bug fix de depluciate model list (#9775)

litellm/model_prices_and_context_window_backup.json

@@ -4847,6 +4847,33 @@
         "supports_tool_choice": true,
         "source": "https://ai.google.dev/pricing#2_0flash"
     },
+    "gemini/gemini-2.5-pro-preview-03-25": {
+        "max_tokens": 65536,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_images_per_prompt": 3000,
+        "max_videos_per_prompt": 10,
+        "max_video_length": 1,
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_pdf_size_mb": 30,
+        "input_cost_per_audio_token": 0.0000007,
+        "input_cost_per_token": 0.00000125,
+        "input_cost_per_token_above_128k_tokens": 0.0000025, 
+        "output_cost_per_token": 0.0000010,
+        "output_cost_per_token_above_128k_tokens": 0.000015, 
+        "litellm_provider": "gemini",
+        "mode": "chat",
+        "rpm": 10000,
+        "tpm": 10000000,
+        "supports_system_messages": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_response_schema": true,
+        "supports_audio_output": false,
+        "supports_tool_choice": true,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview"
+    },
     "gemini/gemini-2.0-flash-exp": {
         "max_tokens": 8192,
         "max_input_tokens": 1048576,
@@ -6665,6 +6692,14 @@
         "mode": "chat",
         "supports_tool_choice": true
     },
+    "mistralai/mistral-small-3.1-24b-instruct": {
+        "max_tokens": 32000,
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.0000003,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
     "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": {
         "max_tokens": 32769,
         "input_cost_per_token": 0.0000005,
@@ -6793,12 +6828,38 @@
         "supports_vision": false,
         "supports_tool_choice": true
     },
+    "openrouter/openai/o3-mini": {
+        "max_tokens": 65536,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 65536,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false,
+        "supports_tool_choice": true
+    },
+    "openrouter/openai/o3-mini-high": {
+        "max_tokens": 65536,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 65536,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false,
+        "supports_tool_choice": true
+    },
     "openrouter/openai/gpt-4o": {
         "max_tokens": 4096,
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "input_cost_per_token": 0.000005,
-        "output_cost_per_token": 0.000015,
+        "input_cost_per_token": 0.0000025,
+        "output_cost_per_token": 0.000010,
         "litellm_provider": "openrouter",
         "mode": "chat",
         "supports_function_calling": true,

litellm/proxy/management_endpoints/model_management_endpoints.py

@@ -13,7 +13,7 @@ model/{model_id}/update - PATCH endpoint for model update.
 import asyncio
 import json
 import uuid
-from typing import Literal, Optional, Union, cast
+from typing import Dict, List, Literal, Optional, Union, cast
 
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from pydantic import BaseModel
@@ -846,3 +846,24 @@ async def update_model(
             param=getattr(e, "param", "None"),
             code=status.HTTP_400_BAD_REQUEST,
         )
+
+
+def _deduplicate_litellm_router_models(models: List[Dict]) -> List[Dict]:
+    """
+    Deduplicate models based on their model_info.id field.
+    Returns a list of unique models keeping only the first occurrence of each model ID.
+
+    Args:
+        models: List of model dictionaries containing model_info
+
+    Returns:
+        List of deduplicated model dictionaries
+    """
+    seen_ids = set()
+    unique_models = []
+    for model in models:
+        model_id = model.get("model_info", {}).get("id", None)
+        if model_id is not None and model_id not in seen_ids:
+            unique_models.append(model)
+            seen_ids.add(model_id)
+    return unique_models

litellm/proxy/proxy_server.py

@@ -229,6 +229,7 @@ from litellm.proxy.management_endpoints.key_management_endpoints import (
 from litellm.proxy.management_endpoints.model_management_endpoints import (
     _add_model_to_db,
     _add_team_model_to_db,
+    _deduplicate_litellm_router_models,
 )
 from litellm.proxy.management_endpoints.model_management_endpoints import (
     router as model_management_router,
@@ -5371,6 +5372,7 @@ async def non_admin_all_models(
             detail={"error": CommonProxyErrors.db_not_connected_error.value},
         )
 
+    # Get all models that are user-added, when model created_by == user_api_key_dict.user_id
     all_models = await _check_if_model_is_user_added(
         models=all_models,
         user_api_key_dict=user_api_key_dict,
@@ -5385,12 +5387,15 @@ async def non_admin_all_models(
         except Exception:
             raise HTTPException(status_code=400, detail={"error": "User not found"})
 
+        # Get all models that are team models, when model team_id == user_row.teams
         all_models += _check_if_model_is_team_model(
             models=llm_router.get_model_list() or [],
             user_row=user_row,
         )
 
-    return all_models
+    # de-duplicate models. Only return unique model ids
+    unique_models = _deduplicate_litellm_router_models(models=all_models)
+    return unique_models
 
 
 @router.get(