Merge pull request #9120 from emerzon/azure_models

Adding/Update of models

litellm/model_prices_and_context_window_backup.json

@@ -1625,13 +1625,23 @@
         "max_tokens": 8192,
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "input_cost_per_token": 0.0,
-        "input_cost_per_token_cache_hit": 0.0,
-        "output_cost_per_token": 0.0,
+        "input_cost_per_token": 0.00000135,
+        "output_cost_per_token": 0.0000054,
         "litellm_provider": "azure_ai",
         "mode": "chat",
-        "supports_prompt_caching": true,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367"
+    },
+    "azure_ai/deepseek-v3": {
+        "max_tokens": 8192,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000114,
+        "output_cost_per_token": 0.00000456,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "supports_tool_choice": true,
+        "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438"
     },
     "azure_ai/jamba-instruct": {
         "max_tokens": 4096,
@@ -1643,6 +1653,17 @@
         "mode": "chat",
         "supports_tool_choice": true
     },
+    "azure_ai/mistral-nemo": {
+        "max_tokens": 4096,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00000015,
+        "output_cost_per_token": 0.00000015,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice"
+    },
     "azure_ai/mistral-large": {
         "max_tokens": 8191,
         "max_input_tokens": 32000,
@@ -1770,10 +1791,34 @@
         "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice",
         "supports_tool_choice": true
     },
-    "azure_ai/Phi-4": {
+    "azure_ai/Phi-4-mini-instruct": {
         "max_tokens": 4096,
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 4096,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/models-featured#microsoft"
+    },
+    "azure_ai/Phi-4-multimodal-instruct": {
+        "max_tokens": 4096,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/models-featured#microsoft"
+    },
+    "azure_ai/Phi-4": {
+        "max_tokens": 16384,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 16384,
         "input_cost_per_token": 0.000000125,
         "output_cost_per_token": 0.0000005,
         "litellm_provider": "azure_ai",
@@ -4511,6 +4556,12 @@
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
+    "vertex_ai/imagen-3.0-generate-002": {
+        "output_cost_per_image": 0.04,
+        "litellm_provider": "vertex_ai-image-models",
+        "mode": "image_generation",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
+    },
     "vertex_ai/imagen-3.0-generate-001": {
         "output_cost_per_image": 0.04,
         "litellm_provider": "vertex_ai-image-models",

model_prices_and_context_window.json

@@ -1625,13 +1625,23 @@
         "max_tokens": 8192,
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "input_cost_per_token": 0.0,
-        "input_cost_per_token_cache_hit": 0.0,
-        "output_cost_per_token": 0.0,
+        "input_cost_per_token": 0.00000135,
+        "output_cost_per_token": 0.0000054,
         "litellm_provider": "azure_ai",
         "mode": "chat",
-        "supports_prompt_caching": true,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367"
+    },
+    "azure_ai/deepseek-v3": {
+        "max_tokens": 8192,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000114,
+        "output_cost_per_token": 0.00000456,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "supports_tool_choice": true,
+        "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438"
     },
     "azure_ai/jamba-instruct": {
         "max_tokens": 4096,
@@ -1643,6 +1653,17 @@
         "mode": "chat",
         "supports_tool_choice": true
     },
+    "azure_ai/mistral-nemo": {
+        "max_tokens": 4096,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00000015,
+        "output_cost_per_token": 0.00000015,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice"
+    },
     "azure_ai/mistral-large": {
         "max_tokens": 8191,
         "max_input_tokens": 32000,
@@ -1770,10 +1791,34 @@
         "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice",
         "supports_tool_choice": true
     },
-    "azure_ai/Phi-4": {
+    "azure_ai/Phi-4-mini-instruct": {
         "max_tokens": 4096,
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 4096,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/models-featured#microsoft"
+    },
+    "azure_ai/Phi-4-multimodal-instruct": {
+        "max_tokens": 4096,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/models-featured#microsoft"
+    },
+    "azure_ai/Phi-4": {
+        "max_tokens": 16384,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 16384,
         "input_cost_per_token": 0.000000125,
         "output_cost_per_token": 0.0000005,
         "litellm_provider": "azure_ai",
@@ -4511,6 +4556,12 @@
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
+    "vertex_ai/imagen-3.0-generate-002": {
+        "output_cost_per_image": 0.04,
+        "litellm_provider": "vertex_ai-image-models",
+        "mode": "image_generation",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
+    },
     "vertex_ai/imagen-3.0-generate-001": {
         "output_cost_per_image": 0.04,
         "litellm_provider": "vertex_ai-image-models",