Litellm dev contributor prs 01 31 2025 (BerriAI#8168)

* Add O3-Mini for Azure and Remove Vision Support (BerriAI#8161)

* Azure Released O3-mini at the same time as OAI, so i've added support here. Confirmed to work with Sweden Central.

* [FIX] replace cgi for python 3.13 with email.Message as suggested in PEP 594 (BerriAI#8160)

* Update model_prices_and_context_window.json (BerriAI#8120)

codestral2501 pricing on vertex_ai

* Fix/db view names (BerriAI#8119)

* Fix to case sensitive DB Views name

* Fix to case sensitive DB View names

* Added quotes to check query as well

* Added quotes to create view query

* test: handle server error  for flaky test

vertex ai has unstable endpoints

---------

Co-authored-by: Wanis Elabbar <[email protected]>
Co-authored-by: Honghua Dong <[email protected]>
Co-authored-by: superpoussin22 <[email protected]>
Co-authored-by: Miguel Armenta <[email protected]>

Author: 5 people

db_scripts/create_views.py

@@ -168,11 +168,11 @@ async def check_view_exists():  # noqa: PLR0915
         print("MonthlyGlobalSpendPerUserPerKey Created!")  # noqa
 
     try:
-        await db.query_raw("""SELECT 1 FROM DailyTagSpend LIMIT 1""")
+        await db.query_raw("""SELECT 1 FROM "DailyTagSpend" LIMIT 1""")
         print("DailyTagSpend Exists!")  # noqa
     except Exception:
         sql_query = """
-        CREATE OR REPLACE VIEW DailyTagSpend AS
+        CREATE OR REPLACE VIEW "DailyTagSpend" AS
         SELECT
             jsonb_array_elements_text(request_tags) AS individual_request_tag,
             DATE(s."startTime") AS spend_date,

litellm/litellm_core_utils/prompt_templates/factory.py

@@ -2153,7 +2153,7 @@ def stringify_json_tool_call_content(messages: List) -> List:
 
 import base64
 import mimetypes
-from cgi import parse_header
+from email.message import Message
 
 import httpx
 
@@ -2174,8 +2174,9 @@ def stringify_json_tool_call_content(messages: List) -> List:
 
 
 def _parse_content_type(content_type: str) -> str:
-    main_type, _ = parse_header(content_type)
-    return main_type
+    m = Message()
+    m['content-type'] = content_type
+    return m.get_content_type()
 
 
 class BedrockImageProcessor:

litellm/model_prices_and_context_window_backup.json

@@ -211,7 +211,7 @@
         "cache_read_input_token_cost": 0.00000055,
         "litellm_provider": "openai",
         "mode": "chat",
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "o3-mini-2025-01-31": {
@@ -223,7 +223,7 @@
         "cache_read_input_token_cost": 0.00000055,
         "litellm_provider": "openai",
         "mode": "chat",
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "o1-mini-2024-09-12": {
@@ -929,6 +929,30 @@
         "input_cost_per_character": 0.000030,
         "litellm_provider": "openai"
     },
+    "azure/o3-mini": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_vision": false,
+        "supports_prompt_caching": true
+    },
+    "azure/o3-mini-2025-01-31": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_vision": false,
+        "supports_prompt_caching": true
+    },
     "azure/tts-1": {
         "mode": "audio_speech", 
         "input_cost_per_character": 0.000015,
@@ -3876,6 +3900,16 @@
         "mode": "chat",
         "supports_function_calling": true
     },
+    "vertex_ai/codestral@2405": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 0.0000002,
+        "output_cost_per_token": 0.0000006,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
     "vertex_ai/imagegeneration@006": {
         "output_cost_per_image": 0.020,
         "litellm_provider": "vertex_ai-image-models",

litellm/proxy/db/create_views.py

@@ -158,11 +158,11 @@ async def create_missing_views(db: _db):  # noqa: PLR0915
         print("MonthlyGlobalSpendPerUserPerKey Created!")  # noqa
 
     try:
-        await db.query_raw("""SELECT 1 FROM DailyTagSpend LIMIT 1""")
+        await db.query_raw("""SELECT 1 FROM "DailyTagSpend" LIMIT 1""")
         print("DailyTagSpend Exists!")  # noqa
     except Exception:
         sql_query = """
-        CREATE OR REPLACE VIEW DailyTagSpend AS
+        CREATE OR REPLACE VIEW "DailyTagSpend" AS
         SELECT
             jsonb_array_elements_text(request_tags) AS individual_request_tag,
             DATE(s."startTime") AS spend_date,

model_prices_and_context_window.json

@@ -211,7 +211,7 @@
         "cache_read_input_token_cost": 0.00000055,
         "litellm_provider": "openai",
         "mode": "chat",
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "o3-mini-2025-01-31": {
@@ -223,7 +223,7 @@
         "cache_read_input_token_cost": 0.00000055,
         "litellm_provider": "openai",
         "mode": "chat",
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "o1-mini-2024-09-12": {
@@ -929,6 +929,30 @@
         "input_cost_per_character": 0.000030,
         "litellm_provider": "openai"
     },
+    "azure/o3-mini": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_vision": false,
+        "supports_prompt_caching": true
+    },
+    "azure/o3-mini-2025-01-31": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_vision": false,
+        "supports_prompt_caching": true
+    },
     "azure/tts-1": {
         "mode": "audio_speech", 
         "input_cost_per_character": 0.000015,
@@ -3876,6 +3900,16 @@
         "mode": "chat",
         "supports_function_calling": true
     },
+    "vertex_ai/codestral@2405": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 0.0000002,
+        "output_cost_per_token": 0.0000006,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
     "vertex_ai/imagegeneration@006": {
         "output_cost_per_image": 0.020,
         "litellm_provider": "vertex_ai-image-models",

tests/local_testing/test_batch_completions.py

@@ -43,6 +43,9 @@ def test_batch_completions():
     except Timeout as e:
         print(f"IN TIMEOUT")
         pass
+    except litellm.InternalServerError as e:
+        print(f"IN INTERNAL SERVER ERROR")
+        pass
     except Exception as e:
         pytest.fail(f"An error occurred: {e}")