Update ai gateway docs

docs/my-website/docs/index.md

@@ -72,6 +72,158 @@ response = completion(
 )
 ```
 
+</TabItem>
+<TabItem value="anthropic" label="Anthropic">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key"
+
+response = completion(
+  model="anthropic/claude-3-sonnet-20240229",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+
+</TabItem>
+<TabItem value="xai" label="xAI">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["XAI_API_KEY"] = "your-api-key"
+
+response = completion(
+  model="xai/grok-2-latest",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+</TabItem>
+<TabItem value="vertex" label="VertexAI">
+
+```python
+from litellm import completion
+import os
+
+# auth: run 'gcloud auth application-default'
+os.environ["VERTEXAI_PROJECT"] = "hardy-device-386718"
+os.environ["VERTEXAI_LOCATION"] = "us-central1"
+
+response = completion(
+  model="vertex_ai/gemini-1.5-pro",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+
+</TabItem>
+
+<TabItem value="nvidia" label="NVIDIA">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["NVIDIA_NIM_API_KEY"] = "nvidia_api_key"
+os.environ["NVIDIA_NIM_API_BASE"] = "nvidia_nim_endpoint_url"
+
+response = completion(
+  model="nvidia_nim/<model_name>",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+
+</TabItem>
+
+<TabItem value="hugging" label="HuggingFace">
+
+```python
+from litellm import completion
+import os
+
+os.environ["HUGGINGFACE_API_KEY"] = "huggingface_api_key"
+
+# e.g. Call 'WizardLM/WizardCoder-Python-34B-V1.0' hosted on HF Inference endpoints
+response = completion(
+  model="huggingface/WizardLM/WizardCoder-Python-34B-V1.0",
+  messages=[{ "content": "Hello, how are you?","role": "user"}],
+  api_base="https://my-endpoint.huggingface.cloud"
+)
+
+print(response)
+```
+
+</TabItem>
+
+<TabItem value="azure" label="Azure OpenAI">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["AZURE_API_KEY"] = ""
+os.environ["AZURE_API_BASE"] = ""
+os.environ["AZURE_API_VERSION"] = ""
+
+# azure call
+response = completion(
+  "azure/<your_deployment_name>",
+  messages = [{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+
+</TabItem>
+
+<TabItem value="ollama" label="Ollama">
+
+```python
+from litellm import completion
+
+response = completion(
+            model="ollama/llama2",
+            messages = [{ "content": "Hello, how are you?","role": "user"}],
+            api_base="http://localhost:11434"
+)
+```
+
+</TabItem>
+<TabItem value="or" label="Openrouter">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["OPENROUTER_API_KEY"] = "openrouter_api_key"
+
+response = completion(
+  model="openrouter/google/palm-2-chat-bison",
+  messages = [{ "content": "Hello, how are you?","role": "user"}],
+)
+```
+
+</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>
 
 <TabItem value="vercel" label="Vercel AI Gateway">
@@ -80,13 +232,12 @@ response = completion(
 from litellm import completion
 import os
 
-## set ENV variables
-os.environ["VERCEL_AI_GATEWAY_API_KEY"] = "your-api-key"
+## set ENV variables.
+os.environ["VERCEL_AI_GATEWAY_API_KEY"] = "your-vercel-api-key"
 
 response = completion(
   model="vercel_ai_gateway/openai/gpt-4o",
-  messages=[{ "content": "Hello, how are you?","role": "user"}],
-  stream=True,
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
 )
 ```
 
@@ -312,6 +463,24 @@ response = completion(
 
 </TabItem>
 
+<TabItem value="vercel" label="Vercel AI Gateway">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables. V
+os.environ["VERCEL_AI_GATEWAY_API_KEY"] = "your-vercel-api-key"
+
+response = completion(
+  model="vercel_ai_gateway/openai/gpt-4o",
+  messages = [{ "content": "Hello, how are you?","role": "user"}],
+  stream=True,
+)
+```
+
+</TabItem>
+
 </Tabs>
 
 ### Streaming Response Format (OpenAI Format)

docs/my-website/docs/providers/vercel_ai_gateway.md

@@ -28,6 +28,8 @@ os.environ["VERCEL_AI_GATEWAY_API_KEY"] = ""  # your Vercel AI Gateway API key
 os.environ["VERCEL_OIDC_TOKEN"] = ""  # your Vercel OIDC token for authentication
 ```
 
+Note: see the [Vercel AI Gateway docs](https://vercel.com/docs/ai-gateway#using-the-ai-gateway-with-an-api-key) for instructions on obtaining a key.
+
 ## Usage - LiteLLM Python SDK
 
 ### Non-streaming

model_prices_and_context_window.json

@@ -17693,10 +17693,10 @@
         "mode": "chat"
     },
     "vercel_ai_gateway/deepseek/deepseek-r1": {
-        "max_tokens": 64000,
+        "max_tokens": 128000,
         "input_cost_per_token": 5.5e-07,
         "output_cost_per_token": 2.19e-06,
-        "max_input_tokens": 64000,
+        "max_input_tokens": 128000,
         "litellm_provider": "vercel_ai_gateway",
         "mode": "chat"
     },
@@ -17999,10 +17999,10 @@
         "mode": "chat"
     },
     "vercel_ai_gateway/meta/llama-3.1-8b": {
-        "max_tokens": 128000,
+        "max_tokens": 131000,
         "input_cost_per_token": 5e-08,
         "output_cost_per_token": 8e-08,
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131000,
         "litellm_provider": "vercel_ai_gateway",
         "mode": "chat"
     },
@@ -18426,10 +18426,10 @@
         "mode": "chat"
     },
     "vercel_ai_gateway/openai/gpt-3.5-turbo": {
-        "max_tokens": 4096,
+        "max_tokens": 16385,
         "input_cost_per_token": 5e-07,
         "output_cost_per_token": 1.5e-06,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 16385,
         "litellm_provider": "vercel_ai_gateway",
         "mode": "chat"
     },
@@ -19278,10 +19278,10 @@
         "mode": "chat"
     },
     "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": {
-        "max_tokens": 2048,
+        "max_tokens": 65536,
         "input_cost_per_token": 1.2e-06,
         "output_cost_per_token": 1.2e-06,
-        "max_input_tokens": 2048,
+        "max_input_tokens": 65536,
         "litellm_provider": "vercel_ai_gateway",
         "mode": "chat"
     },
@@ -19496,9 +19496,9 @@
     },
     "openrouter/qwen/qwen3-235b-a22b-2507": {
         "max_tokens": 262144,
-        "input_cost_per_token": 1.2e-07,
+        "input_cost_per_token": 1.179e-07,
         "max_output_tokens": 262144,
-        "output_cost_per_token": 5.9e-07,
+        "output_cost_per_token": 1.179e-07,
         "litellm_provider": "openrouter",
         "mode": "chat"
     },
@@ -19743,10 +19743,10 @@
         "mode": "chat"
     },
     "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": {
-        "max_tokens": 4096,
+        "max_tokens": 8192,
         "input_cost_per_token": 1.5e-06,
         "output_cost_per_token": 2e-06,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 8192,
         "litellm_provider": "vercel_ai_gateway",
         "mode": "chat"
     },