docs: refresh model examples across provider pages

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

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']`           |

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",
@@ -52,20 +51,19 @@ 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)",
         }
     ],
     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",

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>
+</Tabs>

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
 

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>
+</Tabs>

docs/providers/fireworks_ai.md

@@ -38,15 +38,15 @@ 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"}
    ],
 )
 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)` |
+| fireworks/qwen3-reranker-8b | `rerank(model="fireworks_ai/fireworks/qwen3-reranker-8b", query=query, documents=documents)` |