ['TOGETHERAI_API_KEY']` |
-| defog/sqlcoder                          | `completion('together_ai/defog/sqlcoder', messages)`                          | `os.environ['TOGETHERAI_API_KEY']` |
-| NumbersStation/nsql-llama-2-7B          | `completion('together_ai/NumbersStation/nsql-llama-2-7B', messages)`          | `os.environ['TOGETHERAI_API_KEY']` |
-| WizardLM/WizardCoder-15B-V1.0           | `completion('together_ai/WizardLM/WizardCoder-15B-V1.0', messages)`           | `os.environ['TOGETHERAI_API_KEY']` |
-| WizardLM/WizardCoder-Python-34B-V1.0    | `completion('together_ai/WizardLM/WizardCoder-Python-34B-V1.0', messages)`    | `os.environ['TOGETHERAI_API_KEY']` |
-
-### Language LLMs
-| Model Name                          | Function Call                                                             | Required OS Variables              |
-|-------------------------------------|---------------------------------------------------------------------------|------------------------------------|
-| NousResearch/Nous-Hermes-Llama2-13b | `completion('together_ai/NousResearch/Nous-Hermes-Llama2-13b', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
-| Austism/chronos-hermes-13b          | `completion('together_ai/Austism/chronos-hermes-13b', messages)`          | `os.environ['TOGETHERAI_API_KEY']` |
-| upstage/SOLAR-0-70b-16bit           | `completion('together_ai/upstage/SOLAR-0-70b-16bit', messages)`           | `os.environ['TOGETHERAI_API_KEY']` |
-| WizardLM/WizardLM-70B-V1.0          | `completion('together_ai/WizardLM/WizardLM-70B-V1.0', messages)`          | `os.environ['TOGETHERAI_API_KEY']` |
 
+Use `together_ai/<model-id>` for streaming and non-streaming chat requests. These are representative models; check the [Together AI catalog](https://docs.together.ai/docs/serverless-models) for availability and deployment requirements.
 
-## Prompt Templates
-
-Using a chat model on Together AI with it's own prompt format?
-
-### Using Llama2 Instruct models
-If you're using Together AI's Llama2 variants( `model=togethercomputer/llama-2..-instruct`), LiteLLM can automatically translate between the OpenAI prompt format and the TogetherAI Llama2 one (`[INST]..[/INST]`). 
-
-```python
-from litellm import completion 
-
-# set env variable 
-os.environ["TOGETHERAI_API_KEY"] = ""
+| Model | LiteLLM model ID |
+|-------|------------------|
+| GLM-5.3-Flash | `together_ai/zai-org/GLM-5.3-Flash` |
+| Kimi K3 | `together_ai/moonshotai/Kimi-K3` |
+| GPT OSS 120B | `together_ai/openai/gpt-oss-120b` |
 
-messages = [{"role": "user", "content": "Write me a poem about the blue sky"}]
-
-completion(model="together_ai/togethercomputer/Llama-2-7B-32K-Instruct", messages=messages)
-```
-
-### Using another model
-
-You can create a custom prompt template on LiteLLM (and we [welcome PRs](https://github.com/BerriAI/litellm) to add them to the main repo 🤗)
-
-Let's make one for `OpenAssistant/llama2-70b-oasst-sft-v10`!
-
-The accepted template format is: [Reference](https://huggingface.co/OpenAssistant/llama2-70b-oasst-sft-v10-)
-```
-"""
-<|im_start|>system
-{system_message}<|im_end|>
-<|im_start|>user
-{prompt}<|im_end|>
-<|im_start|>assistant
-"""
-```
-
-Let's register our custom prompt template: [Implementation Code](https://github.com/BerriAI/litellm/blob/64f3d3c56ef02ac5544983efc78293de31c1c201/litellm/llms/prompt_templates/factory.py#L77)
-```python
-import litellm 
-
-litellm.register_prompt_template(
-	    model="OpenAssistant/llama2-70b-oasst-sft-v10",
-	    roles={
-            "system": {
-                "pre_message": "[<|im_start|>system",
-                "post_message": "\n"
-            },
-            "user": {
-                "pre_message": "<|im_start|>user",
-                "post_message": "\n"
-            }, 
-            "assistant": {
-                "pre_message": "<|im_start|>assistant",
-                "post_message": "\n"
-            }
-        }
-    )
-```
 
-Let's use it! 
-
-```python
-from litellm import completion 
-
-# set env variable 
-os.environ["TOGETHERAI_API_KEY"] = ""
-
-messages=[{"role":"user", "content": "Write me a poem about the blue sky"}]
-
-completion(model="together_ai/OpenAssistant/llama2-70b-oasst-sft-v10", messages=messages)
-```
-
-**Complete Code**
-
-```python
-import litellm 
-from litellm import completion
-
-# set env variable 
-os.environ["TOGETHERAI_API_KEY"] = ""
-
-litellm.register_prompt_template(
-	    model="OpenAssistant/llama2-70b-oasst-sft-v10",
-	    roles={
-            "system": {
-                "pre_message": "[<|im_start|>system",
-                "post_message": "\n"
-            },
-            "user": {
-                "pre_message": "<|im_start|>user",
-                "post_message": "\n"
-            }, 
-            "assistant": {
-                "pre_message": "<|im_start|>assistant",
-                "post_message": "\n"
-            }
-        }
-    )
-
-messages=[{"role":"user", "content": "Write me a poem about the blue sky"}]
-
-response = completion(model="together_ai/OpenAssistant/llama2-70b-oasst-sft-v10", messages=messages)
-
-print(response)
-```
+## Prompt Templates
 
-**Output**
-```json
-{
-  "choices": [
-    {
-      "finish_reason": "stop",
-      "index": 0,
-      "message": {
-        "content": ".\n\nThe sky is a canvas of blue,\nWith clouds that drift and move,",
-        "role": "assistant",
-        "logprobs": null
-      }
-    }
-  ],
-  "created": 1693941410.482018,
-  "model": "OpenAssistant/llama2-70b-oasst-sft-v10",
-  "usage": {
-    "prompt_tokens": 7,
-    "completion_tokens": 16,
-    "total_tokens": 23
-  },
-  "litellm_call_id": "f21315db-afd6-4c1e-b43a-0b5682de4b06"
-}
-```
+Chat models accept OpenAI-style messages. For a deployment that requires a custom text prompt, see [prompt formatting](../completion/prompt_formatting.md#format-prompt-yourself).
 
 
 ## Reasoning controls via `chat_template_kwargs`
@@ -360,4 +190,4 @@ curl http://0.0.0.0:4000/rerank \
 ```
 
 </TabItem>
-</Tabs>
\ No newline at end of file
+</Tabs>
diff --git a/docs/providers/vertex.md b/docs/providers/vertex.md
index 694288e22..7de7e868e 100644
--- a/docs/providers/vertex.md
+++ b/docs/providers/vertex.md
@@ -17,9 +17,9 @@ import TabItem from '@theme/TabItem';
 :::tip Vertex AI vs Gemini API
 | Model Format | Provider | Auth Required |
 |-------------|----------|---------------|
-| `vertex_ai/gemini-2.0-flash` | Vertex AI | GCP credentials + project |
-| `gemini-2.0-flash` (no prefix) | Vertex AI | GCP credentials + project |
-| `gemini/gemini-2.0-flash` | Gemini API | `GEMINI_API_KEY` (simple API key) |
+| `vertex_ai/{{gemini_flash}}` | Vertex AI | GCP credentials + project |
+| `{{gemini_flash}}` (no prefix) | Vertex AI | GCP credentials + project |
+| `gemini/{{gemini_flash}}` | Gemini API | `GEMINI_API_KEY` (simple API key) |
 
 **If you just want to use an API key** (like OpenAI), use the `gemini/` prefix instead. See [Gemini - Google AI Studio](./gemini.md).
 
@@ -1755,13 +1755,14 @@ os.environ["VERTEXAI_LOCATION"] = "us-central1" # Your Location
 litellm.vertex_location = "us-central1" # Your Location
 ```
 
-## Gemini Pro
-| Model Name       | Function Call                        |
-|------------------|--------------------------------------|
-| gemini-2.5-pro   | `completion('gemini-2.5-pro', messages)`, `completion('vertex_ai/gemini-2.5-pro', messages)` |
-| gemini-2.5-flash-preview-09-2025   | `completion('gemini-2.5-flash-preview-09-2025', messages)`, `completion('vertex_ai/gemini-2.5-flash-preview-09-2025', messages)` |
-| gemini-2.5-flash-lite-preview-09-2025   | `completion('gemini-2.5-flash-lite-preview-09-2025', messages)`, `completion('vertex_ai/gemini-2.5-flash-lite-preview-09-2025', messages)` |
-| gemini-3.1-flash-lite-preview   | `completion('gemini-3.1-flash-lite-preview', messages)`, `completion('vertex_ai/gemini-3.1-flash-lite-preview', messages)` |
+## Gemini Models {#gemini-pro}
+| Model Name | Function Call |
+|------------|---------------|
+| gemini-3.8-flash | `completion('gemini-3.8-flash', messages)`, `completion('vertex_ai/gemini-3.8-flash', messages)` |
+| gemini-3.1-pro-preview | `completion('gemini-3.1-pro-preview', messages)`, `completion('vertex_ai/gemini-3.1-pro-preview', messages)` |
+| gemini-3.1-flash-lite-preview | `completion('gemini-3.1-flash-lite-preview', messages)`, `completion('vertex_ai/gemini-3.1-flash-lite-preview', messages)` |
+
+This table is a representative selection. See the [Vertex AI model catalog](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models) for the current catalog.
 
 ## PayGo / Priority Cost Tracking
 
diff --git a/docs/providers/xai.md b/docs/providers/xai.md
index 083cf46df..0ae4587b8 100644
--- a/docs/providers/xai.md
+++ b/docs/providers/xai.md
@@ -13,18 +13,18 @@ https://docs.x.ai/docs
 
 ## Supported Models
 
-**Grok 4.5** - Frontier model for coding, agentic tasks, and knowledge work with 500K context, reasoning (low/medium/high), vision, tools, web search, and prompt caching.
+**Grok 4.6** - Frontier model for coding, agentic tasks, and knowledge work with 500K context, reasoning (low/medium/high), vision, tools, web search, and prompt caching.
 
 | Model | Context | Features |
 |-------|---------|----------|
-| `xai/grok-4.5` | 500K tokens | **Reasoning**, Function calling, Vision, Web search, Caching |
+| `xai/grok-4.6` | 500K tokens | **Reasoning**, Function calling, Vision, Web search, Caching |
 
 **Example:**
 ```python
 from litellm import completion
 
 response = completion(
-    model="xai/grok-4.5",
+    model="xai/grok-4.6",
     messages=[{"role": "user", "content": "Find and fix the bug, then explain it."}],
     reasoning_effort="high",  # low | medium | high (default high)
 )
@@ -54,14 +54,14 @@ import os
 
 os.environ['XAI_API_KEY'] = ""
 response = completion(
-    model="xai/grok-4.5",
+    model="xai/grok-4.6",
     messages=[
         {
             "role": "user",
             "content": "What's the weather like in Boston today in Fahrenheit?",
         }
     ],
-    max_tokens=10,
+    max_tokens=4096,
     response_format={ "type": "json_object" },
     seed=123,
     temperature=0.2,
@@ -81,7 +81,7 @@ import os
 
 os.environ['XAI_API_KEY'] = ""
 response = completion(
-    model="xai/grok-4.5",
+    model="xai/grok-4.6",
     messages=[
         {
             "role": "user",
@@ -89,7 +89,7 @@ response = completion(
         }
     ],
     stream=True,
-    max_tokens=10,
+    max_tokens=4096,
     response_format={ "type": "json_object" },
     seed=123,
     temperature=0.2,
@@ -112,7 +112,7 @@ from litellm import completion
 os.environ["XAI_API_KEY"] = "your-api-key"
 
 response = completion(
-    model="xai/grok-4.5",
+    model="xai/grok-4.6",
     messages=[
         {
             "role": "user",
@@ -211,10 +211,10 @@ LiteLLM supports reasoning usage for xAI models.
 
 <TabItem value="python" label="LiteLLM Python SDK">
 
-```python showLineNumbers title="reasoning with xai/grok-4.5"
+```python showLineNumbers title="reasoning with xai/grok-4.6"
 import litellm
 response = litellm.completion(
-    model="xai/grok-4.5",
+    model="xai/grok-4.6",
     messages=[{"role": "user", "content": "What is 101*3?"}],
     reasoning_effort="low",  # low | medium | high
 )
@@ -235,7 +235,7 @@ print(response.usage.completion_tokens_details.reasoning_tokens)
 
 <TabItem value="curl" label="LiteLLM Proxy - OpenAI SDK Usage">
 
-```python showLineNumbers title="reasoning with xai/grok-4.5"
+```python showLineNumbers title="reasoning with xai/grok-4.6"
 import openai
 client = openai.OpenAI(
     api_key="sk-1234",             # pass litellm proxy key, if you're using virtual keys
@@ -243,7 +243,7 @@ client = openai.OpenAI(
 )
 
 response = client.chat.completions.create(
-    model="xai/grok-4.5",
+    model="xai/grok-4.6",
     messages=[{"role": "user", "content": "What is 101*3?"}],
     reasoning_effort="low",  # low | medium | high
 )