litellm oss staging 02 23 2026

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

@@ -120,7 +120,7 @@ All models listed here https://docs.perplexity.ai/docs/model-cards are supported
 
 
 
-## Agentic Research API (Responses API)
+## Agent API (Responses API)
 
 Requires v1.72.6+
 
@@ -196,7 +196,7 @@ import os
 os.environ['PERPLEXITY_API_KEY'] = ""
 
 response = responses(
-    model="perplexity/openai/gpt-4o",
+    model="perplexity/openai/gpt-5.2",
     input="Explain quantum computing in simple terms",
     custom_llm_provider="perplexity",
     max_output_tokens=500,
@@ -215,7 +215,7 @@ import os
 os.environ['PERPLEXITY_API_KEY'] = ""
 
 response = responses(
-    model="perplexity/anthropic/claude-3-5-sonnet-20241022",
+    model="perplexity/anthropic/claude-sonnet-4-5",
     input="Write a short story about a robot learning to paint",
     custom_llm_provider="perplexity",
     max_output_tokens=500,
@@ -234,7 +234,7 @@ import os
 os.environ['PERPLEXITY_API_KEY'] = ""
 
 response = responses(
-    model="perplexity/google/gemini-2.0-flash-exp",
+    model="perplexity/google/gemini-2.5-flash",
     input="Explain the concept of neural networks",
     custom_llm_provider="perplexity",
     max_output_tokens=500,
@@ -253,7 +253,7 @@ import os
 os.environ['PERPLEXITY_API_KEY'] = ""
 
 response = responses(
-    model="perplexity/xai/grok-2-1212",
+    model="perplexity/xai/grok-4-1-fast-non-reasoning",
     input="What makes a good AI assistant?",
     custom_llm_provider="perplexity",
     max_output_tokens=500,
@@ -276,7 +276,7 @@ import os
 os.environ['PERPLEXITY_API_KEY'] = ""
 
 response = responses(
-    model="perplexity/openai/gpt-4o",
+    model="perplexity/openai/gpt-5.2",
     input="What's the weather in San Francisco today?",
     custom_llm_provider="perplexity",
     tools=[{"type": "web_search"}],
@@ -286,6 +286,78 @@ response = responses(
 print(response.output)
 ```
 
+### Function Calling
+
+The Agent API supports custom function tools. Pass function tools through unchanged:
+
+```python
+from litellm import responses
+import os
+
+os.environ['PERPLEXITY_API_KEY'] = ""
+
+response = responses(
+    model="perplexity/openai/gpt-5.2",
+    input="What's the weather in San Francisco?",
+    custom_llm_provider="perplexity",
+    tools=[
+        {"type": "web_search"},
+        {
+            "type": "function",
+            "function": {
+                "name": "get_weather",
+                "description": "Get the current weather for a location",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {"type": "string"},
+                        "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
+                    },
+                },
+            },
+        },
+    ],
+    instructions="Use tools when appropriate.",
+)
+
+print(response.output)
+```
+
+### Structured Outputs
+
+Request JSON schema structured outputs via the `text` parameter:
+
+```python
+from litellm import responses
+import os
+
+os.environ['PERPLEXITY_API_KEY'] = ""
+
+response = responses(
+    model="perplexity/preset/pro-search",
+    input="Extract key facts about the Eiffel Tower",
+    custom_llm_provider="perplexity",
+    text={
+        "format": {
+            "type": "json_schema",
+            "name": "facts",
+            "schema": {
+                "type": "object",
+                "properties": {
+                    "name": {"type": "string"},
+                    "height_meters": {"type": "number"},
+                    "year_built": {"type": "integer"},
+                },
+                "required": ["name", "height_meters", "year_built"],
+            },
+            "strict": True,
+        }
+    },
+)
+
+print(response.output)
+```
+
 
 ### Reasoning Effort (Responses API)
 
@@ -319,7 +391,7 @@ import os
 os.environ['PERPLEXITY_API_KEY'] = ""
 
 response = responses(
-    model="perplexity/anthropic/claude-3-5-sonnet-20241022",
+    model="perplexity/anthropic/claude-sonnet-4-5",
     input=[
         {"type": "message", "role": "system", "content": "You are a helpful assistant."},
         {"type": "message", "role": "user", "content": "What are the latest AI developments?"},
@@ -343,7 +415,7 @@ import os
 os.environ['PERPLEXITY_API_KEY'] = ""
 
 response = responses(
-    model="perplexity/openai/gpt-4o",
+    model="perplexity/openai/gpt-5.2",
     input="Tell me a story about space exploration",
     custom_llm_provider="perplexity",
     stream=True,
@@ -360,23 +432,28 @@ for chunk in response:
 
 | Provider | Model Name | Function Call |
 |----------|------------|---------------|
-| OpenAI | gpt-4o | `responses(model="perplexity/openai/gpt-4o", ...)` |
-| OpenAI | gpt-4o-mini | `responses(model="perplexity/openai/gpt-4o-mini", ...)` |
 | OpenAI | gpt-5.2 | `responses(model="perplexity/openai/gpt-5.2", ...)` |
-| Anthropic | claude-3-5-sonnet-20241022 | `responses(model="perplexity/anthropic/claude-3-5-sonnet-20241022", ...)` |
-| Anthropic | claude-3-5-haiku-20241022 | `responses(model="perplexity/anthropic/claude-3-5-haiku-20241022", ...)` |
-| Google | gemini-2.0-flash-exp | `responses(model="perplexity/google/gemini-2.0-flash-exp", ...)` |
-| Google | gemini-2.0-flash-thinking-exp | `responses(model="perplexity/google/gemini-2.0-flash-thinking-exp", ...)` |
-| xAI | grok-2-1212 | `responses(model="perplexity/xai/grok-2-1212", ...)` |
-| xAI | grok-2-vision-1212 | `responses(model="perplexity/xai/grok-2-vision-1212", ...)` |
+| OpenAI | gpt-5.1 | `responses(model="perplexity/openai/gpt-5.1", ...)` |
+| OpenAI | gpt-5-mini | `responses(model="perplexity/openai/gpt-5-mini", ...)` |
+| Anthropic | claude-opus-4-6 | `responses(model="perplexity/anthropic/claude-opus-4-6", ...)` |
+| Anthropic | claude-opus-4-5 | `responses(model="perplexity/anthropic/claude-opus-4-5", ...)` |
+| Anthropic | claude-sonnet-4-5 | `responses(model="perplexity/anthropic/claude-sonnet-4-5", ...)` |
+| Anthropic | claude-haiku-4-5 | `responses(model="perplexity/anthropic/claude-haiku-4-5", ...)` |
+| Google | gemini-3-pro-preview | `responses(model="perplexity/google/gemini-3-pro-preview", ...)` |
+| Google | gemini-3-flash-preview | `responses(model="perplexity/google/gemini-3-flash-preview", ...)` |
+| Google | gemini-2.5-pro | `responses(model="perplexity/google/gemini-2.5-pro", ...)` |
+| Google | gemini-2.5-flash | `responses(model="perplexity/google/gemini-2.5-flash", ...)` |
+| xAI | grok-4-1-fast-non-reasoning | `responses(model="perplexity/xai/grok-4-1-fast-non-reasoning", ...)` |
+| Perplexity | sonar | `responses(model="perplexity/perplexity/sonar", ...)` |
 
 ### Available Presets
 
-| Preset Name    | Function Call                                           |
-|----------------|--------------------------------------------------------|
-| fast-search    | `responses(model="perplexity/preset/fast-search", ...)`|
-| pro-search     | `responses(model="perplexity/preset/pro-search", ...)` |
-| deep-research  | `responses(model="perplexity/preset/deep-research", ...)`|
+| Preset Name | Function Call |
+|-------------|---------------|
+| fast-search | `responses(model="perplexity/preset/fast-search", ...)` |
+| pro-search | `responses(model="perplexity/preset/pro-search", ...)` |
+| deep-research | `responses(model="perplexity/preset/deep-research", ...)` |
+| advanced-deep-research | `responses(model="perplexity/preset/advanced-deep-research", ...)` |
 
 ### Complete Example
 
@@ -388,7 +465,7 @@ os.environ['PERPLEXITY_API_KEY'] = ""
 
 # Comprehensive example with multiple features
 response = responses(
-    model="perplexity/openai/gpt-4o",
+    model="perplexity/openai/gpt-5.2",
     input="Research the latest developments in quantum computing and provide sources",
     custom_llm_provider="perplexity",
     tools=[

litellm/cost_calculator.py

@@ -1242,6 +1242,16 @@ def completion_cost(  # noqa: PLR0915
                     )
                 elif call_type in _VIDEO_CALL_TYPES:
                     ### VIDEO GENERATION COST CALCULATION ###
+                    # Extract custom model_info for deployment-specific pricing
+                    _video_model_info: Optional[ModelInfo] = None
+                    if custom_pricing and litellm_logging_obj is not None:
+                        _litellm_params = getattr(
+                            litellm_logging_obj, "litellm_params", None
+                        )
+                        if _litellm_params is not None:
+                            _metadata = _litellm_params.get("metadata", {}) or {}
+                            _video_model_info = _metadata.get("model_info", None)
+
                     usage_obj = getattr(completion_response, "usage", None)
                     if completion_response is not None and usage_obj:
                         # Handle both dict and Pydantic Usage object
@@ -1262,12 +1272,14 @@ def completion_cost(  # noqa: PLR0915
                                 model=model,
                                 duration_seconds=duration_seconds,
                                 custom_llm_provider=custom_llm_provider,
+                                model_info=_video_model_info,
                             )
                     # Fallback to default video cost calculation if no duration available
                     return default_video_cost_calculator(
                         model=model,
                         duration_seconds=0.0,  # Default to 0 if no duration available
                         custom_llm_provider=custom_llm_provider,
+                        model_info=_video_model_info,
                     )
                 elif call_type in _SPEECH_CALL_TYPES:
                     prompt_characters = litellm.utils._count_characters(text=prompt)
@@ -1892,6 +1904,7 @@ def default_video_cost_calculator(
     model: str,
     duration_seconds: float,
     custom_llm_provider: Optional[str] = None,
+    model_info: Optional[ModelInfo] = None,
 ) -> float:
     """
     Default video cost calculator for video generation
@@ -1900,49 +1913,57 @@ def default_video_cost_calculator(
         model (str): Model name
         duration_seconds (float): Duration of the generated video in seconds
         custom_llm_provider (Optional[str]): Custom LLM provider
+        model_info (Optional[ModelInfo]): Deployment-level model info containing
+            custom video pricing. When provided, used before falling back to
+            the global litellm.model_cost lookup.
 
     Returns:
         float: Cost in USD for the video generation
 
     Raises:
         Exception: If model pricing not found in cost map
     """
-    # Build model names for cost lookup
-    base_model_name = model
-    model_name_without_custom_llm_provider: Optional[str] = None
-    if custom_llm_provider and model.startswith(f"{custom_llm_provider}/"):
-        model_name_without_custom_llm_provider = model.replace(
-            f"{custom_llm_provider}/", ""
-        )
-        base_model_name = (
-            f"{custom_llm_provider}/{model_name_without_custom_llm_provider}"
-        )
+    # Use custom model_info pricing if provided (deployment-specific pricing)
+    cost_info: Optional[dict] = None
+    if model_info is not None:
+        cost_info = dict(model_info)
+    else:
+        # Build model names for cost lookup
+        base_model_name = model
+        model_name_without_custom_llm_provider: Optional[str] = None
+        if custom_llm_provider and model.startswith(f"{custom_llm_provider}/"):
+            model_name_without_custom_llm_provider = model.replace(
+                f"{custom_llm_provider}/", ""
+            )
+            base_model_name = (
+                f"{custom_llm_provider}/{model_name_without_custom_llm_provider}"
+            )
 
-    verbose_logger.debug(f"Looking up cost for video model: {base_model_name}")
+        verbose_logger.debug(f"Looking up cost for video model: {base_model_name}")
 
-    model_without_provider = model.split("/")[-1]
+        model_without_provider = model.split("/")[-1]
 
-    # Try model with provider first, fall back to base model name
-    cost_info: Optional[dict] = None
-    models_to_check: List[Optional[str]] = [
-        base_model_name,
-        model,
-        model_without_provider,
-        model_name_without_custom_llm_provider,
-    ]
-    for _model in models_to_check:
-        if _model is not None and _model in litellm.model_cost:
-            cost_info = litellm.model_cost[_model]
-            break
+        # Try model with provider first, fall back to base model name
+        models_to_check: List[Optional[str]] = [
+            base_model_name,
+            model,
+            model_without_provider,
+            model_name_without_custom_llm_provider,
+        ]
+        for _model in models_to_check:
+            if _model is not None and _model in litellm.model_cost:
+                cost_info = litellm.model_cost[_model]
+                break
+
+        # If still not found, try with custom_llm_provider prefix
+        if cost_info is None and custom_llm_provider:
+            prefixed_model = f"{custom_llm_provider}/{model}"
+            if prefixed_model in litellm.model_cost:
+                cost_info = litellm.model_cost[prefixed_model]
 
-    # If still not found, try with custom_llm_provider prefix
-    if cost_info is None and custom_llm_provider:
-        prefixed_model = f"{custom_llm_provider}/{model}"
-        if prefixed_model in litellm.model_cost:
-            cost_info = litellm.model_cost[prefixed_model]
     if cost_info is None:
         raise Exception(
-            f"Model not found in cost map. Tried checking {models_to_check}"
+            f"Model not found in cost map for model={model}"
         )
 
     # Check for video-specific cost per second first

litellm/litellm_core_utils/litellm_logging.py

@@ -4709,6 +4709,7 @@ def get_model_cost_information(
         custom_pricing: Optional[bool],
         custom_llm_provider: Optional[str],
         init_response_obj: Union[Any, BaseModel, dict],
+        api_base: Optional[str] = None,
     ) -> StandardLoggingModelInformation:
         model_cost_name = _select_model_name_for_cost_calc(
             model=None,
@@ -4723,7 +4724,9 @@ def get_model_cost_information(
         else:
             try:
                 _model_cost_information = litellm.get_model_info(
-                    model=model_cost_name, custom_llm_provider=custom_llm_provider
+                    model=model_cost_name,
+                    custom_llm_provider=custom_llm_provider,
+                    api_base=api_base,
                 )
                 model_cost_information = StandardLoggingModelInformation(
                     model_map_key=model_cost_name,
@@ -5236,6 +5239,7 @@ def get_standard_logging_object_payload(
             custom_pricing=custom_pricing,
             custom_llm_provider=kwargs.get("custom_llm_provider"),
             init_response_obj=init_response_obj,
+            api_base=litellm_params.get("api_base"),
         )
         response_cost: float = kwargs.get("response_cost", 0) or 0.0
 

litellm/litellm_core_utils/prompt_templates/factory.py

@@ -1848,9 +1848,10 @@ def convert_to_anthropic_tool_invoke(
                         break
         else:
             # Regular tool_use
+            sanitized_tool_id = _sanitize_anthropic_tool_use_id(tool_id)
             _anthropic_tool_use_param = AnthropicMessagesToolUseParam(
                 type="tool_use",
-                id=tool_id,
+                id=sanitized_tool_id,
                 name=tool_name,
                 input=tool_input,
             )

litellm/llms/custom_httpx/http_handler.py

@@ -28,6 +28,7 @@
     AIOHTTP_CONNECTOR_LIMIT,
     AIOHTTP_CONNECTOR_LIMIT_PER_HOST,
     AIOHTTP_KEEPALIVE_TIMEOUT,
+    AIOHTTP_NEEDS_CLEANUP_CLOSED,
     AIOHTTP_TTL_DNS_CACHE,
     DEFAULT_SSL_CIPHERS,
 )
@@ -876,9 +877,10 @@ def _create_aiohttp_transport(
         transport_connector_kwargs = {
             "keepalive_timeout": AIOHTTP_KEEPALIVE_TIMEOUT,
             "ttl_dns_cache": AIOHTTP_TTL_DNS_CACHE,
-            "enable_cleanup_closed": True,
             **connector_kwargs,
         }
+        if AIOHTTP_NEEDS_CLEANUP_CLOSED:
+            transport_connector_kwargs["enable_cleanup_closed"] = True
         if AIOHTTP_CONNECTOR_LIMIT > 0:
             transport_connector_kwargs["limit"] = AIOHTTP_CONNECTOR_LIMIT
         if AIOHTTP_CONNECTOR_LIMIT_PER_HOST > 0: