diff --git a/examples/lar1_ollama_config.yaml b/examples/lar1_ollama_config.yaml
new file mode 100644
index 00000000000..998cbf169b3
--- /dev/null
+++ b/examples/lar1_ollama_config.yaml
@@ -0,0 +1,45 @@
+model_list:
+  - model_name: agent-router
+    litellm_params:
+      model: ollama/qwen3.5:9b
+      api_base: http://127.0.0.1:11434
+    model_info:
+      id: cloud-smart
+      type: cloud-smart
+
+  - model_name: agent-router
+    litellm_params:
+      model: ollama/phi4-mini:latest
+      api_base: http://127.0.0.1:11434
+    model_info:
+      id: cloud-fast
+      type: cloud-fast
+
+  - model_name: agent-router
+    litellm_params:
+      model: ollama/llama3.2:3b
+      api_base: http://127.0.0.1:11434
+    model_info:
+      id: local
+      type: local
+
+  - model_name: agent-router
+    litellm_params:
+      model: ollama/lfm2.5-thinking:latest
+      api_base: http://127.0.0.1:11434
+    model_info:
+      id: deep
+      type: deep
+
+router_settings:
+  routing_strategy: lar1
+  routing_strategy_args:
+    confidence_threshold_low: 0.3
+    confidence_threshold_medium: 0.5
+    confidence_threshold_high: 0.7
+
+general_settings:
+  master_key: sk-lar1-demo
+
+litellm_settings:
+  set_verbose: true
diff --git a/litellm/integrations/focus/destinations/mavvrik_destination.py b/litellm/integrations/focus/destinations/mavvrik_destination.py
index 1e3c98b9a70..81944ba69e2 100644
--- a/litellm/integrations/focus/destinations/mavvrik_destination.py
+++ b/litellm/integrations/focus/destinations/mavvrik_destination.py
@@ -3,6 +3,7 @@
 Flow:
   1. GET /metrics/agent/ai/{connection_id}/upload-url → GCS signed URL
   2. PUT <signed_url> with CSV content
+  3. PATCH /metrics/agent/ai/{connection_id} → advance metricsMarker
 """
 
 from __future__ import annotations
@@ -33,8 +34,7 @@ def _validate_api_endpoint(api_endpoint: str) -> None:
     hostname = (urlparse(api_endpoint).hostname or "").lower()
     if not any(hostname.endswith(suffix) for suffix in _MAVVRIK_ALLOWED_SUFFIXES):
         raise ValueError(
-            "MAVVRIK_API_ENDPOINT host must be a Mavvrik domain "
-            "(e.g. https://api.mavvrik.dev/<tenant_id>)"
+            "MAVVRIK_API_ENDPOINT host must be a Mavvrik domain (e.g. https://api.mavvrik.dev/<tenant_id>)"
         )
 
 
@@ -50,8 +50,7 @@ def _validate_gcs_url(url: str, label: str) -> None:
         or hostname.endswith(".storage.googleapis.com")
     ):
         raise ValueError(
-            f"Mavvrik FOCUS destination: {label} must be a GCS endpoint "
-            f"(storage.googleapis.com), got '{hostname}'"
+            f"Mavvrik FOCUS destination: {label} must be a GCS endpoint (storage.googleapis.com), got '{hostname}'"
         )
 
 
@@ -127,8 +126,6 @@ class FocusMavvrikDestination(FocusDestination):
             timeout=30.0,
         )
         if resp.status_code == 410:
-            # Connector has been disconnected in Mavvrik — reset flag so next
-            # delivery attempt re-registers after it becomes active again.
             self._registered = False
             raise RuntimeError(
                 "Mavvrik FOCUS destination: connector is disconnected (410). "
@@ -136,8 +133,7 @@ class FocusMavvrikDestination(FocusDestination):
             )
         if resp.status_code >= 400:
             raise RuntimeError(
-                f"Mavvrik FOCUS destination: register failed "
-                f"({resp.status_code}): {resp.text[:200]}"
+                f"Mavvrik FOCUS destination: register failed ({resp.status_code}): {resp.text[:200]}"
             )
         self._registered = True
         metrics_marker = resp.json().get("metricsMarker", 0)
@@ -159,8 +155,7 @@ class FocusMavvrikDestination(FocusDestination):
         )
         if resp.status_code >= 400:
             raise RuntimeError(
-                f"Mavvrik FOCUS destination: failed to get signed URL "
-                f"({resp.status_code}): {resp.text[:200]}"
+                f"Mavvrik FOCUS destination: failed to get signed URL ({resp.status_code}): {resp.text[:200]}"
             )
         signed_url = resp.json().get("url")
         if not signed_url:
@@ -205,8 +200,7 @@ class FocusMavvrikDestination(FocusDestination):
         )
         if init_resp.status_code not in (200, 201):
             raise RuntimeError(
-                f"Mavvrik FOCUS destination: GCS session init failed "
-                f"({init_resp.status_code}): {init_resp.text[:400]}"
+                f"Mavvrik FOCUS destination: GCS session init failed ({init_resp.status_code}): {init_resp.text[:400]}"
             )
 
         session_uri = init_resp.headers.get("Location")
@@ -217,8 +211,7 @@ class FocusMavvrikDestination(FocusDestination):
         _validate_gcs_url(session_uri, "session URI")
 
         verbose_logger.debug(
-            "Mavvrik FOCUS destination: GCS session started, uploading %d gzip bytes "
-            "in %d chunk(s)",
+            "Mavvrik FOCUS destination: GCS session started, uploading %d gzip bytes in %d chunk(s)",
             total,
             max(1, -(-total // _GCS_CHUNK_SIZE)),  # ceiling division
         )
@@ -273,14 +266,33 @@ class FocusMavvrikDestination(FocusDestination):
                 pass
             raise
 
+    async def _update_metrics_marker(self, date_epoch: int) -> None:
+        """PATCH agent endpoint to advance metricsMarker after a successful upload."""
+        resp = await self._http.client.request(
+            method="PATCH",
+            url=self._agent_url,
+            headers=self._auth_headers,
+            json={"metricsMarker": date_epoch},
+            timeout=30.0,
+        )
+        if resp.status_code == 410:
+            self._registered = False
+            raise RuntimeError(
+                "Mavvrik FOCUS destination: connector is disconnected (410). "
+                "Re-enable the connection in the Mavvrik dashboard."
+            )
+        if resp.status_code >= 400:
+            raise RuntimeError(
+                f"Mavvrik FOCUS destination: failed to update metricsMarker "
+                f"({resp.status_code}): {resp.text[:200]}"
+            )
+        verbose_logger.debug(
+            "Mavvrik FOCUS destination: metricsMarker advanced to %s", date_epoch
+        )
+
     async def get_metrics_marker(self) -> Optional[int]:
         """Register with Mavvrik and return the current metricsMarker.
 
-        The metricsMarker is a Unix timestamp (seconds) representing the last
-        date Mavvrik has successfully ingested. Called on every scheduled run
-        so the logger can detect and catch up any dates missed due to previous
-        export failures.
-
         Always calls the Mavvrik register API — unlike deliver() which skips
         registration once _registered is True, catch-up requires a fresh
         marker value on every run.
@@ -300,8 +312,7 @@ class FocusMavvrikDestination(FocusDestination):
             )
         if resp.status_code >= 400:
             raise RuntimeError(
-                f"Mavvrik FOCUS destination: register failed "
-                f"({resp.status_code}): {resp.text[:200]}"
+                f"Mavvrik FOCUS destination: register failed ({resp.status_code}): {resp.text[:200]}"
             )
         self._registered = True
         metrics_marker = resp.json().get("metricsMarker", 0)
@@ -321,14 +332,19 @@ class FocusMavvrikDestination(FocusDestination):
 
         Uses the start date of the time window as the object date key.
         """
+        date_str = time_window.start_time.strftime("%Y-%m-%d")
+        date_epoch = int(time_window.start_time.timestamp())
+
+        await self._ensure_registered()
+
         if not content:
             verbose_logger.debug(
-                "Mavvrik FOCUS destination: empty content, skipping upload"
+                "Mavvrik FOCUS destination: empty content for date=%s, advancing marker",
+                date_str,
             )
+            await self._update_metrics_marker(date_epoch)
             return
 
-        date_str = time_window.start_time.strftime("%Y-%m-%d")
-
         verbose_logger.debug(
             "Mavvrik FOCUS destination: uploading %d bytes for date=%s (%s)",
             len(content),
@@ -336,9 +352,9 @@ class FocusMavvrikDestination(FocusDestination):
             filename,
         )
 
-        await self._ensure_registered()
         signed_url = await self._get_signed_url(date_str)
         await self._upload_to_gcs(signed_url, content)
+        await self._update_metrics_marker(date_epoch)
 
         verbose_logger.debug(
             "Mavvrik FOCUS destination: upload complete for date=%s", date_str
diff --git a/litellm/integrations/mavvrik_focus/mavvrik_focus_logger.py b/litellm/integrations/mavvrik_focus/mavvrik_focus_logger.py
index 47d3e1da7bc..49030ffc2e1 100644
--- a/litellm/integrations/mavvrik_focus/mavvrik_focus_logger.py
+++ b/litellm/integrations/mavvrik_focus/mavvrik_focus_logger.py
@@ -72,6 +72,16 @@ def _parse_metrics_marker(
     return None
 
 
+def _is_empty_metrics_marker(marker: Optional[object]) -> bool:
+    if marker is None:
+        return True
+    if isinstance(marker, (int, float)):
+        return marker == 0
+    if isinstance(marker, str):
+        return not marker.strip()
+    return False
+
+
 class MavvrikFocusLogger(FocusLogger):
     """FOCUS-based export logger that routes to the Mavvrik destination."""
 
@@ -122,19 +132,17 @@ class MavvrikFocusLogger(FocusLogger):
                 window.start_time.date(),
                 window.end_time.date(),
             )
+        payload = b""
         if data.is_empty():
             verbose_proxy_logger.debug(
                 "Mavvrik FOCUS export: no usage data for window %s", window
             )
-            return
-        normalized = engine._transformer.transform(data)
-        if normalized.is_empty():
-            return
-        payload = engine._serializer.serialize(normalized)
-        if not payload:
-            return
+        else:
+            normalized = engine._transformer.transform(data)
+            if not normalized.is_empty():
+                payload = engine._serializer.serialize(normalized)
         await engine._destination.deliver(
-            content=payload,
+            content=payload or b"",
             time_window=window,
             filename=engine._build_filename(window),
         )
@@ -149,8 +157,8 @@ class MavvrikFocusLogger(FocusLogger):
 
         On each run:
         1. Register with Mavvrik → get metricsMarker (last successfully ingested date)
-        2. If metricsMarker is behind yesterday, catch up missed dates (capped at
-           _MAX_CATCHUP_DAYS to avoid runaway loops on long outages)
+        2. If metricsMarker is behind yesterday (or 0/None for a fresh connector),
+           catch up missed dates (capped at _MAX_CATCHUP_DAYS)
         3. Export yesterday (today's daily window)
 
         This ensures a failed export on day N is automatically retried on day N+1
@@ -177,13 +185,19 @@ class MavvrikFocusLogger(FocusLogger):
 
         last_ingested = _parse_metrics_marker(marker)
 
-        # Catch up missed dates, capped at _MAX_CATCHUP_DAYS
-        if last_ingested and last_ingested < yesterday:
-            # Never go further back than _MAX_CATCHUP_DAYS from yesterday
-            earliest_catchup = yesterday - timedelta(days=self._MAX_CATCHUP_DAYS - 1)
-            catch_up_date = max(last_ingested + timedelta(days=1), earliest_catchup)
+        is_empty_marker = _is_empty_metrics_marker(marker)
+        earliest_catchup = yesterday - timedelta(days=self._MAX_CATCHUP_DAYS - 1)
+        if is_empty_marker or (last_ingested is not None and last_ingested < yesterday):
+            catch_up_date = (
+                earliest_catchup
+                if last_ingested is None
+                else max(last_ingested + timedelta(days=1), earliest_catchup)
+            )
 
-            if last_ingested + timedelta(days=1) < earliest_catchup:
+            if (
+                last_ingested is not None
+                and last_ingested + timedelta(days=1) < earliest_catchup
+            ):
                 verbose_proxy_logger.warning(
                     "Mavvrik FOCUS export: metricsMarker is more than %d days behind "
                     "(%s). Catching up from %s only; earlier data will not be re-exported.",
@@ -197,18 +211,24 @@ class MavvrikFocusLogger(FocusLogger):
                     "Mavvrik FOCUS export: catching up missed date %s",
                     catch_up_date.date(),
                 )
+                # Use now as end_time for catch-up windows too — rows for old dates
+                # may have been flushed to DB well after their calendar day ended.
+                catch_up_end = min(catch_up_date + timedelta(days=1), now)
                 window = FocusTimeWindow(
                     start_time=catch_up_date,
-                    end_time=catch_up_date + timedelta(days=1),
+                    end_time=catch_up_end,
                     frequency="daily",
                 )
                 await self._export_window(window=window, limit=None)
                 catch_up_date += timedelta(days=1)
 
-        # Export yesterday's window (the normal daily run)
+        # Export yesterday's window (the normal daily run).
+        # Use `now` as end_time so spend rows flushed after midnight are included.
+        # LiteLLM's DailyUserSpend rows for a given date keep getting updated_at
+        # bumped as the flush job runs; capping at midnight would miss those updates.
         window = FocusTimeWindow(
             start_time=yesterday,
-            end_time=yesterday + timedelta(days=1),
+            end_time=now,
             frequency="daily",
         )
         await self._export_window(window=window, limit=None)
@@ -253,6 +273,21 @@ class MavvrikFocusLogger(FocusLogger):
             )
             if type(cb) is MavvrikFocusLogger
         ]
+        if not loggers and "mavvrik" in litellm.callbacks:
+            # The logger is registered as the string "mavvrik" but hasn't been
+            # instantiated yet (lazy init happens on first LLM call). Force it now
+            # so the scheduler can register the daily export job at startup.
+            from litellm.litellm_core_utils.litellm_logging import (  # noqa: PLC0415
+                _init_custom_logger_compatible_class,
+            )
+
+            instance = _init_custom_logger_compatible_class(
+                logging_integration="mavvrik",
+                internal_usage_cache=None,
+                llm_router=None,
+            )
+            if isinstance(instance, MavvrikFocusLogger):
+                loggers = [instance]
         if not loggers:
             verbose_proxy_logger.debug(
                 "No MavvrikFocusLogger registered; skipping scheduler"
diff --git a/litellm/llms/anthropic/chat/handler.py b/litellm/llms/anthropic/chat/handler.py
index b1212f93059..7154a6f3595 100644
--- a/litellm/llms/anthropic/chat/handler.py
+++ b/litellm/llms/anthropic/chat/handler.py
@@ -11,7 +11,6 @@ from typing import (
     Dict,
     List,
     Literal,
-    Optional,
     Tuple,
     Union,
     cast,
@@ -73,17 +72,17 @@ if TYPE_CHECKING:
 
 
 async def make_call(
-    client: Optional[AsyncHTTPHandler],
+    client: AsyncHTTPHandler | None,
     api_base: str,
     headers: dict,
     data: str,
     model: str,
     messages: list,
     logging_obj,
-    timeout: Optional[Union[float, httpx.Timeout]],
+    timeout: Union[float, httpx.Timeout] | None,
     json_mode: bool,
-    speed: Optional[str] = None,
-    tool_name_reverse_map: Optional[Dict[str, str]] = None,
+    speed: str | None = None,
+    tool_name_reverse_map: Dict[str, str] | None = None,
 ) -> Tuple[Any, httpx.Headers]:
     if client is None:
         client = litellm.module_level_aclient
@@ -133,17 +132,17 @@ async def make_call(
 
 
 def make_sync_call(
-    client: Optional[HTTPHandler],
+    client: HTTPHandler | None,
     api_base: str,
     headers: dict,
     data: str,
     model: str,
     messages: list,
     logging_obj,
-    timeout: Optional[Union[float, httpx.Timeout]],
+    timeout: Union[float, httpx.Timeout] | None,
     json_mode: bool,
-    speed: Optional[str] = None,
-    tool_name_reverse_map: Optional[Dict[str, str]] = None,
+    speed: str | None = None,
+    tool_name_reverse_map: Dict[str, str] | None = None,
 ) -> Tuple[Any, httpx.Headers]:
     if client is None:
         client = litellm.module_level_client  # re-use a module level client
@@ -213,7 +212,7 @@ class AnthropicChatCompletion(BaseLLM):
         model_response: ModelResponse,
         print_verbose: Callable,
         timeout: Union[float, httpx.Timeout],
-        client: Optional[AsyncHTTPHandler],
+        client: AsyncHTTPHandler | None,
         encoding,
         api_key,
         logging_obj,
@@ -277,7 +276,7 @@ class AnthropicChatCompletion(BaseLLM):
         provider_config: "BaseConfig",
         logger_fn=None,
         headers={},
-        client: Optional[AsyncHTTPHandler] = None,
+        client: AsyncHTTPHandler | None = None,
     ) -> Union[ModelResponse, "CustomStreamWrapper"]:
         async_handler = client or get_async_httpx_client(
             llm_provider=litellm.LlmProviders.ANTHROPIC
@@ -539,9 +538,9 @@ class ModelResponseIterator:
         self,
         streaming_response,
         sync_stream: bool,
-        json_mode: Optional[bool] = False,
-        speed: Optional[str] = None,
-        tool_name_reverse_map: Optional[Dict[str, str]] = None,
+        json_mode: bool | None = False,
+        speed: str | None = None,
+        tool_name_reverse_map: Dict[str, str] | None = None,
     ):
         self.streaming_response = streaming_response
         self.response_iterator = self.streaming_response
@@ -571,7 +570,7 @@ class ModelResponseIterator:
 
         # Track current content block type to avoid emitting tool calls for non-tool blocks
         # See: https://github.com/BerriAI/litellm/issues/17254
-        self.current_content_block_type: Optional[str] = None
+        self.current_content_block_type: str | None = None
 
         # Accumulate web_search_tool_result blocks for multi-turn reconstruction
         # See: https://github.com/BerriAI/litellm/issues/17737
@@ -587,8 +586,8 @@ class ModelResponseIterator:
         # Track server tool use inputs and results for code_interpreter_results
         self._server_tool_inputs: Dict[str, Any] = {}
         self.tool_results: List[Dict[str, Any]] = []
-        self._current_server_tool_id: Optional[str] = None
-        self._container_id: Optional[str] = None
+        self._current_server_tool_id: str | None = None
+        self._container_id: str | None = None
 
     def check_empty_tool_call_args(self) -> bool:
         """
@@ -629,16 +628,18 @@ class ModelResponseIterator:
         self, chunk: dict
     ) -> Tuple[
         str,
-        Optional[ChatCompletionToolCallChunk],
+        ChatCompletionToolCallChunk | None,
         List[Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]],
         Dict[str, Any],
+        str | None,
     ]:
         """
         Helper function to handle the content block delta
         """
         text = ""
-        tool_use: Optional[ChatCompletionToolCallChunk] = None
+        tool_use: ChatCompletionToolCallChunk | None = None
         provider_specific_fields = {}
+        reasoning_content: str | None = None
         content_block = ContentBlockDelta(**chunk)  # type: ignore
         thinking_blocks: List[
             Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]
@@ -673,14 +674,31 @@ class ModelResponseIterator:
             thinking_content = content_block["delta"].get("thinking")
             if isinstance(thinking_content, str) and thinking_content:
                 self.reasoning_content_chunks.append(thinking_content)
-            thinking_blocks = [
-                ChatCompletionThinkingBlock(
-                    type="thinking",
-                    thinking=thinking_content or "",
-                    signature=str(content_block["delta"].get("signature") or ""),
-                )
-            ]
-            provider_specific_fields["thinking_blocks"] = thinking_blocks
+                reasoning_content = thinking_content
+                thinking_blocks = [
+                    ChatCompletionThinkingBlock(
+                        type="thinking",
+                        thinking=thinking_content,
+                    )
+                ]
+                provider_specific_fields["thinking_blocks"] = thinking_blocks
+
+            signature = content_block["delta"].get("signature")
+            if isinstance(signature, str) and signature:
+                thinking_blocks = [
+                    ChatCompletionThinkingBlock(
+                        type="thinking",
+                        thinking="".join(
+                            cast(str, block["delta"].get("thinking"))
+                            for block in self.content_blocks
+                            if isinstance(block["delta"].get("thinking"), str)
+                        ),
+                        signature=signature,
+                    )
+                ]
+                provider_specific_fields["thinking_blocks"] = thinking_blocks
+                if reasoning_content is None:
+                    reasoning_content = ""
         elif (
             "content" in content_block["delta"]
             and content_block["delta"].get("type") == "compaction_delta"
@@ -691,25 +709,13 @@ class ModelResponseIterator:
                 "content": content_block["delta"]["content"],
             }
 
-        return text, tool_use, thinking_blocks, provider_specific_fields
-
-    def _handle_reasoning_content(
-        self,
-        thinking_blocks: List[
-            Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]
-        ],
-    ) -> Optional[str]:
-        """
-        Handle the reasoning content
-        """
-        reasoning_content = None
-        for block in thinking_blocks:
-            thinking_content = cast(Optional[str], block.get("thinking"))
-            if reasoning_content is None:
-                reasoning_content = ""
-            if thinking_content is not None:
-                reasoning_content += thinking_content
-        return reasoning_content
+        return (
+            text,
+            tool_use,
+            thinking_blocks,
+            provider_specific_fields,
+            reasoning_content,
+        )
 
     def _handle_redacted_thinking_content(
         self,
@@ -780,18 +786,19 @@ class ModelResponseIterator:
             type_chunk = chunk.get("type", "") or ""
 
             text = ""
-            tool_use: Optional[ChatCompletionToolCallChunk] = None
+            tool_use: ChatCompletionToolCallChunk | None = None
             finish_reason = ""
-            usage: Optional[Usage] = None
+            usage: Usage | None = None
             provider_specific_fields: Dict[str, Any] = {}
-            reasoning_content: Optional[str] = None
-            thinking_blocks: Optional[
+            reasoning_content: str | None = None
+            thinking_blocks: (
                 List[
                     Union[
                         ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock
                     ]
                 ]
-            ] = None
+                | None
+            ) = None
 
             # Always use index=0 for OpenAI choice format (fixes multi-choice errors)
             index = 0
@@ -805,11 +812,8 @@ class ModelResponseIterator:
                     tool_use,
                     thinking_blocks,
                     provider_specific_fields,
+                    reasoning_content,
                 ) = self._content_block_delta_helper(chunk=chunk)
-                if thinking_blocks:
-                    reasoning_content = self._handle_reasoning_content(
-                        thinking_blocks=thinking_blocks
-                    )
             elif type_chunk == "content_block_start":
                 """
                 event: content_block_start
@@ -1061,8 +1065,8 @@ class ModelResponseIterator:
             raise ValueError(f"Failed to decode JSON from chunk: {chunk}")
 
     def _handle_json_mode_chunk(
-        self, text: str, tool_use: Optional[ChatCompletionToolCallChunk]
-    ) -> Tuple[str, Optional[ChatCompletionToolCallChunk]]:
+        self, text: str, tool_use: ChatCompletionToolCallChunk | None
+    ) -> Tuple[str, ChatCompletionToolCallChunk | None]:
         """
         If JSON mode is enabled, convert the tool call to a message.
 
@@ -1110,7 +1114,7 @@ class ModelResponseIterator:
 
     def _handle_message_delta(
         self, chunk: dict
-    ) -> Tuple[str, Optional[Usage], Optional[Dict[str, Any]]]:
+    ) -> Tuple[str, Usage | None, Dict[str, Any] | None]:
         """
         Handle message_delta event for finish_reason, usage, and container.
 
@@ -1134,7 +1138,7 @@ class ModelResponseIterator:
 
     def _handle_accumulated_json_chunk(
         self, data_str: str
-    ) -> Optional[ModelResponseStream]:
+    ) -> ModelResponseStream | None:
         """
         Handle partial JSON chunks by accumulating them until valid JSON is received.
 
@@ -1159,7 +1163,7 @@ class ModelResponseIterator:
             # If it's not valid JSON yet, continue to the next chunk
             return None
 
-    def _parse_sse_data(self, str_line: str) -> Optional[ModelResponseStream]:
+    def _parse_sse_data(self, str_line: str) -> ModelResponseStream | None:
         """
         Parse SSE data line, handling both complete and partial JSON chunks.
 
diff --git a/litellm/llms/base_llm/chat/transformation.py b/litellm/llms/base_llm/chat/transformation.py
index 8f9d5cad7c4..4f7e98af780 100644
--- a/litellm/llms/base_llm/chat/transformation.py
+++ b/litellm/llms/base_llm/chat/transformation.py
@@ -377,6 +377,17 @@ class BaseConfig(ABC):
     ) -> "ModelResponse":
         pass
 
+    def transform_parsed_response_dict(self, parsed_response: dict) -> dict:
+        """
+        Repair a parsed OpenAI-format response dict before generic conversion.
+
+        Providers routed through the OpenAI SDK handler bypass transform_response,
+        which calls convert_to_model_response_object directly on the SDK's parsed
+        output. Override this to normalize a malformed response (e.g. github_copilot
+        returning empty choices for Anthropic-native Claude responses).
+        """
+        return parsed_response
+
     @abstractmethod
     def get_error_class(
         self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
diff --git a/litellm/llms/base_llm/rerank/transformation.py b/litellm/llms/base_llm/rerank/transformation.py
index 166f876ba04..eac44ba85c5 100644
--- a/litellm/llms/base_llm/rerank/transformation.py
+++ b/litellm/llms/base_llm/rerank/transformation.py
@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any, Dict, List, Tuple, Union
 
 import httpx
 
@@ -22,8 +22,8 @@ class BaseRerankConfig(ABC):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> dict:
         pass
 
@@ -33,7 +33,7 @@ class BaseRerankConfig(ABC):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         return {}
 
@@ -44,7 +44,7 @@ class BaseRerankConfig(ABC):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
@@ -54,9 +54,9 @@ class BaseRerankConfig(ABC):
     @abstractmethod
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         """
         OPTIONAL
@@ -79,12 +79,13 @@ class BaseRerankConfig(ABC):
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         pass
 
@@ -100,9 +101,9 @@ class BaseRerankConfig(ABC):
     def calculate_rerank_cost(
         self,
         model: str,
-        custom_llm_provider: Optional[str] = None,
-        billed_units: Optional[RerankBilledUnits] = None,
-        model_info: Optional[ModelInfo] = None,
+        custom_llm_provider: str | None = None,
+        billed_units: RerankBilledUnits | None = None,
+        model_info: ModelInfo | None = None,
     ) -> Tuple[float, float]:
         """
         Calculates the cost per query for a given rerank model.
diff --git a/litellm/llms/bedrock/common_utils.py b/litellm/llms/bedrock/common_utils.py
index 69c0a8529b4..44312eb3926 100644
--- a/litellm/llms/bedrock/common_utils.py
+++ b/litellm/llms/bedrock/common_utils.py
@@ -601,6 +601,15 @@ def extract_model_name_from_bedrock_arn(model: str) -> str:
     return model
 
 
+def is_bedrock_application_inference_profile_arn(model: str) -> bool:
+    """
+    An application inference profile ARN ends in an opaque id with no provider
+    substring, so the invoke path cannot resolve a provider from it. Such ARNs
+    must use the converse route, which needs no provider.
+    """
+    return ":application-inference-profile/" in model
+
+
 def strip_bedrock_routing_prefix(model: str) -> str:
     """Strip LiteLLM routing prefixes from model name."""
     for prefix in ["bedrock/", "converse/", "invoke/", "openai/", "nova-2/", "nova/"]:
@@ -919,6 +928,9 @@ class BedrockModelInfo(BaseLLMModelInfo):
         ) or _model_after_bedrock.startswith("nova/"):
             return "converse"
 
+        if is_bedrock_application_inference_profile_arn(model):
+            return "converse"
+
         base_model = BedrockModelInfo.get_base_model(model)
         alt_model = BedrockModelInfo.get_non_litellm_routing_model_name(model=model)
         if (
diff --git a/litellm/llms/bedrock/embed/embedding.py b/litellm/llms/bedrock/embed/embedding.py
index bc72f04deac..e07ccb8c11b 100644
--- a/litellm/llms/bedrock/embed/embedding.py
+++ b/litellm/llms/bedrock/embed/embedding.py
@@ -226,6 +226,10 @@ class BedrockEmbedding(BaseAWSLLM):
                 returned_response = AmazonTitanV2Config()._transform_response(
                     response_list=response_list, model=model
                 )
+            elif model == "amazon.titan-embed-g1-text-02":
+                returned_response = AmazonTitanG1Config()._transform_response(
+                    response_list=response_list, model=model
+                )
             elif provider == "twelvelabs":
                 returned_response = (
                     TwelveLabsMarengoEmbeddingConfig()._transform_response(
@@ -449,6 +453,7 @@ class BedrockEmbedding(BaseAWSLLM):
             "amazon.titan-embed-image-v1",
             "amazon.titan-embed-text-v1",
             "amazon.titan-embed-text-v2:0",
+            "amazon.titan-embed-g1-text-02",
         ]:
             batch_data = []
             for i in input:
@@ -466,6 +471,10 @@ class BedrockEmbedding(BaseAWSLLM):
                     transformed_request = AmazonTitanV2Config()._transform_request(
                         input=i, inference_params=inference_params
                     )
+                elif model == "amazon.titan-embed-g1-text-02":
+                    transformed_request = AmazonTitanG1Config()._transform_request(
+                        input=i, inference_params=inference_params
+                    )
                 else:
                     raise Exception(
                         "Unmapped model. Received={}. Expected={}".format(
@@ -474,6 +483,7 @@ class BedrockEmbedding(BaseAWSLLM):
                                 "amazon.titan-embed-image-v1",
                                 "amazon.titan-embed-text-v1",
                                 "amazon.titan-embed-text-v2:0",
+                                "amazon.titan-embed-g1-text-02",
                             ],
                         )
                     )
diff --git a/litellm/llms/cohere/rerank/guardrail_translation/handler.py b/litellm/llms/cohere/rerank/guardrail_translation/handler.py
index e9a5823d2b8..0824e1cca41 100644
--- a/litellm/llms/cohere/rerank/guardrail_translation/handler.py
+++ b/litellm/llms/cohere/rerank/guardrail_translation/handler.py
@@ -26,11 +26,18 @@ class CohereRerankHandler(BaseTranslation):
 
     The handler specifically processes:
     - The 'query' parameter (string)
+    - The 'instruction' parameter (string), when present
 
     Note: Documents are not processed by guardrails as they are the corpus
     being searched, not user input.
     """
 
+    # User-controlled free-text fields that reach the model and must be
+    # scanned. 'instruction' is folded into the prompt by instruction-aware
+    # rerankers (e.g. hosted vLLM / Qwen3-Reranker), so it is as sensitive as
+    # 'query'; omitting it would let a caller smuggle content past guardrails.
+    _SCANNED_FIELDS = ("query", "instruction")
+
     async def process_input_messages(
         self,
         data: dict,
@@ -38,42 +45,55 @@ class CohereRerankHandler(BaseTranslation):
         litellm_logging_obj: Optional[Any] = None,
     ) -> Any:
         """
-        Process input query by applying guardrails.
+        Process input text fields ('query' and 'instruction') by applying
+        guardrails and writing the sanitized values back.
 
         Args:
-            data: Request data dictionary containing 'query'
+            data: Request data dictionary containing 'query' and optionally
+                'instruction'
             guardrail_to_apply: The guardrail instance to apply
 
         Returns:
-            Modified data with guardrails applied to query only
+            Modified data with guardrails applied to query/instruction only
         """
-        # Process query only
-        query = data.get("query")
-        if query is not None and isinstance(query, str):
-            inputs = GenericGuardrailAPIInputs(texts=[query])
-            # Include model information if available
-            model = data.get("model")
-            if model:
-                inputs["model"] = model
-            guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
-                inputs=inputs,
-                request_data=data,
-                input_type="request",
-                logging_obj=litellm_logging_obj,
+        # Collect every scannable text field in a stable order so the
+        # guardrailed results can be written back to the right key by index.
+        fields_to_scan = [
+            (key, data[key])
+            for key in self._SCANNED_FIELDS
+            if isinstance(data.get(key), str)
+        ]
+        if not fields_to_scan:
+            verbose_proxy_logger.debug(
+                "Rerank: No query/instruction to process or not strings"
             )
-            guardrailed_texts = guardrailed_inputs.get("texts", [])
-            data["query"] = guardrailed_texts[0] if guardrailed_texts else query
+            return data
 
-            verbose_proxy_logger.debug(
-                "Rerank: Applied guardrail to query. "
-                "Original length: %d, New length: %d",
-                len(query),
-                len(data["query"]),
-            )
-        else:
-            verbose_proxy_logger.debug(
-                "Rerank: No query to process or query is not a string"
-            )
+        inputs = GenericGuardrailAPIInputs(texts=[value for _, value in fields_to_scan])
+        # Include model information if available
+        model = data.get("model")
+        if model:
+            inputs["model"] = model
+        guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
+            inputs=inputs,
+            request_data=data,
+            input_type="request",
+            logging_obj=litellm_logging_obj,
+        )
+        guardrailed_texts = guardrailed_inputs.get("texts", [])
+
+        for idx, (key, original) in enumerate(fields_to_scan):
+            # Defensive: only write back when the guardrail returned a value for
+            # this index; otherwise keep the original (never forward unscanned).
+            if idx < len(guardrailed_texts):
+                data[key] = guardrailed_texts[idx]
+                verbose_proxy_logger.debug(
+                    "Rerank: Applied guardrail to %s. "
+                    "Original length: %d, New length: %d",
+                    key,
+                    len(original),
+                    len(data[key]),
+                )
 
         return data
 
diff --git a/litellm/llms/cohere/rerank/transformation.py b/litellm/llms/cohere/rerank/transformation.py
index 64ae8e8ffa7..dd3f0f1a446 100644
--- a/litellm/llms/cohere/rerank/transformation.py
+++ b/litellm/llms/cohere/rerank/transformation.py
@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 import httpx
 
@@ -22,9 +22,9 @@ class CohereRerankConfig(BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         if api_base:
             # Remove trailing slashes and ensure clean base URL
@@ -46,17 +46,18 @@ class CohereRerankConfig(BaseRerankConfig):
 
     def map_cohere_rerank_params(
         self,
-        non_default_params: Optional[dict],
+        non_default_params: dict | None,
         model: str,
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         """
         Map Cohere rerank params
@@ -78,8 +79,8 @@ class CohereRerankConfig(BaseRerankConfig):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> dict:
         if api_key is None:
             api_key = (
@@ -111,7 +112,7 @@ class CohereRerankConfig(BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         if "query" not in optional_rerank_params:
             raise ValueError("query is required for Cohere rerank")
@@ -134,7 +135,7 @@ class CohereRerankConfig(BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
diff --git a/litellm/llms/cohere/rerank_v2/transformation.py b/litellm/llms/cohere/rerank_v2/transformation.py
index 4c800d6455d..7c68a431a90 100644
--- a/litellm/llms/cohere/rerank_v2/transformation.py
+++ b/litellm/llms/cohere/rerank_v2/transformation.py
@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 from litellm.llms.cohere.rerank.transformation import CohereRerankConfig
 from litellm.types.rerank import OptionalRerankParams, RerankRequest
@@ -14,9 +14,9 @@ class CohereRerankV2Config(CohereRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         if api_base:
             # Remove trailing slashes and ensure clean base URL
@@ -38,17 +38,18 @@ class CohereRerankV2Config(CohereRerankConfig):
 
     def map_cohere_rerank_params(
         self,
-        non_default_params: Optional[dict],
+        non_default_params: dict | None,
         model: str,
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         """
         Map Cohere rerank params
@@ -71,7 +72,7 @@ class CohereRerankV2Config(CohereRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         if "query" not in optional_rerank_params:
             raise ValueError("query is required for Cohere rerank")
diff --git a/litellm/llms/dashscope/rerank/transformation.py b/litellm/llms/dashscope/rerank/transformation.py
index 629f3cf4af7..365e15fdd7a 100644
--- a/litellm/llms/dashscope/rerank/transformation.py
+++ b/litellm/llms/dashscope/rerank/transformation.py
@@ -22,7 +22,7 @@ as supported only for gte-rerank-v2 / qwen3-vl-rerank.
 Docs - https://help.aliyun.com/zh/model-studio/text-rerank-api
 """
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 import httpx
 
@@ -59,9 +59,9 @@ class DashScopeRerankConfig(BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         if api_base is None:
             api_base = get_secret_str("DASHSCOPE_API_BASE_RERANK") or DEFAULT_RERANK_URL
@@ -83,8 +83,8 @@ class DashScopeRerankConfig(BaseRerankConfig):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> dict:
         if api_key is None:
             api_key = get_secret_str("DASHSCOPE_API_KEY")
@@ -105,17 +105,18 @@ class DashScopeRerankConfig(BaseRerankConfig):
 
     def map_cohere_rerank_params(
         self,
-        non_default_params: Optional[dict],
+        non_default_params: dict | None,
         model: str,
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         # qwen3-rerank accepts query/documents/top_n/return_documents. The
         # rest (rank_fields, max_*_per_doc) are silently dropped.
@@ -134,7 +135,7 @@ class DashScopeRerankConfig(BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         if "query" not in optional_rerank_params:
             raise ValueError("query is required for DashScope rerank")
@@ -158,10 +159,10 @@ class DashScopeRerankConfig(BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
-        request_data: Optional[dict] = None,
-        optional_params: Optional[dict] = None,
-        litellm_params: Optional[dict] = None,
+        api_key: str | None = None,
+        request_data: dict | None = None,
+        optional_params: dict | None = None,
+        litellm_params: dict | None = None,
     ) -> RerankResponse:
         request_data = request_data or {}
         optional_params = optional_params or {}
diff --git a/litellm/llms/deepinfra/rerank/transformation.py b/litellm/llms/deepinfra/rerank/transformation.py
index e4bfbcb2513..385aa051d00 100644
--- a/litellm/llms/deepinfra/rerank/transformation.py
+++ b/litellm/llms/deepinfra/rerank/transformation.py
@@ -2,7 +2,7 @@
 Translate between Cohere's `/rerank` format and Deepinfra's `/rerank` format.
 """
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 import httpx
 
@@ -30,9 +30,9 @@ class DeepinfraRerankConfig(BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         """
         Constructs the complete DeepInfra inference endpoint URL for rerank.
@@ -67,8 +67,8 @@ class DeepinfraRerankConfig(BaseRerankConfig):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> dict:
         if api_key is None:
             api_key = get_secret_str("DEEPINFRA_API_KEY")
@@ -98,12 +98,13 @@ class DeepinfraRerankConfig(BaseRerankConfig):
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         # Start with the basic parameters
         optional_rerank_params = {}
@@ -132,7 +133,7 @@ class DeepinfraRerankConfig(BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         # Convert OptionalRerankParams to dict as expected by parent class
         if optional_rerank_params is None:
@@ -145,7 +146,7 @@ class DeepinfraRerankConfig(BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
diff --git a/litellm/llms/deepseek/chat/transformation.py b/litellm/llms/deepseek/chat/transformation.py
index 7ed3e484535..b90b1e1aa21 100644
--- a/litellm/llms/deepseek/chat/transformation.py
+++ b/litellm/llms/deepseek/chat/transformation.py
@@ -146,6 +146,86 @@ class DeepSeekChatConfig(OpenAIGPTConfig):
             and (optional_params.get("thinking") or {}).get("type") == "enabled"
         )
 
+    @staticmethod
+    def _drop_unsupported_tools(optional_params: dict) -> dict:
+        """
+        DeepSeek's /chat/completions only accepts tools of type "function".
+
+        Requests bridged from /v1/responses can carry responses-API-native tool
+        types (e.g. a Codex CLI tool typed "namespace"); DeepSeek rejects the
+        whole request with `unknown variant '<type>', expected 'function'` (issue
+        #30722). Drop the unsupported entries so the function tools still go
+        through, and drop the now-dangling tool_choice/parallel_tool_calls when
+        nothing callable survives.
+
+        When a specific `tool_choice` points at a dropped tool, clear it so the
+        sanitized request does not reference a tool DeepSeek will never receive.
+        """
+        tools = optional_params.get("tools")
+        if not isinstance(tools, list) or not tools:
+            return optional_params
+
+        def _is_function_tool(tool: object) -> bool:
+            return isinstance(tool, dict) and tool.get("type") == "function"
+
+        def _get_function_tool_name(tool: object) -> str | None:
+            if not isinstance(tool, dict):
+                return None
+            function = tool.get("function")
+            if not isinstance(function, dict):
+                return None
+            name = function.get("name")
+            return name if isinstance(name, str) else None
+
+        def _tool_choice_matches_function_tool(
+            tool_choice: object, function_tool_names: set[str]
+        ) -> bool:
+            if not isinstance(tool_choice, dict):
+                return True
+            if tool_choice.get("type") != "function":
+                return False
+            function = tool_choice.get("function")
+            if not isinstance(function, dict):
+                return False
+            name = function.get("name")
+            return isinstance(name, str) and name in function_tool_names
+
+        function_tools = [tool for tool in tools if _is_function_tool(tool)]
+        if len(function_tools) == len(tools):
+            return optional_params
+
+        dropped_types = sorted(
+            {
+                str(tool.get("type")) if isinstance(tool, dict) else type(tool).__name__
+                for tool in tools
+                if not _is_function_tool(tool)
+            }
+        )
+        litellm.verbose_logger.warning(
+            "DeepSeek chat completions only supports function tools; dropping "
+            "unsupported tool type(s) %s before sending the request",
+            dropped_types,
+        )
+
+        cleaned = {k: v for k, v in optional_params.items() if k != "tools"}
+        if function_tools:
+            function_tool_names = {
+                name
+                for tool in function_tools
+                for name in (_get_function_tool_name(tool),)
+                if name is not None
+            }
+            if not _tool_choice_matches_function_tool(
+                cleaned.get("tool_choice"), function_tool_names
+            ):
+                cleaned = {k: v for k, v in cleaned.items() if k != "tool_choice"}
+            return {**cleaned, "tools": function_tools}
+        return {
+            k: v
+            for k, v in cleaned.items()
+            if k not in ("tool_choice", "parallel_tool_calls")
+        }
+
     def transform_request(
         self,
         model: str,
@@ -163,6 +243,7 @@ class DeepSeekChatConfig(OpenAIGPTConfig):
         (user explicitly enabled it), preventing spurious injection on models
         like deepseek-v3.2 that support thinking as opt-in but not always-on.
         """
+        optional_params = self._drop_unsupported_tools(optional_params)
         if self._thinking_mode_active(model=model, optional_params=optional_params):
             messages = self._fill_reasoning_content(messages)
         return super().transform_request(
@@ -185,6 +266,7 @@ class DeepSeekChatConfig(OpenAIGPTConfig):
         Async equivalent of transform_request — applies the same reasoning_content
         fix for multi-turn thinking-mode conversations.
         """
+        optional_params = self._drop_unsupported_tools(optional_params)
         if self._thinking_mode_active(model=model, optional_params=optional_params):
             messages = self._fill_reasoning_content(messages)
         return await super().async_transform_request(
diff --git a/litellm/llms/fireworks_ai/rerank/transformation.py b/litellm/llms/fireworks_ai/rerank/transformation.py
index 4a7b64b9b77..400d511a02f 100644
--- a/litellm/llms/fireworks_ai/rerank/transformation.py
+++ b/litellm/llms/fireworks_ai/rerank/transformation.py
@@ -4,7 +4,7 @@ Fireworks AI Rerank API transformation
 Reference: https://docs.fireworks.ai/inference-api-reference/rerank
 """
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 import httpx
 
@@ -29,9 +29,9 @@ class FireworksAIRerankConfig(FireworksAIMixin, BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         if api_base:
             # Remove trailing slashes and ensure clean base URL
@@ -56,17 +56,18 @@ class FireworksAIRerankConfig(FireworksAIMixin, BaseRerankConfig):
 
     def map_cohere_rerank_params(
         self,
-        non_default_params: Optional[dict],
+        non_default_params: dict | None,
         model: str,
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict[str, Any]:
         """
         Map Cohere rerank params to Fireworks AI rerank params
@@ -101,8 +102,8 @@ class FireworksAIRerankConfig(FireworksAIMixin, BaseRerankConfig):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> dict:
         api_key = self._get_api_key(api_key)
         if api_key is None:
@@ -127,7 +128,7 @@ class FireworksAIRerankConfig(FireworksAIMixin, BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         """
         Transform request to Fireworks AI rerank format
@@ -175,7 +176,7 @@ class FireworksAIRerankConfig(FireworksAIMixin, BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
@@ -220,7 +221,7 @@ class FireworksAIRerankConfig(FireworksAIMixin, BaseRerankConfig):
         rerank_meta = RerankResponseMeta(billed_units=_billed_units, tokens=_tokens)
 
         # Extract results - Fireworks AI uses "data" instead of "results"
-        _results: Optional[List[dict]] = raw_response_json.get(
+        _results: List[dict] | None = raw_response_json.get(
             "data"
         ) or raw_response_json.get("results")
 
diff --git a/litellm/llms/github_copilot/chat/transformation.py b/litellm/llms/github_copilot/chat/transformation.py
index 72dacb59f8a..54cbf69a4ac 100644
--- a/litellm/llms/github_copilot/chat/transformation.py
+++ b/litellm/llms/github_copilot/chat/transformation.py
@@ -1,5 +1,5 @@
 import json
-from typing import Any, List, Optional, Tuple
+from typing import Any, List, Tuple
 
 import os
 
@@ -22,8 +22,8 @@ from ..common_utils import (
 class GithubCopilotConfig(OpenAIConfig):
     def __init__(
         self,
-        api_key: Optional[str] = None,
-        api_base: Optional[str] = None,
+        api_key: str | None = None,
+        api_base: str | None = None,
         custom_llm_provider: str = "openai",
     ) -> None:
         super().__init__()
@@ -32,10 +32,10 @@ class GithubCopilotConfig(OpenAIConfig):
     def _get_openai_compatible_provider_info(
         self,
         model: str,
-        api_base: Optional[str],
-        api_key: Optional[str],
+        api_base: str | None,
+        api_key: str | None,
         custom_llm_provider: str,
-    ) -> Tuple[Optional[str], Optional[str], str]:
+    ) -> Tuple[str | None, str | None, str]:
         dynamic_api_base = (
             api_base
             or self.authenticator.get_api_base()
@@ -85,8 +85,8 @@ class GithubCopilotConfig(OpenAIConfig):
         messages: List[AllMessageValues],
         optional_params: dict,
         litellm_params: dict,
-        api_key: Optional[str] = None,
-        api_base: Optional[str] = None,
+        api_key: str | None = None,
+        api_base: str | None = None,
     ) -> dict:
         # Get base headers from parent
         validated_headers = super().validate_environment(
@@ -173,7 +173,7 @@ class GithubCopilotConfig(OpenAIConfig):
     @staticmethod
     def _parse_anthropic_native_content(
         content_blocks: List[Any],
-    ) -> Tuple[str, List[ChatCompletionToolCallChunk], Optional[List[Any]]]:
+    ) -> Tuple[str, List[ChatCompletionToolCallChunk], List[Any] | None]:
         """
         Parse Anthropic-native content blocks into OpenAI-compatible fields.
 
@@ -194,6 +194,88 @@ class GithubCopilotConfig(OpenAIConfig):
         )
         return text_content, tool_calls, thinking_blocks
 
+    @staticmethod
+    def _normalize_anthropic_usage(usage: dict) -> dict:
+        normalized = dict(usage)
+        if "input_tokens" in usage and "prompt_tokens" not in usage:
+            normalized["prompt_tokens"] = usage["input_tokens"]
+        if "output_tokens" in usage and "completion_tokens" not in usage:
+            normalized["completion_tokens"] = usage["output_tokens"]
+        if "total_tokens" not in normalized:
+            normalized["total_tokens"] = normalized.get(
+                "prompt_tokens", 0
+            ) + normalized.get("completion_tokens", 0)
+        return normalized
+
+    @classmethod
+    def _synthesize_choices_for_anthropic_native(cls, response_json: dict) -> dict:
+        """
+        Synthesize a `choices` array from an Anthropic-native Copilot response.
+
+        Newer Copilot Claude models (e.g. opus-4.7, opus-4.8) return content
+        blocks and `stop_reason` without an OpenAI-style `choices` array, and the
+        max_tokens=1 probe returns no content at all. Returns the response
+        unchanged when it already carries choices.
+
+        See: https://github.com/BerriAI/litellm/issues/29391
+        """
+        if response_json.get("choices"):
+            return response_json
+
+        content = ""
+        tool_calls: List[ChatCompletionToolCallChunk] = []
+        thinking_blocks: List[Any] | None = None
+        raw_content = response_json.get("content")
+        if isinstance(raw_content, list):
+            content, tool_calls, thinking_blocks = cls._parse_anthropic_native_content(
+                raw_content
+            )
+        elif isinstance(raw_content, str):
+            content = raw_content
+
+        stop_reason = response_json.get("stop_reason")
+        finish_reason_map = {
+            "end_turn": "stop",
+            "max_tokens": "length",
+            "stop_sequence": "stop",
+            "tool_use": "tool_calls",
+        }
+        if tool_calls:
+            finish_reason = "tool_calls"
+        elif stop_reason in finish_reason_map:
+            finish_reason = finish_reason_map[stop_reason]
+        elif content:
+            finish_reason = "stop"
+        else:
+            finish_reason = "length"
+
+        message: dict = {
+            "role": "assistant",
+            "content": content if content or not tool_calls else None,
+        }
+        if tool_calls:
+            message["tool_calls"] = tool_calls
+        if thinking_blocks:
+            message["thinking_blocks"] = thinking_blocks
+
+        synthesized = {
+            **response_json,
+            "choices": [
+                {"index": 0, "message": message, "finish_reason": finish_reason}
+            ],
+        }
+        usage = response_json.get("usage")
+        if isinstance(usage, dict):
+            synthesized["usage"] = cls._normalize_anthropic_usage(usage)
+        return synthesized
+
+    def transform_parsed_response_dict(self, parsed_response: dict) -> dict:
+        """
+        Repair the OpenAI-SDK-parsed response on the handler path that bypasses
+        transform_response. See: https://github.com/BerriAI/litellm/issues/30927
+        """
+        return self._synthesize_choices_for_anthropic_native(parsed_response)
+
     def transform_response(
         self,
         model: str,
@@ -205,18 +287,9 @@ class GithubCopilotConfig(OpenAIConfig):
         optional_params: dict,
         litellm_params: dict,
         encoding: Any,
-        api_key: Optional[str] = None,
-        json_mode: Optional[bool] = None,
+        api_key: str | None = None,
+        json_mode: bool | None = None,
     ) -> "ModelResponse":
-        """
-        Handle newer Copilot models (e.g. claude-opus-4.7, claude-opus-4.8) that
-        return Anthropic-native format responses without a `choices` array.
-
-        Synthesizes the missing `choices` from Anthropic-native fields, then
-        delegates to the parent so all standard post-processing applies.
-
-        See: https://github.com/BerriAI/litellm/issues/29391
-        """
         try:
             response_json = raw_response.json()
         except Exception:
@@ -235,70 +308,12 @@ class GithubCopilotConfig(OpenAIConfig):
             )
 
         if not response_json.get("choices"):
-            content = ""
-            tool_calls: List[ChatCompletionToolCallChunk] = []
-            thinking_blocks: Optional[List[Any]] = None
-            if "content" in response_json and isinstance(
-                response_json["content"], list
-            ):
-                content, tool_calls, thinking_blocks = (
-                    self._parse_anthropic_native_content(response_json["content"])
-                )
-            elif isinstance(response_json.get("content"), str):
-                content = response_json["content"]
-
-            stop_reason = response_json.get("stop_reason")
-            finish_reason_map = {
-                "end_turn": "stop",
-                "max_tokens": "length",
-                "stop_sequence": "stop",
-                "tool_use": "tool_calls",
-            }
-            # Prefer tool_calls when blocks were extracted; otherwise map stop_reason.
-            if tool_calls:
-                finish_reason = "tool_calls"
-            elif stop_reason in finish_reason_map:
-                finish_reason = finish_reason_map[stop_reason]
-            elif content:
-                finish_reason = "stop"
-            else:
-                finish_reason = "length"
-
-            message: dict = {
-                "role": "assistant",
-                "content": content if content or not tool_calls else None,
-            }
-            if tool_calls:
-                message["tool_calls"] = tool_calls
-            if thinking_blocks:
-                message["thinking_blocks"] = thinking_blocks
-
-            response_json["choices"] = [
-                {
-                    "index": 0,
-                    "message": message,
-                    "finish_reason": finish_reason,
-                }
-            ]
-
-            if "usage" in response_json:
-                usage = response_json["usage"]
-                if "input_tokens" in usage and "prompt_tokens" not in usage:
-                    usage["prompt_tokens"] = usage["input_tokens"]
-                if "output_tokens" in usage and "completion_tokens" not in usage:
-                    usage["completion_tokens"] = usage["output_tokens"]
-                if "total_tokens" not in usage:
-                    usage["total_tokens"] = usage.get("prompt_tokens", 0) + usage.get(
-                        "completion_tokens", 0
-                    )
-
-            # Build a patched response so super() sees valid JSON with choices
-            patched = httpx.Response(
+            response_json = self._synthesize_choices_for_anthropic_native(response_json)
+            raw_response = httpx.Response(
                 status_code=raw_response.status_code,
                 headers=raw_response.headers,
                 content=json.dumps(response_json).encode(),
             )
-            raw_response = patched
 
         return super().transform_response(
             model=model,
diff --git a/litellm/llms/hosted_vllm/rerank/transformation.py b/litellm/llms/hosted_vllm/rerank/transformation.py
index 60b6dc7d23d..47495350460 100644
--- a/litellm/llms/hosted_vllm/rerank/transformation.py
+++ b/litellm/llms/hosted_vllm/rerank/transformation.py
@@ -2,7 +2,7 @@
 Transformation logic for Hosted VLLM rerank
 """
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 import httpx
 
@@ -28,7 +28,7 @@ class HostedVLLMRerankError(BaseLLMException):
         self,
         status_code: int,
         message: str,
-        headers: Optional[Union[dict, httpx.Headers]] = None,
+        headers: Union[dict, httpx.Headers] | None = None,
     ):
         super().__init__(status_code=status_code, message=message, headers=headers)
 
@@ -39,9 +39,9 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         if api_base:
             # Remove trailing slashes and ensure clean base URL
@@ -61,21 +61,23 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
             "top_n",
             "rank_fields",
             "return_documents",
+            "instruction",
         ]
 
     def map_cohere_rerank_params(
         self,
-        non_default_params: Optional[dict],
+        non_default_params: dict | None,
         model: str,
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         """
         Map parameters for Hosted VLLM rerank
@@ -83,22 +85,28 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
         if max_chunks_per_doc is not None:
             raise ValueError("Hosted VLLM does not support max_chunks_per_doc")
 
-        return dict(
-            OptionalRerankParams(
-                query=query,
-                documents=documents,
-                top_n=top_n,
-                rank_fields=rank_fields,
-                return_documents=return_documents,
-            )
+        mapped_params = OptionalRerankParams(
+            query=query,
+            documents=documents,
+            top_n=top_n,
+            rank_fields=rank_fields,
+            return_documents=return_documents,
         )
 
+        # `instruction` is a vLLM-supported passthrough (folded into the model's
+        # chat_template_kwargs). Only forward it when explicitly set so omitting
+        # it leaves the request unchanged.
+        if instruction is not None:
+            mapped_params["instruction"] = instruction
+
+        return dict(mapped_params)
+
     def validate_environment(
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> dict:
         if api_key is None:
             api_key = get_secret_str("HOSTED_VLLM_API_KEY") or "fake-api-key"
@@ -121,7 +129,7 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         if "query" not in optional_rerank_params:
             raise ValueError("query is required for Hosted VLLM rerank")
@@ -135,6 +143,7 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
             top_n=optional_rerank_params.get("top_n", None),
             rank_fields=optional_rerank_params.get("rank_fields", None),
             return_documents=optional_rerank_params.get("return_documents", None),
+            instruction=optional_rerank_params.get("instruction", None),
         )
         return rerank_request.model_dump(exclude_none=True)
 
@@ -144,7 +153,7 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
@@ -178,7 +187,7 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
         rerank_meta = RerankResponseMeta(billed_units=_billed_units, tokens=_tokens)
 
         # Extract results
-        _results: Optional[List[dict]] = response.get("results")
+        _results: List[dict] | None = response.get("results")
 
         if _results is None:
             raise ValueError(f"No results found in the response={response}")
diff --git a/litellm/llms/huggingface/rerank/transformation.py b/litellm/llms/huggingface/rerank/transformation.py
index 2c847b617ef..c94fc65acbd 100644
--- a/litellm/llms/huggingface/rerank/transformation.py
+++ b/litellm/llms/huggingface/rerank/transformation.py
@@ -1,5 +1,5 @@
 import os
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any, Dict, List, Tuple, Union
 
 import httpx
 from typing_extensions import TypedDict
@@ -35,7 +35,7 @@ class HuggingFaceRerankResponseItem(TypedDict):
 
     index: int
     score: float
-    text: Optional[str]  # Optional, included when return_text=True
+    text: str | None  # Optional, included when return_text=True
 
 
 class HuggingFaceRerankResponse(TypedDict):
@@ -50,7 +50,7 @@ HuggingFaceRerankResponseList = List[HuggingFaceRerankResponseItem]
 
 
 class HuggingFaceRerankConfig(BaseRerankConfig):
-    def get_api_base(self, model: str, api_base: Optional[str]) -> str:
+    def get_api_base(self, model: str, api_base: str | None) -> str:
         if api_base is not None:
             return api_base
         elif os.getenv("HF_API_BASE") is not None:
@@ -62,9 +62,9 @@ class HuggingFaceRerankConfig(BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         """
         Get the complete URL for the API call, including the /rerank suffix if necessary.
@@ -89,17 +89,18 @@ class HuggingFaceRerankConfig(BaseRerankConfig):
 
     def map_cohere_rerank_params(
         self,
-        non_default_params: Optional[dict],
+        non_default_params: dict | None,
         model: str,
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         optional_rerank_params = {}
         if non_default_params is not None:
@@ -121,9 +122,9 @@ class HuggingFaceRerankConfig(BaseRerankConfig):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
-        api_base: Optional[str] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
+        api_base: str | None = None,
     ) -> dict:
         # Get API credentials
         api_key, api_base = self.get_api_credentials(api_key=api_key, api_base=api_base)
@@ -146,7 +147,7 @@ class HuggingFaceRerankConfig(BaseRerankConfig):
         model: str,
         optional_rerank_params: Union[OptionalRerankParams, dict],
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         if "query" not in optional_rerank_params:
             raise ValueError("query is required for HuggingFace rerank")
@@ -172,7 +173,7 @@ class HuggingFaceRerankConfig(BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LoggingClass,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
@@ -275,9 +276,9 @@ class HuggingFaceRerankConfig(BaseRerankConfig):
 
     def get_api_credentials(
         self,
-        api_key: Optional[str] = None,
-        api_base: Optional[str] = None,
-    ) -> Tuple[Optional[str], Optional[str]]:
+        api_key: str | None = None,
+        api_base: str | None = None,
+    ) -> Tuple[str | None, str | None]:
         """
         Get API key and base URL from multiple sources.
         Returns tuple of (api_key, api_base).
diff --git a/litellm/llms/jina_ai/rerank/transformation.py b/litellm/llms/jina_ai/rerank/transformation.py
index 56be754fc34..cabaf079edc 100644
--- a/litellm/llms/jina_ai/rerank/transformation.py
+++ b/litellm/llms/jina_ai/rerank/transformation.py
@@ -6,7 +6,7 @@ Why separate file? Make it easy to see how transformation works
 Docs - https://jina.ai/reranker
 """
 
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, List, Tuple, Union
 
 from httpx import URL, Response
 
@@ -39,12 +39,13 @@ class JinaAIRerankConfig(BaseRerankConfig):
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         optional_params = {}
         supported_params = self.get_supported_cohere_rerank_params(model)
@@ -59,9 +60,9 @@ class JinaAIRerankConfig(BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         base_path = "/v1/rerank"
 
@@ -78,7 +79,7 @@ class JinaAIRerankConfig(BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: Dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> Dict:
         return {"model": model, **optional_rerank_params}
 
@@ -88,7 +89,7 @@ class JinaAIRerankConfig(BaseRerankConfig):
         raw_response: Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: Dict = {},
         optional_params: Dict = {},
         litellm_params: Dict = {},
@@ -104,7 +105,7 @@ class JinaAIRerankConfig(BaseRerankConfig):
         _tokens = RerankTokens(**_json_response.get("usage", {}))
         rerank_meta = RerankResponseMeta(billed_units=_billed_units, tokens=_tokens)
 
-        _results: Optional[List[dict]] = _json_response.get("results")
+        _results: List[dict] | None = _json_response.get("results")
 
         if _results is None:
             raise ValueError(f"No results found in the response={_json_response}")
@@ -136,8 +137,8 @@ class JinaAIRerankConfig(BaseRerankConfig):
         self,
         headers: Dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> Dict:
         if api_key is None:
             raise ValueError(
@@ -152,9 +153,9 @@ class JinaAIRerankConfig(BaseRerankConfig):
     def calculate_rerank_cost(
         self,
         model: str,
-        custom_llm_provider: Optional[str] = None,
-        billed_units: Optional[RerankBilledUnits] = None,
-        model_info: Optional[ModelInfo] = None,
+        custom_llm_provider: str | None = None,
+        billed_units: RerankBilledUnits | None = None,
+        model_info: ModelInfo | None = None,
     ) -> Tuple[float, float]:
         """
         Jina AI reranker is priced at $0.000000018 per token.
diff --git a/litellm/llms/moonshot/chat/transformation.py b/litellm/llms/moonshot/chat/transformation.py
index 587fa0ed8d6..a5ac696aae2 100644
--- a/litellm/llms/moonshot/chat/transformation.py
+++ b/litellm/llms/moonshot/chat/transformation.py
@@ -242,11 +242,11 @@ class MoonshotChatConfig(OpenAIGPTConfig):
 
         https://platform.moonshot.ai/docs/guide/migrating-from-openai-to-kimi#about-tool_choice
         """
-        messages.append(
+        optional_params.pop("tool_choice")
+        return [
+            *messages,
             {
                 "role": "user",
                 "content": "Please select a tool to handle the current issue.",  # Usually, the Kimi large language model understands the intention to invoke a tool and selects one for invocation
-            }
-        )
-        optional_params.pop("tool_choice")
-        return messages
+            },
+        ]
diff --git a/litellm/llms/nvidia_nim/rerank/transformation.py b/litellm/llms/nvidia_nim/rerank/transformation.py
index 05f545c2944..7ae3f913297 100644
--- a/litellm/llms/nvidia_nim/rerank/transformation.py
+++ b/litellm/llms/nvidia_nim/rerank/transformation.py
@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Literal, Optional, Union
+from typing import Any, Dict, List, Literal, Union
 
 import httpx
 from typing_extensions import Required, TypedDict
@@ -64,9 +64,9 @@ class NvidiaNimRerankConfig(BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         """
         Construct the Nvidia NIM rerank URL.
@@ -106,17 +106,18 @@ class NvidiaNimRerankConfig(BaseRerankConfig):
 
     def map_cohere_rerank_params(
         self,
-        non_default_params: Optional[dict],
+        non_default_params: dict | None,
         model: str,
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         """
         Map Cohere/OpenAI rerank params to Nvidia NIM format.
@@ -145,8 +146,8 @@ class NvidiaNimRerankConfig(BaseRerankConfig):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> dict:
         """
         Validate that the Nvidia NIM API key is present.
@@ -177,7 +178,7 @@ class NvidiaNimRerankConfig(BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         """
         Transform request to Nvidia NIM format.
@@ -258,7 +259,7 @@ class NvidiaNimRerankConfig(BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
diff --git a/litellm/llms/openai/image_generation/cost_calculator.py b/litellm/llms/openai/image_generation/cost_calculator.py
index d009a085fab..dab277a7ba8 100644
--- a/litellm/llms/openai/image_generation/cost_calculator.py
+++ b/litellm/llms/openai/image_generation/cost_calculator.py
@@ -7,7 +7,10 @@ These models use token-based pricing instead of pixel-based pricing like DALL-E.
 from typing import Optional
 
 from litellm import verbose_logger
-from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token
+from litellm.litellm_core_utils.llm_cost_calc.utils import (
+    calculate_image_response_cost_from_usage,
+    generic_cost_per_token,
+)
 from litellm.types.utils import ImageResponse, Usage
 
 
@@ -16,54 +19,40 @@ def cost_calculator(
     image_response: ImageResponse,
     custom_llm_provider: Optional[str] = None,
 ) -> float:
-    """
-    Calculate cost for OpenAI gpt-image models.
-
-    Uses the same usage format as Responses API, so we reuse the helper
-    to transform to chat completion format and use generic_cost_per_token.
-
-    Args:
-        model: The model name (e.g., "gpt-image-1", "gpt-image-2")
-        image_response: The ImageResponse containing usage data
-        custom_llm_provider: Optional provider name
-
-    Returns:
-        float: Total cost in USD
-    """
+    """Calculate cost for OpenAI gpt-image models (token-based pricing)."""
     usage = getattr(image_response, "usage", None)
-
     if usage is None:
         verbose_logger.debug(
             f"No usage data available for {model}, cannot calculate token-based cost"
         )
         return 0.0
 
-    # If usage is already a Usage object with completion_tokens_details set,
-    # use it directly (it was already transformed in convert_to_image_response)
+    provider = custom_llm_provider or "openai"
+
+    # A chat Usage with an explicit output breakdown: cost via generic_cost_per_token.
     if isinstance(usage, Usage) and usage.completion_tokens_details is not None:
-        chat_usage = usage
-    else:
-        # Transform ImageUsage to Usage using the existing helper
-        # ImageUsage has the same format as ResponseAPIUsage
-        from litellm.responses.utils import ResponseAPILoggingUtils
-
-        chat_usage = (
-            ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage(usage)
+        prompt_cost, completion_cost = generic_cost_per_token(
+            model=model, usage=usage, custom_llm_provider=provider
         )
+        return prompt_cost + completion_cost
 
-    # Use generic_cost_per_token for cost calculation
-    prompt_cost, completion_cost = generic_cost_per_token(
-        model=model,
-        usage=chat_usage,
-        custom_llm_provider=custom_llm_provider or "openai",
-    )
+    # ImageUsage / ResponseAPIUsage: reuse the shared helper (same path as
+    # azure_ai/gemini/vertex_ai). It prices generated output tokens at
+    # output_cost_per_image_token, classifying them as image tokens when the provider
+    # does not itemize output and splitting text/image when it does.
+    if getattr(usage, "input_tokens", None) is not None:
+        token_based_cost = calculate_image_response_cost_from_usage(
+            model=model, image_response=image_response, custom_llm_provider=provider
+        )
+        if token_based_cost is not None:
+            return token_based_cost
 
-    total_cost = prompt_cost + completion_cost
+    # Fallback: a Usage with no output breakdown that the image helper can't read —
+    # cost via generic_cost_per_token (text rate) instead of returning 0.0.
+    if isinstance(usage, Usage):
+        prompt_cost, completion_cost = generic_cost_per_token(
+            model=model, usage=usage, custom_llm_provider=provider
+        )
+        return prompt_cost + completion_cost
 
-    verbose_logger.debug(
-        f"OpenAI gpt-image cost calculation for {model}: "
-        f"prompt_cost=${prompt_cost:.6f}, completion_cost=${completion_cost:.6f}, "
-        f"total=${total_cost:.6f}"
-    )
-
-    return total_cost
+    return 0.0
diff --git a/litellm/llms/openai/openai.py b/litellm/llms/openai/openai.py
index 59acbac6e15..0b90381ba59 100644
--- a/litellm/llms/openai/openai.py
+++ b/litellm/llms/openai/openai.py
@@ -785,7 +785,11 @@ class OpenAIChatCompletion(BaseLLM, BaseOpenAILLM):
                         )
 
                         logging_obj.model_call_details["response_headers"] = headers
-                        stringified_response = response.model_dump()
+                        stringified_response = (
+                            provider_config.transform_parsed_response_dict(
+                                response.model_dump()
+                            )
+                        )
                         logging_obj.post_call(
                             input=messages,
                             api_key=api_key,
@@ -933,7 +937,9 @@ class OpenAIChatCompletion(BaseLLM, BaseOpenAILLM):
                     timeout=timeout,
                     logging_obj=logging_obj,
                 )
-                stringified_response = response.model_dump()
+                stringified_response = provider_config.transform_parsed_response_dict(
+                    response.model_dump()
+                )
                 logging_obj.post_call(
                     input=data["messages"],
                     api_key=api_key,
diff --git a/litellm/llms/vertex_ai/rerank/transformation.py b/litellm/llms/vertex_ai/rerank/transformation.py
index 3b84972e946..382a8498d40 100644
--- a/litellm/llms/vertex_ai/rerank/transformation.py
+++ b/litellm/llms/vertex_ai/rerank/transformation.py
@@ -4,7 +4,7 @@ Translates from Cohere's `/v1/rerank` input format to Vertex AI Discovery Engine
 Why separate file? Make it easy to see how transformation works
 """
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 import httpx
 
@@ -36,9 +36,9 @@ class VertexAIRerankConfig(BaseRerankConfig, VertexBase):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[Dict] = None,
+        optional_params: Dict | None = None,
     ) -> str:
         """
         Get the complete URL for the Vertex AI Discovery Engine ranking API
@@ -76,8 +76,8 @@ class VertexAIRerankConfig(BaseRerankConfig, VertexBase):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[Dict] = None,
+        api_key: str | None = None,
+        optional_params: Dict | None = None,
     ) -> dict:
         """
         Validate and set up authentication for Vertex AI Discovery Engine API
@@ -112,7 +112,7 @@ class VertexAIRerankConfig(BaseRerankConfig, VertexBase):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         """
         Transform the request from Cohere format to Vertex AI Discovery Engine format
@@ -161,7 +161,7 @@ class VertexAIRerankConfig(BaseRerankConfig, VertexBase):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
@@ -236,12 +236,13 @@ class VertexAIRerankConfig(BaseRerankConfig, VertexBase):
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         """
         Map Cohere rerank params to Vertex AI format
diff --git a/litellm/llms/voyage/rerank/transformation.py b/litellm/llms/voyage/rerank/transformation.py
index d64450a1211..05991d4cc8c 100644
--- a/litellm/llms/voyage/rerank/transformation.py
+++ b/litellm/llms/voyage/rerank/transformation.py
@@ -4,7 +4,7 @@ Transformation logic for Voyage AI's /v1/rerank endpoint.
 Docs - https://docs.voyageai.com/docs/reranker
 """
 
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, List, Tuple, Union
 
 import httpx
 
@@ -33,12 +33,13 @@ class VoyageRerankConfig(BaseRerankConfig):
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         # Voyage AI uses 'top_k' instead of 'top_n'
         optional_params: Dict[str, Any] = {"query": query, "documents": documents}
@@ -52,9 +53,9 @@ class VoyageRerankConfig(BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         if api_base is None:
             return "https://api.voyageai.com/v1/rerank"
@@ -71,7 +72,7 @@ class VoyageRerankConfig(BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: Dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> Dict:
         return {"model": model, **optional_rerank_params}
 
@@ -81,7 +82,7 @@ class VoyageRerankConfig(BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: Dict = {},
         optional_params: Dict = {},
         litellm_params: Dict = {},
@@ -102,7 +103,7 @@ class VoyageRerankConfig(BaseRerankConfig):
             )
 
         # Voyage AI returns results in "data" key, not "results"
-        _results: Optional[List[dict]] = _json_response.get("data")
+        _results: List[dict] | None = _json_response.get("data")
         if _results is None:
             raise ValueError(f"No results found in the response={_json_response}")
 
@@ -136,8 +137,8 @@ class VoyageRerankConfig(BaseRerankConfig):
         self,
         headers: Dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> Dict:
         if api_key is None:
             api_key = get_secret_str("VOYAGE_API_KEY") or get_secret_str(
@@ -155,9 +156,9 @@ class VoyageRerankConfig(BaseRerankConfig):
     def calculate_rerank_cost(
         self,
         model: str,
-        custom_llm_provider: Optional[str] = None,
-        billed_units: Optional[RerankBilledUnits] = None,
-        model_info: Optional[ModelInfo] = None,
+        custom_llm_provider: str | None = None,
+        billed_units: RerankBilledUnits | None = None,
+        model_info: ModelInfo | None = None,
     ) -> Tuple[float, float]:
         if (
             model_info is None
diff --git a/litellm/llms/watsonx/rerank/transformation.py b/litellm/llms/watsonx/rerank/transformation.py
index 202760f68a6..790606c7e6d 100644
--- a/litellm/llms/watsonx/rerank/transformation.py
+++ b/litellm/llms/watsonx/rerank/transformation.py
@@ -5,7 +5,7 @@ Docs - https://cloud.ibm.com/apidocs/watsonx-ai#text-rerank
 """
 
 import uuid
-from typing import Any, Dict, List, Optional, Union, cast
+from typing import Any, Dict, List, Union, cast
 
 import httpx
 
@@ -31,9 +31,9 @@ class IBMWatsonXRerankConfig(IBMWatsonXMixin, BaseRerankConfig):
 
     def get_complete_url(
         self,
-        api_base: Optional[str],
+        api_base: str | None,
         model: str,
-        optional_params: Optional[dict] = None,
+        optional_params: dict | None = None,
     ) -> str:
         base_url = self._get_base_url(api_base=api_base)
         endpoint = WatsonXAIEndpoint.RERANK.value
@@ -60,8 +60,8 @@ class IBMWatsonXRerankConfig(IBMWatsonXMixin, BaseRerankConfig):
         self,
         headers: dict,
         model: str,
-        api_key: Optional[str] = None,
-        optional_params: Optional[dict] = None,
+        api_key: str | None = None,
+        optional_params: dict | None = None,
     ) -> Dict:
         optional_params = optional_params or {}
 
@@ -73,11 +73,11 @@ class IBMWatsonXRerankConfig(IBMWatsonXMixin, BaseRerankConfig):
         if "Authorization" in headers:
             return {**default_headers, **headers}
         token = cast(
-            Optional[str],
+            str | None,
             optional_params.pop("token", None) or get_secret_str("WATSONX_TOKEN"),
         )
         zen_api_key = cast(
-            Optional[str],
+            str | None,
             optional_params.pop("zen_api_key", None)
             or get_secret_str("WATSONX_ZENAPIKEY"),
         )
@@ -93,17 +93,18 @@ class IBMWatsonXRerankConfig(IBMWatsonXMixin, BaseRerankConfig):
 
     def map_cohere_rerank_params(
         self,
-        non_default_params: Optional[dict],
+        non_default_params: dict | None,
         model: str,
         drop_params: bool,
         query: str,
         documents: List[Union[str, Dict[str, Any]]],
-        custom_llm_provider: Optional[str] = None,
-        top_n: Optional[int] = None,
-        rank_fields: Optional[List[str]] = None,
-        return_documents: Optional[bool] = True,
-        max_chunks_per_doc: Optional[int] = None,
-        max_tokens_per_doc: Optional[int] = None,
+        custom_llm_provider: str | None = None,
+        top_n: int | None = None,
+        rank_fields: List[str] | None = None,
+        return_documents: bool | None = True,
+        max_chunks_per_doc: int | None = None,
+        max_tokens_per_doc: int | None = None,
+        instruction: str | None = None,
     ) -> Dict:
         """
         Map Cohere rerank params to IBM watsonx.ai rerank params
@@ -143,7 +144,7 @@ class IBMWatsonXRerankConfig(IBMWatsonXMixin, BaseRerankConfig):
         model: str,
         optional_rerank_params: Dict,
         headers: dict,
-        litellm_params: Optional[dict] = None,
+        litellm_params: dict | None = None,
     ) -> dict:
         """
         Transform request to IBM watsonx.ai rerank format
@@ -162,7 +163,7 @@ class IBMWatsonXRerankConfig(IBMWatsonXMixin, BaseRerankConfig):
         raw_response: httpx.Response,
         model_response: RerankResponse,
         logging_obj: LiteLLMLoggingObj,
-        api_key: Optional[str] = None,
+        api_key: str | None = None,
         request_data: dict = {},
         optional_params: dict = {},
         litellm_params: dict = {},
@@ -179,7 +180,7 @@ class IBMWatsonXRerankConfig(IBMWatsonXMixin, BaseRerankConfig):
                 headers=raw_response.headers,
             )
 
-        _results: Optional[List[dict]] = raw_response_json.get("results")
+        _results: List[dict] | None = raw_response_json.get("results")
         if _results is None:
             raise ValueError(f"No results found in the response={raw_response_json}")
 
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index d44fc654a56..1fa6cb1ec71 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -583,6 +583,15 @@
         "output_cost_per_token": 0.0,
         "output_vector_size": 1536
     },
+    "amazon.titan-embed-g1-text-02": {
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1536
+    },
     "amazon.titan-embed-text-v2:0": {
         "input_cost_per_token": 2e-08,
         "litellm_provider": "bedrock",
@@ -14156,6 +14165,14 @@
             "notes": "APISerpent deep search (/api/search), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches."
         }
     },
+    "tinyfish/search": {
+        "input_cost_per_query": 0.0,
+        "litellm_provider": "tinyfish",
+        "mode": "search",
+        "metadata": {
+            "notes": "TinyFish Search API"
+        }
+    },
     "elevenlabs/scribe_v1": {
         "input_cost_per_second": 6.11e-05,
         "litellm_provider": "elevenlabs",
@@ -31414,13 +31431,13 @@
         "output_cost_per_token": 0.0
     },
     "sambanova/MiniMax-M2.7": {
-        "input_cost_per_token": 3e-07,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "sambanova",
-        "max_input_tokens": 204800,
+        "max_input_tokens": 196608,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token": 2.4e-06,
         "source": "https://cloud.sambanova.ai/plans/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -31437,6 +31454,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/DeepSeek-R1-Distill-Llama-70B": {
+        "deprecation_date": "2026-03-20",
         "input_cost_per_token": 7e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 131072,
@@ -31447,6 +31465,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/DeepSeek-V3-0324": {
+        "deprecation_date": "2026-04-14",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "sambanova",
         "max_input_tokens": 32768,
@@ -31477,6 +31496,7 @@
         "supports_vision": true
     },
     "sambanova/Llama-4-Scout-17B-16E-Instruct": {
+        "deprecation_date": "2025-06-19",
         "input_cost_per_token": 4e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 8192,
@@ -31493,6 +31513,7 @@
         "supports_tool_choice": true
     },
     "sambanova/Meta-Llama-3.1-405B-Instruct": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31506,6 +31527,7 @@
         "supports_tool_choice": true
     },
     "sambanova/Meta-Llama-3.1-8B-Instruct": {
+        "deprecation_date": "2026-04-14",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31519,6 +31541,7 @@
         "supports_tool_choice": true
     },
     "sambanova/Meta-Llama-3.2-1B-Instruct": {
+         "deprecation_date": "2025-06-25",
         "input_cost_per_token": 4e-08,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31529,6 +31552,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/Meta-Llama-3.2-3B-Instruct": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 8e-08,
         "litellm_provider": "sambanova",
         "max_input_tokens": 4096,
@@ -31552,6 +31576,7 @@
         "supports_tool_choice": true
     },
     "sambanova/Meta-Llama-Guard-3-8B": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31562,6 +31587,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/QwQ-32B": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31572,6 +31598,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/Qwen2-Audio-7B-Instruct": {
+        "deprecation_date": "2025-06-19",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 4096,
@@ -31583,6 +31610,7 @@
         "supports_audio_input": true
     },
     "sambanova/Qwen3-32B": {
+        "deprecation_date": "2026-04-06",
         "input_cost_per_token": 4e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 8192,
@@ -31596,9 +31624,9 @@
         "supports_tool_choice": true
     },
     "sambanova/DeepSeek-V3.1": {
-        "max_tokens": 32768,
-        "max_input_tokens": 32768,
-        "max_output_tokens": 32768,
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
         "input_cost_per_token": 3e-06,
         "output_cost_per_token": 4.5e-06,
         "litellm_provider": "sambanova",
@@ -31612,8 +31640,8 @@
         "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 3e-06,
-        "output_cost_per_token": 4.5e-06,
+        "input_cost_per_token": 2.2e-07,
+        "output_cost_per_token": 5.9e-07,
         "litellm_provider": "sambanova",
         "mode": "chat",
         "supports_function_calling": true,
@@ -31621,21 +31649,55 @@
         "supports_reasoning": true,
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
-    "snowflake/claude-3-5-sonnet": {
-        "litellm_provider": "snowflake",
-        "max_input_tokens": 18000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "supports_computer_use": true
-    },
-    "snowflake/deepseek-r1": {
-        "litellm_provider": "snowflake",
+    "sambanova/DeepSeek-V3.2": {
+        "max_tokens": 32768,
         "max_input_tokens": 32768,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 4.5e-06,
+        "litellm_provider": "sambanova",
         "mode": "chat",
-        "supports_reasoning": true
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "source": "https://cloud.sambanova.ai/plans/pricing"
+    },
+    "sambanova/gemma-4-31B-it": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 1.15e-06,
+        "litellm_provider": "sambanova",
+        "mode": "chat",
+        "supports_vision": true,
+        "source": "https://cloud.sambanova.ai/plans/pricing"
+    },
+      "snowflake/claude-3-5-sonnet": {
+        "litellm_provider": "snowflake",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015,
+        "cache_read_input_token_cost": 0.0000003,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+      "snowflake/deepseek-r1": {
+        "litellm_provider": "snowflake",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "input_cost_per_token": 0.00000135,
+        "output_cost_per_token": 0.0000054,
+        "supports_reasoning": true,
+        "supports_system_messages": true
     },
     "snowflake/gemma-7b": {
         "litellm_provider": "snowflake",
@@ -31689,23 +31751,34 @@
     "snowflake/llama3.1-405b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat"
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "input_cost_per_token": 0.0000012,
+        "output_cost_per_token": 0.0000012,
+        "supports_function_calling": true,
+        "supports_system_messages": true
     },
     "snowflake/llama3.1-70b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat"
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "input_cost_per_token": 0.00000072,
+        "output_cost_per_token": 0.00000072,
+        "supports_function_calling": true,
+        "supports_system_messages": true
     },
     "snowflake/llama3.1-8b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat"
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "input_cost_per_token": 0.00000024,
+        "output_cost_per_token": 0.00000024,
+        "supports_system_messages": true
     },
     "snowflake/llama3.2-1b": {
         "litellm_provider": "snowflake",
@@ -31721,13 +31794,17 @@
         "max_tokens": 8192,
         "mode": "chat"
     },
-    "snowflake/llama3.3-70b": {
-        "litellm_provider": "snowflake",
+      "snowflake/llama3.3-70b": {
+        "max_tokens": 16384,
         "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat"
-    },
+        "max_output_tokens": 16384,
+        "input_cost_per_token": 0.00000072,
+        "output_cost_per_token": 0.00000072,
+        "litellm_provider": "snowflake",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_system_messages": true
+      },
     "snowflake/mistral-7b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 32000,
@@ -31742,12 +31819,17 @@
         "max_tokens": 8192,
         "mode": "chat"
     },
-    "snowflake/mistral-large2": {
+     "snowflake/mistral-large2": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat"
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.000006,
+        "supports_function_calling": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
     },
     "snowflake/mixtral-8x7b": {
         "litellm_provider": "snowflake",
@@ -31784,13 +31866,17 @@
         "max_tokens": 8192,
         "mode": "chat"
     },
-    "snowflake/snowflake-llama-3.3-70b": {
+      "snowflake/snowflake-llama-3.3-70b": {
+        "max_tokens": 16384,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "input_cost_per_token": 0.00000072,
+        "output_cost_per_token": 0.00000072,
         "litellm_provider": "snowflake",
-        "max_input_tokens": 8000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat"
-    },
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_system_messages": true
+      },
     "stability/sd3": {
         "litellm_provider": "stability",
         "mode": "image_generation",
@@ -32133,6 +32219,11 @@
         "litellm_provider": "tavily",
         "mode": "search"
     },
+    "you_com/search": {
+        "input_cost_per_query": 0.0,
+        "litellm_provider": "you_com",
+        "mode": "search"
+    },
     "text-completion-codestral/codestral-2405": {
         "input_cost_per_token": 0.0,
         "litellm_provider": "text-completion-codestral",
@@ -36652,17 +36743,7 @@
         "max_input_tokens": 32000,
         "max_tokens": 32000,
         "mode": "embedding",
-        "output_cost_per_token": 0.0,
-        "supports_vision": true
-    },
-    "voyage/voyage-multimodal-3.5": {
-        "input_cost_per_token": 1.2e-07,
-        "litellm_provider": "voyage",
-        "max_input_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "embedding",
-        "output_cost_per_token": 0.0,
-        "supports_vision": true
+        "output_cost_per_token": 0.0
     },
     "wandb/openai/gpt-oss-120b": {
         "max_tokens": 131072,
@@ -40327,6 +40408,178 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "scaleway/qwen/qwen3.5-397b-a17b": {
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 3.6e-06,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "scaleway/qwen/qwen3.6-35b-a3b": {
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-06,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_reasoning": true
+    },
+    "scaleway/qwen/qwen3-235b-a22b-instruct-2507": {
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 2.25e-06,
+        "supports_function_calling": true
+    },
+    "scaleway/qwen/qwen3-embedding-8b": {
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "scaleway",
+        "mode": "embedding",
+        "output_cost_per_token": 0.0
+    },
+    "scaleway/qwen/qwen3-coder-30b-a3b-instruct": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "supports_function_calling": true
+    },
+    "scaleway/openai/gpt-oss-120b": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_function_calling": true
+    },
+    "scaleway/openai/whisper-large-v3": {
+        "input_cost_per_audio_token": 0.0,
+        "litellm_provider": "scaleway",
+        "mode": "audio_transcription",
+        "output_cost_per_token": 0.0
+    },
+    "scaleway/google/gemma-4-26b-a4b-it": {
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "scaleway/google/gemma-3-27b-it": {
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 40000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "scaleway/hcompany/holo2-30b-a3b": {
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 22000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 7e-07,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "scaleway/mistralai/mistral-medium-3.5-128b": {
+        "input_cost_per_token": 1.5e-06,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-06,
+        "supports_reasoning": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_tool_choice": true
+    },
+    "scaleway/mistralai/devstral-2-123b-instruct-2512": {
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "supports_function_calling": true
+    },
+    "scaleway/mistralai/voxtral-small-24b-2507": {
+        "input_cost_per_audio_token": 1.5e-07,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 32000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 3.5e-07,
+        "supports_audio_input": true
+    },
+    "scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 3.5e-07,
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "scaleway/mistralai/pixtral-12b-2409": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 2e-07,
+        "supports_vision": true,
+        "supports_function_calling": true
+    },
+    "scaleway/BAAI/bge-multilingual-gemma2": {
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "scaleway",
+        "mode": "embedding",
+        "output_cost_per_token": 0.0
+    },
+    "scaleway/meta/llama-3.3-70b-instruct": {
+        "input_cost_per_token": 9e-07,
+        "litellm_provider": "scaleway",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 9e-07,
+        "supports_function_calling": true
+    },
     "novita/deepseek/deepseek-v3.2": {
         "litellm_provider": "novita",
         "mode": "chat",
@@ -43108,192 +43361,362 @@
         "supports_native_structured_output": true,
         "supports_pdf_input": true
     },
-    "soniox/stt-async-v4": {
-        "litellm_provider": "soniox",
-        "max_output_tokens": 8000,
-        "max_tokens": 8000,
-        "input_cost_per_second": 0.0,
-        "output_cost_per_second": 0.0000277778,
-        "mode": "audio_transcription",
-        "source": "https://soniox.com/pricing",
-        "supported_endpoints": [
-            "/v1/audio/transcriptions"
-        ],
-        "supports_audio_input": true
-    },
-    "soniox/stt-async-v5": {
-        "litellm_provider": "soniox",
-        "max_output_tokens": 8000,
-        "max_tokens": 8000,
-        "input_cost_per_second": 0.0,
-        "output_cost_per_second": 0.0000277778,
-        "mode": "audio_transcription",
-        "source": "https://soniox.com/pricing",
-        "supported_endpoints": [
-            "/v1/audio/transcriptions"
-        ],
-        "supports_audio_input": true
-    },
-    "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 3.6e-06,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 4.5e-07,
-        "output_cost_per_token": 1.8e-06,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/Qwen/Qwen3.6-27B-FP8": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 3.2e-07,
-        "output_cost_per_token": 3.2e-06,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 1.4e-06,
-        "output_cost_per_token": 4.4e-06,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 202752,
-        "max_output_tokens": 202752,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/deepseek-ai/DeepSeek-V4-Flash": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 1.4e-07,
-        "output_cost_per_token": 2.8e-07,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 32768,
-        "max_output_tokens": 32768,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/moonshotai/Kimi-K2.6": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 9.6e-07,
-        "output_cost_per_token": 4e-06,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 32768,
-        "max_output_tokens": 32768,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/MiniMaxAI/MiniMax-M2.5": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 196608,
-        "max_output_tokens": 196608,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/google/gemma-4-31B-it": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 1.4e-07,
-        "output_cost_per_token": 5.6e-07,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 32768,
-        "max_output_tokens": 32768,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/openai/gpt-oss-120b": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    },
-    "tensormesh/openai/gpt-oss-20b": {
-        "litellm_provider": "tensormesh",
-        "mode": "chat",
-        "input_cost_per_token": 7e-08,
-        "output_cost_per_token": 2.8e-07,
-        "cache_read_input_token_cost": 0,
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_system_messages": true,
-        "supports_reasoning": true,
-        "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
-    }
-,
+  "snowflake/claude-sonnet-4-5": {
+    "max_tokens": 16384,
+    "max_input_tokens": 200000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.000003,
+    "output_cost_per_token": 0.000015,
+    "cache_read_input_token_cost": 0.0000003,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_vision": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_response_schema": true
+  },
+  "snowflake/claude-sonnet-4-6": {
+    "max_tokens": 16384,
+    "max_input_tokens": 200000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.000003,
+    "output_cost_per_token": 0.000015,
+    "cache_read_input_token_cost": 0.0000003,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_vision": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_response_schema": true
+  },
+  "snowflake/claude-4-sonnet": {
+    "max_tokens": 16384,
+    "max_input_tokens": 200000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.000003,
+    "output_cost_per_token": 0.000015,
+    "cache_read_input_token_cost": 0.0000003,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_vision": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_response_schema": true
+  },
+  "snowflake/claude-4-opus": {
+    "max_tokens": 16384,
+    "max_input_tokens": 200000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.000005,
+    "output_cost_per_token": 0.000025,
+    "cache_read_input_token_cost": 0.0000005,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_vision": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "supports_response_schema": true
+  },
+  "snowflake/claude-haiku-4-5": {
+    "max_tokens": 16384,
+    "max_input_tokens": 200000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.000001,
+    "output_cost_per_token": 0.000005,
+    "cache_read_input_token_cost": 0.0000001,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_vision": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_response_schema": true
+  },
+  "snowflake/claude-3-7-sonnet": {
+    "max_tokens": 16384,
+    "max_input_tokens": 200000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.000003,
+    "output_cost_per_token": 0.000015,
+    "cache_read_input_token_cost": 0.0000003,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_vision": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "supports_response_schema": true
+  },
+  "snowflake/openai-gpt-4.1": {
+    "max_tokens": 16384,
+    "max_input_tokens": 300000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.000002,
+    "output_cost_per_token": 0.000008,
+    "cache_read_input_token_cost": 0.0000005,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_vision": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_response_schema": true
+  },
+  "snowflake/openai-gpt-5": {
+    "max_tokens": 16384,
+    "max_input_tokens": 300000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.00000125,
+    "output_cost_per_token": 0.00001,
+    "cache_read_input_token_cost": 0.000000125,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_vision": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "supports_response_schema": true
+  },
+  "snowflake/openai-gpt-5-mini": {
+    "max_tokens": 16384,
+    "max_input_tokens": 1000000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.0000003,
+    "output_cost_per_token": 0.0000012,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_system_messages": true,
+    "supports_response_schema": true
+  },
+  "snowflake/openai-gpt-5-nano": {
+    "max_tokens": 16384,
+    "max_input_tokens": 5000000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.00000015,
+    "output_cost_per_token": 0.0000006,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_system_messages": true,
+    "supports_response_schema": true
+  },
+  "snowflake/llama4-maverick": {
+    "max_tokens": 16384,
+    "max_input_tokens": 128000,
+    "max_output_tokens": 16384,
+    "input_cost_per_token": 0.00000024,
+    "output_cost_per_token": 0.00000097,
+    "litellm_provider": "snowflake",
+    "mode": "chat",
+    "supports_function_calling": true,
+    "supports_system_messages": true
+  },
+  "snowflake/snowflake-arctic-embed-l-v2.0": {
+    "max_tokens": 8192,
+    "max_input_tokens": 8192,
+    "input_cost_per_token": 0.00000007,
+    "output_cost_per_token": 0.0,
+    "litellm_provider": "snowflake",
+    "mode": "embedding"
+  },
+  "snowflake/snowflake-arctic-embed-m-v2.0": {
+    "max_tokens": 8192,
+    "max_input_tokens": 8192,
+    "input_cost_per_token": 0.00000007,
+    "output_cost_per_token": 0.0,
+    "litellm_provider": "snowflake",
+    "mode": "embedding"
+  },
+  "soniox/stt-async-v4": {
+    "litellm_provider": "soniox",
+    "max_output_tokens": 8000,
+    "max_tokens": 8000,
+    "input_cost_per_second": 0.0,
+    "output_cost_per_second": 0.0000277778,
+    "mode": "audio_transcription",
+    "source": "https://soniox.com/pricing",
+    "supported_endpoints": ["/v1/audio/transcriptions"],
+    "supports_audio_input": true
+  },
+  "soniox/stt-async-v5": {
+    "litellm_provider": "soniox",
+    "max_output_tokens": 8000,
+    "max_tokens": 8000,
+    "input_cost_per_second": 0.0,
+    "output_cost_per_second": 0.0000277778,
+    "mode": "audio_transcription",
+    "source": "https://soniox.com/pricing",
+    "supported_endpoints": ["/v1/audio/transcriptions"],
+    "supports_audio_input": true
+  },
+  "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 6e-07,
+    "output_cost_per_token": 3.6e-06,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 262144,
+    "max_output_tokens": 262144,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 4.5e-07,
+    "output_cost_per_token": 1.8e-06,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 262144,
+    "max_output_tokens": 262144,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/Qwen/Qwen3.6-27B-FP8": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 3.2e-07,
+    "output_cost_per_token": 3.2e-06,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 262144,
+    "max_output_tokens": 262144,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 1.4e-06,
+    "output_cost_per_token": 4.4e-06,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 202752,
+    "max_output_tokens": 202752,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/deepseek-ai/DeepSeek-V4-Flash": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 1.4e-07,
+    "output_cost_per_token": 2.8e-07,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 32768,
+    "max_output_tokens": 32768,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/moonshotai/Kimi-K2.6": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 9.6e-07,
+    "output_cost_per_token": 4e-06,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 32768,
+    "max_output_tokens": 32768,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/MiniMaxAI/MiniMax-M2.5": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 3e-07,
+    "output_cost_per_token": 1.2e-06,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 196608,
+    "max_output_tokens": 196608,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/google/gemma-4-31B-it": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 1.4e-07,
+    "output_cost_per_token": 5.6e-07,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 32768,
+    "max_output_tokens": 32768,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/openai/gpt-oss-120b": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 1.5e-07,
+    "output_cost_per_token": 6e-07,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 131072,
+    "max_output_tokens": 131072,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  },
+  "tensormesh/openai/gpt-oss-20b": {
+    "litellm_provider": "tensormesh",
+    "mode": "chat",
+    "input_cost_per_token": 7e-08,
+    "output_cost_per_token": 2.8e-07,
+    "cache_read_input_token_cost": 0,
+    "max_input_tokens": 131072,
+    "max_output_tokens": 131072,
+    "supports_function_calling": true,
+    "supports_tool_choice": true,
+    "supports_response_schema": true,
+    "supports_prompt_caching": true,
+    "supports_system_messages": true,
+    "supports_reasoning": true,
+    "source": "https://serverless.tensormesh.ai/v1/models/openrouter"
+  }
+ ,
     "deepseek-v4-flash": {
         "cache_creation_input_token_cost": 0.0,
         "cache_read_input_token_cost": 2.8e-09,
@@ -43427,5 +43850,83 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": false
+    },
+    "pinstripes/ps/glm-4.5-air": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 0.000000125,
+        "output_cost_per_token": 0.00000045,
+        "litellm_provider": "pinstripes",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_assistant_prefill": true,
+        "supports_reasoning": true,
+        "source": "https://pinstripes.io/pricing"
+    },
+    "pinstripes/ps/qwen3.6-35b-a3b": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.00000014,
+        "output_cost_per_token": 0.00000045,
+        "litellm_provider": "pinstripes",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_assistant_prefill": true,
+        "supports_reasoning": true,
+        "source": "https://pinstripes.io/pricing"
+    },
+    "pinstripes/ps/qwen3-30b-a3b": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.00000009,
+        "output_cost_per_token": 0.0000002,
+        "litellm_provider": "pinstripes",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_assistant_prefill": true,
+        "supports_reasoning": true,
+        "source": "https://pinstripes.io/pricing"
+    },
+    "pinstripes/ps/qwen3-coder-30b-a3b": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.0000003,
+        "output_cost_per_token": 0.0000006,
+        "litellm_provider": "pinstripes",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_assistant_prefill": true,
+        "supports_reasoning": false,
+        "source": "https://pinstripes.io/pricing"
+    },
+    "pinstripes/ps/deepseek-v4-flash": {
+        "max_tokens": 163840,
+        "max_input_tokens": 163840,
+        "max_output_tokens": 163840,
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.0000002,
+        "litellm_provider": "pinstripes",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_assistant_prefill": true,
+        "supports_reasoning": true,
+        "source": "https://pinstripes.io/pricing"
+    },
+    "pinstripes/ps/minimax-m2.7": {
+        "max_tokens": 1000192,
+        "max_input_tokens": 1000192,
+        "max_output_tokens": 1000192,
+        "input_cost_per_token": 0.000000255,
+        "output_cost_per_token": 0.00000055,
+        "litellm_provider": "pinstripes",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_assistant_prefill": true,
+        "supports_reasoning": false,
+        "source": "https://pinstripes.io/pricing"
     }
 }
diff --git a/litellm/proxy/spend_tracking/cold_storage_handler.py b/litellm/proxy/spend_tracking/cold_storage_handler.py
index 57c41bafccd..01c698c7122 100644
--- a/litellm/proxy/spend_tracking/cold_storage_handler.py
+++ b/litellm/proxy/spend_tracking/cold_storage_handler.py
@@ -4,8 +4,6 @@ This module is responsible for handling Getting/Setting the proxy server request
 It allows fetching a dict of the proxy server request from s3 or GCS bucket.
 """
 
-from typing import Optional
-
 import litellm
 from litellm import _custom_logger_compatible_callbacks_literal
 from litellm.integrations.custom_logger import CustomLogger
@@ -16,12 +14,18 @@ class ColdStorageHandler:
     This class is responsible for handling Getting/Setting the proxy server request from cold storage.
 
     It allows fetching a dict of the proxy server request from s3 or GCS bucket.
+
+    The cold storage logger can be injected for testing; when omitted it is
+    resolved from the configured ``litellm.cold_storage_custom_logger``.
     """
 
+    def __init__(self, cold_storage_logger: CustomLogger | None = None):
+        self._injected_cold_storage_logger = cold_storage_logger
+
     async def get_proxy_server_request_from_cold_storage_with_object_key(
         self,
         object_key: str,
-    ) -> Optional[dict]:
+    ) -> dict | None:
         """
         Get the proxy server request from cold storage using the object key directly.
 
@@ -31,38 +35,31 @@ class ColdStorageHandler:
         Returns:
             Optional[dict]: The proxy server request dict or None if not found
         """
-
-        # select the custom logger to use for cold storage
-        custom_logger_name: Optional[_custom_logger_compatible_callbacks_literal] = (
-            self._select_custom_logger_for_cold_storage()
+        custom_logger = (
+            self._injected_cold_storage_logger or self._resolve_cold_storage_logger()
         )
-
-        # if no custom logger name is configured, return None
-        if custom_logger_name is None:
+        if custom_logger is None:
             return None
 
-        # get the active/initialized custom logger
-        custom_logger: Optional[CustomLogger] = (
+        return await custom_logger.get_proxy_server_request_from_cold_storage_with_object_key(
+            object_key=object_key,
+        )
+
+    def _resolve_cold_storage_logger(self) -> CustomLogger | None:
+        custom_logger_name = self._select_custom_logger_for_cold_storage()
+        if custom_logger_name is None:
+            return None
+        return (
             litellm.logging_callback_manager.get_active_custom_logger_for_callback_name(
                 custom_logger_name
             )
         )
 
-        # if no custom logger is found, return None
-        if custom_logger is None:
-            return None
-
-        proxy_server_request = await custom_logger.get_proxy_server_request_from_cold_storage_with_object_key(
-            object_key=object_key,
-        )
-
-        return proxy_server_request
-
     def _select_custom_logger_for_cold_storage(
         self,
-    ) -> Optional[_custom_logger_compatible_callbacks_literal]:
-        cold_storage_custom_logger: Optional[
-            _custom_logger_compatible_callbacks_literal
-        ] = litellm.cold_storage_custom_logger
+    ) -> _custom_logger_compatible_callbacks_literal | None:
+        cold_storage_custom_logger: (
+            _custom_logger_compatible_callbacks_literal | None
+        ) = litellm.cold_storage_custom_logger
 
         return cold_storage_custom_logger
diff --git a/litellm/proxy/spend_tracking/spend_management_endpoints.py b/litellm/proxy/spend_tracking/spend_management_endpoints.py
index 29fc6d7c30f..8ca048a0caa 100644
--- a/litellm/proxy/spend_tracking/spend_management_endpoints.py
+++ b/litellm/proxy/spend_tracking/spend_management_endpoints.py
@@ -3,7 +3,16 @@ import collections
 import json
 import os
 from datetime import datetime, timedelta, timezone
-from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Dict,
+    List,
+    Literal,
+    Mapping,
+    NamedTuple,
+    Union,
+)
 
 import fastapi
 from fastapi import APIRouter, Depends, HTTPException, Request, status
@@ -29,6 +38,7 @@ from litellm.repositories.verification_token_repository import (
 
 if TYPE_CHECKING:
     from litellm.proxy.proxy_server import PrismaClient
+    from litellm.proxy.spend_tracking.cold_storage_handler import ColdStorageHandler
 else:
     PrismaClient = Any
 
@@ -104,7 +114,7 @@ def _strip_password_from_users(users) -> None:
     include_in_schema=False,
 )
 async def spend_user_fn(
-    user_id: Optional[str] = fastapi.Query(
+    user_id: str | None = fastapi.Query(
         default=None,
         description="Get User Table row for user_id",
     ),
@@ -185,11 +195,11 @@ async def spend_user_fn(
     },
 )
 async def view_spend_tags(
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing key spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view key spend",
     ),
@@ -290,11 +300,11 @@ async def get_global_activity_internal_user(
     include_in_schema=False,
 )
 async def get_global_activity(
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view spend",
     ),
@@ -437,11 +447,11 @@ async def get_global_activity_model_internal_user(
     include_in_schema=False,
 )
 async def get_global_activity_model(
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view spend",
     ),
@@ -597,11 +607,11 @@ async def get_global_activity_exceptions_per_deployment(
     model_group: str = fastapi.Query(
         description="Filter by model group",
     ),
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view spend",
     ),
@@ -750,11 +760,11 @@ async def get_global_activity_exceptions(
     model_group: str = fastapi.Query(
         description="Filter by model group",
     ),
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view spend",
     ),
@@ -857,11 +867,11 @@ async def get_global_activity_exceptions(
     },
 )
 async def get_global_spend_provider(
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view spend",
     ),
@@ -992,31 +1002,31 @@ async def get_global_spend_provider(
     },
 )
 async def get_global_spend_report(
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view spend",
     ),
-    group_by: Optional[Literal["team", "customer", "api_key"]] = fastapi.Query(
+    group_by: Literal["team", "customer", "api_key"] | None = fastapi.Query(
         default="team",
         description="Group spend by internal team or customer or api_key",
     ),
-    api_key: Optional[str] = fastapi.Query(
+    api_key: str | None = fastapi.Query(
         default=None,
         description="View spend for a specific api_key. Example api_key='sk-1234",
     ),
-    internal_user_id: Optional[str] = fastapi.Query(
+    internal_user_id: str | None = fastapi.Query(
         default=None,
         description="View spend for a specific internal_user_id. Example internal_user_id='1234",
     ),
-    team_id: Optional[str] = fastapi.Query(
+    team_id: str | None = fastapi.Query(
         default=None,
         description="View spend for a specific team_id. Example team_id='1234",
     ),
-    customer_id: Optional[str] = fastapi.Query(
+    customer_id: str | None = fastapi.Query(
         default=None,
         description="View spend for a specific customer_id. Example customer_id='1234. Can be used in conjunction with team_id as well.",
     ),
@@ -1412,15 +1422,15 @@ async def global_get_all_tag_names():
     },
 )
 async def global_view_spend_tags(
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing key spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view key spend",
     ),
-    tags: Optional[str] = fastapi.Query(
+    tags: str | None = fastapi.Query(
         default=None,
         description="comman separated tags to filter on",
     ),
@@ -1639,7 +1649,7 @@ async def calculate_spend(request: SpendCalculateRequest):
 
             # check if model in llm_router
             _model_in_llm_router = None
-            cost_per_token: Optional[CostPerToken] = None
+            cost_per_token: CostPerToken | None = None
             if llm_router is not None:
                 if (
                     llm_router.model_group_alias is not None
@@ -1732,35 +1742,35 @@ async def calculate_spend(request: SpendCalculateRequest):
 )
 async def ui_view_spend_logs(
     request: Request,
-    api_key: Optional[str] = fastapi.Query(
+    api_key: str | None = fastapi.Query(
         default=None,
         description="Get spend logs based on api key",
     ),
-    user_id: Optional[str] = fastapi.Query(
+    user_id: str | None = fastapi.Query(
         default=None,
         description="Get spend logs based on user_id",
     ),
-    request_id: Optional[str] = fastapi.Query(
+    request_id: str | None = fastapi.Query(
         default=None,
         description="request_id to get spend logs for specific request_id",
     ),
-    team_id: Optional[str] = fastapi.Query(
+    team_id: str | None = fastapi.Query(
         default=None,
         description="Filter spend logs by team_id",
     ),
-    min_spend: Optional[float] = fastapi.Query(
+    min_spend: float | None = fastapi.Query(
         default=None,
         description="Filter logs with spend greater than or equal to this value",
     ),
-    max_spend: Optional[float] = fastapi.Query(
+    max_spend: float | None = fastapi.Query(
         default=None,
         description="Filter logs with spend less than or equal to this value",
     ),
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing key spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view key spend",
     ),
@@ -1771,36 +1781,34 @@ async def ui_view_spend_logs(
         default=50, description="Number of items per page", ge=1, le=100
     ),
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
-    status_filter: Optional[str] = fastapi.Query(
+    status_filter: str | None = fastapi.Query(
         default=None, description="Filter logs by status (e.g., success, failure)"
     ),
-    model: Optional[str] = fastapi.Query(
-        default=None, description="Filter logs by model"
-    ),
-    model_id: Optional[str] = fastapi.Query(
+    model: str | None = fastapi.Query(default=None, description="Filter logs by model"),
+    model_id: str | None = fastapi.Query(
         default=None,
         description="Filter logs by model ID (litellm model deployment id)",
     ),
-    model_group: Optional[str] = fastapi.Query(
+    model_group: str | None = fastapi.Query(
         default=None, description="Filter logs by model group"
     ),
-    key_alias: Optional[str] = fastapi.Query(
+    key_alias: str | None = fastapi.Query(
         default=None, description="Filter logs by key alias"
     ),
-    end_user: Optional[str] = fastapi.Query(
+    end_user: str | None = fastapi.Query(
         default=None, description="Filter logs by end user"
     ),
-    error_code: Optional[str] = fastapi.Query(
+    error_code: str | None = fastapi.Query(
         default=None, description="Filter logs by error code (e.g., '404', '500')"
     ),
-    error_message: Optional[str] = fastapi.Query(
+    error_message: str | None = fastapi.Query(
         default=None, description="Filter logs by error message (partial string match)"
     ),
     sort_by: str = fastapi.Query(
         default="startTime",
         description="Sort logs by field: spend, total_tokens, startTime, endTime, request_duration_ms, model, or ttft_ms",
     ),
-    sort_order: Optional[str] = fastapi.Query(
+    sort_order: str | None = fastapi.Query(
         default="desc",
         description="Sort order: asc or desc",
     ),
@@ -1964,7 +1972,7 @@ async def ui_view_spend_logs(
             if max_spend is not None:
                 where_conditions["spend"]["lte"] = max_spend
         is_admin_view = _is_admin_view_safe(user_api_key_dict=user_api_key_dict)
-        permitted_team_ids: Optional[List[str]] = None
+        permitted_team_ids: List[str] | None = None
         if not is_admin_view:
             if team_id is not None:
                 can_view_team = await _can_team_member_view_log(
@@ -2171,6 +2179,89 @@ async def ui_view_spend_logs(
         raise handle_exception_on_proxy(e)
 
 
+class RequestResponsePayload(NamedTuple):
+    messages: Union[str, list, dict] | None
+    response: Union[str, list, dict] | None
+    proxy_server_request: Union[str, dict] | None
+
+
+_EMPTY_SPEND_LOG_VALUES = frozenset({"", "{}", "[]", "null"})
+
+
+def _spend_log_field_has_content(value: Union[str, list, dict] | None) -> bool:
+    if value is None:
+        return False
+    if isinstance(value, str):
+        return value.strip() not in _EMPTY_SPEND_LOG_VALUES
+    if isinstance(value, (list, dict)):
+        return len(value) > 0
+    return True
+
+
+def _cold_storage_object_key_from_metadata(
+    metadata: Union[str, dict] | None,
+) -> str | None:
+    if isinstance(metadata, str):
+        try:
+            metadata = json.loads(metadata)
+        except (json.JSONDecodeError, TypeError):
+            return None
+    if not isinstance(metadata, dict):
+        return None
+    object_key = metadata.get("cold_storage_object_key")
+    return object_key if isinstance(object_key, str) and object_key else None
+
+
+async def _resolve_request_response_payload(
+    row: Mapping[str, Any],
+    cold_storage_handler: "ColdStorageHandler",
+) -> RequestResponsePayload:
+    """
+    Decide where the prompt/response come from for a single spend-log row.
+
+    PG holds the content when ``store_prompts_in_spend_logs`` is on; otherwise it
+    holds ``"{}"`` placeholders and the real payload lives in cold storage keyed
+    by ``metadata.cold_storage_object_key``. The choice is made on actual row
+    content, not config flags, so historical and mixed-storage rows both resolve
+    correctly.
+    """
+    messages = row.get("messages")
+    response = row.get("response")
+    proxy_server_request = row.get("proxy_server_request")
+
+    pg_payload = RequestResponsePayload(messages, response, proxy_server_request)
+    if (
+        _spend_log_field_has_content(messages)
+        or _spend_log_field_has_content(response)
+        or _spend_log_field_has_content(proxy_server_request)
+    ):
+        return pg_payload
+
+    object_key = _cold_storage_object_key_from_metadata(row.get("metadata"))
+    if object_key is None:
+        return pg_payload
+
+    try:
+        payload = await cold_storage_handler.get_proxy_server_request_from_cold_storage_with_object_key(
+            object_key=object_key
+        )
+    except Exception:
+        verbose_proxy_logger.warning(
+            "Failed to fetch cold storage payload for key %s; falling back to DB values",
+            object_key,
+            exc_info=True,
+        )
+        return pg_payload
+    if payload is None:
+        return pg_payload
+
+    return RequestResponsePayload(
+        messages=payload.get("messages"),
+        response=payload.get("response"),
+        proxy_server_request=payload.get("proxy_server_request"),
+    )
+
+
 @router.get(
     "/spend/logs/ui/{request_id}",
     tags=["Budget & Spend Tracking"],
@@ -2179,11 +2270,11 @@ async def ui_view_spend_logs(
 )
 async def ui_view_request_response_for_request_id(
     request_id: str,
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing key spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view key spend",
     ),
@@ -2215,8 +2306,8 @@ async def ui_view_request_response_for_request_id(
         )
 
     custom_loggers = litellm.logging_callback_manager.get_active_additional_logging_utils_from_custom_logger()
-    start_date_obj: Optional[datetime] = None
-    end_date_obj: Optional[datetime] = None
+    start_date_obj: datetime | None = None
+    end_date_obj: datetime | None = None
     if start_date is not None:
         start_date_obj = datetime.strptime(start_date, "%Y-%m-%d %H:%M:%S").replace(
             tzinfo=timezone.utc
@@ -2235,26 +2326,27 @@ async def ui_view_request_response_for_request_id(
         if payload is not None:
             return payload
 
-    # Fallback: fetch heavy columns directly from the database.
-    # The list endpoint (/spend/logs/ui) intentionally excludes messages,
-    # response, and proxy_server_request for performance. When no custom
-    # logger (S3, GCS, etc.) is configured, we still need to serve these
-    # fields from the DB for the detail/drawer view.
+    # Fallback: the list endpoint omits the heavy columns for performance, so
+    # serve them here. When prompts were offloaded to cold storage the DB holds
+    # only placeholders, so _resolve_request_response_payload fetches the real
+    # payload from the configured cold storage backend by object key.
     if prisma_client is not None:
+        from litellm.proxy.spend_tracking.cold_storage_handler import (
+            ColdStorageHandler,
+        )
+
         sql_query = """
-            SELECT messages, response, proxy_server_request
+            SELECT messages, response, proxy_server_request, metadata
             FROM "LiteLLM_SpendLogs"
             WHERE request_id = $1
             LIMIT 1
         """
         db_result = await prisma_client.db.query_raw(sql_query, request_id)
         if db_result and len(db_result) > 0:
-            row = db_result[0]
-            return {
-                "messages": row.get("messages"),
-                "response": row.get("response"),
-                "proxy_server_request": row.get("proxy_server_request"),
-            }
+            resolved = await _resolve_request_response_payload(
+                db_result[0], cold_storage_handler=ColdStorageHandler()
+            )
+            return resolved._asdict()
 
     return None
 
@@ -2268,23 +2360,23 @@ async def ui_view_request_response_for_request_id(
     },
 )
 async def view_spend_logs(
-    api_key: Optional[str] = fastapi.Query(
+    api_key: str | None = fastapi.Query(
         default=None,
         description="Get spend logs based on api key",
     ),
-    user_id: Optional[str] = fastapi.Query(
+    user_id: str | None = fastapi.Query(
         default=None,
         description="Get spend logs based on user_id",
     ),
-    request_id: Optional[str] = fastapi.Query(
+    request_id: str | None = fastapi.Query(
         default=None,
         description="request_id to get spend logs for specific request_id. If none passed then pass spend logs for all requests",
     ),
-    start_date: Optional[str] = fastapi.Query(
+    start_date: str | None = fastapi.Query(
         default=None,
         description="Time from which to start viewing key spend",
     ),
-    end_date: Optional[str] = fastapi.Query(
+    end_date: str | None = fastapi.Query(
         default=None,
         description="Time till which to view key spend",
     ),
@@ -2622,7 +2714,7 @@ async def global_spend_refresh():
 
 
 async def global_spend_for_internal_user(
-    api_key: Optional[str] = None,
+    api_key: str | None = None,
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
 ):
     from litellm.proxy.proxy_server import prisma_client
@@ -2666,7 +2758,7 @@ async def global_spend_for_internal_user(
     include_in_schema=False,
 )
 async def global_spend_logs(
-    api_key: Optional[str] = fastapi.Query(
+    api_key: str | None = fastapi.Query(
         default=None,
         description="API Key to get global spend (spend per day for last 30d). Admin-only endpoint",
     ),
@@ -3025,7 +3117,7 @@ async def global_view_all_end_users():
     dependencies=[Depends(user_api_key_auth)],
     include_in_schema=False,
 )
-async def global_spend_end_users(data: Optional[GlobalEndUsersSpend] = None):
+async def global_spend_end_users(data: GlobalEndUsersSpend | None = None):
     """
     [BETA] This is a beta endpoint. It will change.
 
@@ -3258,8 +3350,8 @@ async def get_spend_by_tags(
 async def ui_get_spend_by_tags(
     start_date: str,
     end_date: str,
-    prisma_client: Optional[PrismaClient] = None,
-    tags_str: Optional[str] = None,
+    prisma_client: PrismaClient | None = None,
+    tags_str: str | None = None,
 ):
     """
     Should cover 2 cases:
@@ -3270,7 +3362,7 @@ async def ui_get_spend_by_tags(
     # tags_str is a list of strings csv of tags
     # tags_str = tag1,tag2,tag3
     # convert to list if it's not None
-    tags_list: Optional[List[str]] = None
+    tags_list: List[str] | None = None
     if tags_str is not None and len(tags_str) > 0:
         tags_list = tags_str.split(",")
 
@@ -3534,7 +3626,7 @@ async def _build_ui_spend_logs_response(
     }
 
 
-def _build_status_filter_condition(status_filter: Optional[str]) -> Dict[str, Any]:
+def _build_status_filter_condition(status_filter: str | None) -> Dict[str, Any]:
     """
     Helper function to build the status filter condition for database queries.
 
@@ -3573,7 +3665,7 @@ def _is_admin_view_safe(user_api_key_dict: UserAPIKeyAuth) -> bool:
 async def _can_team_member_view_log(
     prisma_client,
     user_api_key_dict: UserAPIKeyAuth,
-    team_id: Optional[str],
+    team_id: str | None,
 ) -> bool:
     """
     Check if the requesting user can view spend logs for the given team.
diff --git a/litellm/rerank_api/main.py b/litellm/rerank_api/main.py
index e40e12e9197..35d40423bca 100644
--- a/litellm/rerank_api/main.py
+++ b/litellm/rerank_api/main.py
@@ -1,7 +1,7 @@
 import asyncio
 import contextvars
 from functools import partial
-from typing import Any, Coroutine, Dict, List, Literal, Optional, Union
+from typing import Any, Coroutine, Dict, List, Literal, Union
 
 import litellm
 from litellm._logging import verbose_logger
@@ -30,15 +30,16 @@ async def arerank(
     model: str,
     query: str,
     documents: List[Union[str, Dict[str, Any]]],
-    custom_llm_provider: Optional[
+    custom_llm_provider: (
         Literal[
             "cohere", "together_ai", "deepinfra", "fireworks_ai", "voyage", "watsonx"
         ]
-    ] = None,
-    top_n: Optional[int] = None,
-    rank_fields: Optional[List[str]] = None,
-    return_documents: Optional[bool] = None,
-    max_chunks_per_doc: Optional[int] = None,
+        | None
+    ) = None,
+    top_n: int | None = None,
+    rank_fields: List[str] | None = None,
+    return_documents: bool | None = None,
+    max_chunks_per_doc: int | None = None,
     **kwargs,
 ) -> Union[RerankResponse, Coroutine[Any, Any, RerankResponse]]:
     """
@@ -79,7 +80,7 @@ def rerank(
     model: str,
     query: str,
     documents: List[Union[str, Dict[str, Any]]],
-    custom_llm_provider: Optional[
+    custom_llm_provider: (
         Literal[
             "cohere",
             "together_ai",
@@ -92,20 +93,26 @@ def rerank(
             "voyage",
             "watsonx",
         ]
-    ] = None,
-    top_n: Optional[int] = None,
-    rank_fields: Optional[List[str]] = None,
-    return_documents: Optional[bool] = True,
-    max_chunks_per_doc: Optional[int] = None,
-    max_tokens_per_doc: Optional[int] = None,
+        | None
+    ) = None,
+    top_n: int | None = None,
+    rank_fields: List[str] | None = None,
+    return_documents: bool | None = True,
+    max_chunks_per_doc: int | None = None,
+    max_tokens_per_doc: int | None = None,
     **kwargs,
 ) -> Union[RerankResponse, Coroutine[Any, Any, RerankResponse]]:
     """
     Reranks a list of documents based on their relevance to the query
     """
-    headers: Optional[dict] = kwargs.get("headers")  # type: ignore
+    # `instruction` is read from kwargs rather than declared as a named param.
+    # The router forwards rerank calls via an untyped `**kwargs` unpack, and a
+    # typed named param there would trip the basedpyright budget gate without
+    # adding real safety; it stays typed downstream via get_optional_rerank_params.
+    instruction: str | None = kwargs.get("instruction", None)
+    headers: dict | None = kwargs.get("headers")  # type: ignore
     litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj")  # type: ignore
-    litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None)
+    litellm_call_id: str | None = kwargs.get("litellm_call_id", None)
     proxy_server_request = kwargs.get("proxy_server_request", None)
     model_info = kwargs.get("model_info", None)
     user = kwargs.get("user", None)
@@ -155,6 +162,7 @@ def rerank(
             return_documents=return_documents,
             max_chunks_per_doc=max_chunks_per_doc,
             max_tokens_per_doc=max_tokens_per_doc,
+            instruction=instruction,
             non_default_params=kwargs,
         )
         verbose_logger.info(f"optional_rerank_params: {optional_rerank_params}")
@@ -187,11 +195,11 @@ def rerank(
             or _custom_llm_provider == litellm.LlmProviders.LITELLM_PROXY
         ):
             # Implement Cohere rerank logic
-            api_key: Optional[str] = (
+            api_key: str | None = (
                 dynamic_api_key or optional_params.api_key or litellm.api_key
             )
 
-            api_base: Optional[str] = (
+            api_base: str | None = (
                 dynamic_api_base
                 or optional_params.api_base
                 or litellm.api_base
diff --git a/litellm/rerank_api/rerank_utils.py b/litellm/rerank_api/rerank_utils.py
index 38e599ef824..856029e45ea 100644
--- a/litellm/rerank_api/rerank_utils.py
+++ b/litellm/rerank_api/rerank_utils.py
@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 from litellm.llms.base_llm.rerank.transformation import BaseRerankConfig
 
@@ -9,13 +9,14 @@ def get_optional_rerank_params(
     drop_params: bool,
     query: str,
     documents: List[Union[str, Dict[str, Any]]],
-    custom_llm_provider: Optional[str] = None,
-    top_n: Optional[int] = None,
-    rank_fields: Optional[List[str]] = None,
-    return_documents: Optional[bool] = True,
-    max_chunks_per_doc: Optional[int] = None,
-    max_tokens_per_doc: Optional[int] = None,
-    non_default_params: Optional[dict] = None,
+    custom_llm_provider: str | None = None,
+    top_n: int | None = None,
+    rank_fields: List[str] | None = None,
+    return_documents: bool | None = True,
+    max_chunks_per_doc: int | None = None,
+    max_tokens_per_doc: int | None = None,
+    instruction: str | None = None,
+    non_default_params: dict | None = None,
 ) -> Dict:
     all_non_default_params = non_default_params or {}
     if query is not None:
@@ -30,6 +31,11 @@ def get_optional_rerank_params(
         all_non_default_params["max_chunks_per_doc"] = max_chunks_per_doc
     if max_tokens_per_doc is not None:
         all_non_default_params["max_tokens_per_doc"] = max_tokens_per_doc
+    if instruction is not None:
+        # Also surfaced in non_default_params so providers that read it from
+        # there (e.g. DeepInfra) keep working now that `rerank()` consumes
+        # `instruction` as a named param instead of leaving it in **kwargs.
+        all_non_default_params["instruction"] = instruction
     return rerank_provider_config.map_cohere_rerank_params(
         model=model,
         drop_params=drop_params,
@@ -41,5 +47,6 @@ def get_optional_rerank_params(
         return_documents=return_documents,
         max_chunks_per_doc=max_chunks_per_doc,
         max_tokens_per_doc=max_tokens_per_doc,
+        instruction=instruction,
         non_default_params=all_non_default_params,
     )
diff --git a/litellm/router.py b/litellm/router.py
index 1aba259a328..20f8eba22ff 100644
--- a/litellm/router.py
+++ b/litellm/router.py
@@ -320,6 +320,7 @@ class Router:
             "latency-based-routing",
             "cost-based-routing",
             "usage-based-routing-v2",
+            "lar1",
         ] = "simple-shuffle",
         optional_pre_call_checks: Optional[OptionalPreCallChecks] = None,
         routing_strategy_args: dict = {},  # just for latency-based
@@ -639,10 +640,15 @@ class Router:
         """
 
         ### ROUTING SETUP ###
-        self.routing_strategy_init(
-            routing_strategy=routing_strategy,
-            routing_strategy_args=routing_strategy_args,
-        )
+        if self._normalize_strategy(routing_strategy) == "lar1":
+            from litellm.router_strategy.lar1_routing import apply_lar1_routing_strategy
+
+            apply_lar1_routing_strategy(self, routing_strategy_args)
+        else:
+            self.routing_strategy_init(
+                routing_strategy=routing_strategy,
+                routing_strategy_args=routing_strategy_args,
+            )
         self._init_routing_groups(self._routing_groups_input)
         self.access_groups = None
         ## USAGE TRACKING ##
@@ -863,7 +869,9 @@ class Router:
         self, routing_strategy: Union[RoutingStrategy, str, None]
     ) -> None:
         # See: https://github.com/BerriAI/litellm/issues/11330
-        valid_strategy_strings = ["simple-shuffle"] + [s.value for s in RoutingStrategy]
+        valid_strategy_strings = ["simple-shuffle", "lar1"] + [
+            s.value for s in RoutingStrategy
+        ]
         if routing_strategy is None:
             return
         is_valid_string = (
@@ -953,6 +961,7 @@ class Router:
     ):
         verbose_router_logger.info(f"Routing strategy: {routing_strategy}")
         self._validate_routing_strategy(routing_strategy)
+        self._reset_custom_routing_strategy()
 
         self._unregister_router_selectors(
             [
@@ -10601,6 +10610,7 @@ class Router:
 
         _existing_router_settings = self.get_settings()
         rebuild_routing_groups = False
+        relink_lar1_from_args = False
         for var in kwargs:
             if var in _allowed_settings:
                 if var in _int_settings:
@@ -10615,17 +10625,37 @@ class Router:
                     if var == "routing_strategy":
                         value = self._normalize_strategy(value)
                         if _existing_router_settings["routing_strategy"] != value:
-                            self.routing_strategy_init(
-                                routing_strategy=value,
-                                routing_strategy_args=kwargs.get(
-                                    "routing_strategy_args", {}
-                                ),
-                            )
+                            if value == "lar1":
+                                from litellm.router_strategy.lar1_routing import (
+                                    apply_lar1_routing_strategy,
+                                )
+
+                                apply_lar1_routing_strategy(
+                                    self,
+                                    kwargs.get("routing_strategy_args"),
+                                )
+                            else:
+                                self.routing_strategy_init(
+                                    routing_strategy=value,
+                                    routing_strategy_args=kwargs.get(
+                                        "routing_strategy_args", {}
+                                    ),
+                                )
                             rebuild_routing_groups = True
+                    elif var == "routing_strategy_args":
+                        relink_lar1_from_args = True
                     setattr(self, var, value)
             else:
                 verbose_router_logger.debug("Setting {} is not allowed".format(var))
 
+        if (
+            relink_lar1_from_args
+            and self._normalize_strategy(self.routing_strategy) == "lar1"
+        ):
+            from litellm.router_strategy.lar1_routing import apply_lar1_routing_strategy
+
+            apply_lar1_routing_strategy(self, self.routing_strategy_args)
+
         if rebuild_routing_groups:
             self._init_routing_groups(self._routing_groups_input)
         verbose_router_logger.debug(f"Updated Router settings: {self.get_settings()}")
@@ -12189,6 +12219,11 @@ class Router:
             CustomRoutingStrategy.async_get_available_deployment,
         )
 
+    def _reset_custom_routing_strategy(self) -> None:
+        for attr in ("get_available_deployment", "async_get_available_deployment"):
+            if attr in self.__dict__:
+                delattr(self, attr)
+
     def flush_cache(self):
         litellm.cache = None
         self.cache.flush_cache()
diff --git a/litellm/router_strategy/lar1_routing.py b/litellm/router_strategy/lar1_routing.py
new file mode 100644
index 00000000000..31aa5a96bad
--- /dev/null
+++ b/litellm/router_strategy/lar1_routing.py
@@ -0,0 +1,192 @@
+"""
+LAR-1 Semantic Routing Strategy
+
+Routes requests based on agent confidence level (LAR-1 protocol).
+Thresholds are configurable via routing_strategy_args in router config.
+
+LAR-1 metadata passed via request_kwargs["metadata"]["lar1"]
+"""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import TYPE_CHECKING, Optional, Union
+
+from pydantic import ValidationError
+
+from litellm._logging import verbose_router_logger
+from litellm.router import CustomRoutingStrategyBase
+from litellm.types.lar1 import LAR1Metadata, LAR1Time
+
+if TYPE_CHECKING:
+    from litellm.router import Router
+
+DEFAULT_THRESHOLDS: dict[str, float] = {"low": 0.3, "medium": 0.5, "high": 0.7}
+
+
+def _coerce_threshold(value: object, default: float) -> float:
+    if isinstance(value, (int, float)):
+        return float(value)
+    return default
+
+
+def lar1_thresholds_from_args(
+    routing_strategy_args: Optional[Mapping[str, object]] = None,
+) -> dict[str, float]:
+    args = routing_strategy_args or {}
+    return {
+        "low": _coerce_threshold(
+            args.get("confidence_threshold_low"), DEFAULT_THRESHOLDS["low"]
+        ),
+        "medium": _coerce_threshold(
+            args.get("confidence_threshold_medium"), DEFAULT_THRESHOLDS["medium"]
+        ),
+        "high": _coerce_threshold(
+            args.get("confidence_threshold_high"), DEFAULT_THRESHOLDS["high"]
+        ),
+    }
+
+
+def apply_lar1_routing_strategy(
+    router: Router,
+    routing_strategy_args: Optional[Mapping[str, object]] = None,
+) -> None:
+    strategy = LAR1RoutingStrategy(
+        router_instance=router,
+        thresholds=lar1_thresholds_from_args(routing_strategy_args),
+    )
+    router.routing_strategy = "lar1"
+    router.set_custom_routing_strategy(strategy)
+
+
+def _normalize_thresholds(thresholds: Optional[dict[str, float]]) -> dict[str, float]:
+    merged = {**DEFAULT_THRESHOLDS, **(thresholds or {})}
+    low = merged["low"]
+    medium = merged["medium"]
+    high = merged["high"]
+    if not (0 < low < medium < high < 1):
+        raise ValueError(
+            "LAR-1 thresholds must satisfy 0 < low < medium < high < 1, "
+            f"got low={low}, medium={medium}, high={high}"
+        )
+    return merged
+
+
+def _parse_lar1_metadata(request_kwargs: dict) -> LAR1Metadata:
+    lar1_raw = request_kwargs.get("metadata", {}).get("lar1", {})
+    if not isinstance(lar1_raw, dict):
+        verbose_router_logger.warning(
+            f"[LAR-1] Invalid lar1 metadata type: {type(lar1_raw).__name__}. Using defaults"
+        )
+        return LAR1Metadata()
+    try:
+        return LAR1Metadata.model_validate(lar1_raw)
+    except ValidationError as exc:
+        verbose_router_logger.warning(
+            f"[LAR-1] Invalid lar1 metadata: {exc}. Using defaults"
+        )
+        return LAR1Metadata()
+
+
+class LAR1RoutingStrategy(CustomRoutingStrategyBase):
+    def __init__(
+        self,
+        router_instance: Optional[Router] = None,
+        thresholds: Optional[dict[str, float]] = None,
+    ):
+        self._router = router_instance
+        self.thresholds = _normalize_thresholds(thresholds)
+
+    async def async_get_available_deployment(
+        self,
+        model: str,
+        messages: Optional[list[dict[str, str]]] = None,
+        input: Optional[Union[str, list]] = None,
+        specific_deployment: Optional[bool] = False,
+        request_kwargs: Optional[dict] = None,
+    ):
+        if request_kwargs is None:
+            request_kwargs = {}
+        if self._router is None:
+            return None
+
+        lar1 = _parse_lar1_metadata(request_kwargs)
+        confidence = lar1.confidence
+        evidence = tuple(e.value for e in lar1.evidence)
+        time_dim = lar1.time.value
+
+        healthy = await self._router.async_get_healthy_deployments(
+            model=model,
+            request_kwargs=request_kwargs,
+            messages=messages,
+            input=input,
+            specific_deployment=specific_deployment,
+        )
+        if isinstance(healthy, dict):
+            return healthy
+
+        if not healthy:
+            return None
+
+        target = self._classify_request(confidence, evidence, time_dim)
+        selected, exact_match = self._select_deployment(target, healthy)
+
+        if selected is None:
+            return None
+        if exact_match:
+            verbose_router_logger.info(f"[LAR-1] confidence={confidence} -> {target}")
+        else:
+            actual_type = selected.get("model_info", {}).get("type", "unknown")
+            verbose_router_logger.warning(
+                f"[LAR-1] No deployment for type '{target}', "
+                f"fallback to deployment type '{actual_type}'"
+            )
+        return selected
+
+    def _classify_request(
+        self,
+        confidence: float,
+        evidence: tuple[str, ...],
+        time_dim: str,
+    ) -> str:
+        if "UNVERIFIED" in evidence:
+            return "cloud-smart"
+
+        if time_dim == LAR1Time.MEM.value:
+            return "cloud-fast"
+
+        t = self.thresholds
+        if confidence < t["low"]:
+            return "cloud-smart"
+        if confidence < t["medium"]:
+            return "cloud-fast"
+        if confidence < t["high"]:
+            return "local"
+        return "deep"
+
+    def _select_deployment(
+        self,
+        target_type: str,
+        deployments: list[dict],
+    ) -> tuple[Optional[dict], bool]:
+        if not deployments:
+            return None, False
+
+        for deployment in deployments:
+            if not isinstance(deployment, dict):
+                continue
+            model_type = deployment.get("model_info", {}).get("type", "")
+            if model_type == target_type:
+                return deployment, True
+
+        for deployment in deployments:
+            if isinstance(deployment, dict):
+                return deployment, False
+
+        return None, False
+
+    def get_available_deployment(self, *args, **kwargs):
+        raise NotImplementedError(
+            "LAR-1 routing only supports async routing. "
+            "Enable async_only_mode on the router or use acompletion."
+        )
diff --git a/litellm/router_utils/fallback_event_handlers.py b/litellm/router_utils/fallback_event_handlers.py
index f0edc7fc9db..891d80d785a 100644
--- a/litellm/router_utils/fallback_event_handlers.py
+++ b/litellm/router_utils/fallback_event_handlers.py
@@ -72,7 +72,7 @@ def get_fallback_model_group(
             elif list(item.keys())[0] == "*":  # check generic fallback
                 generic_fallback_idx = idx
         elif isinstance(item, str):
-            fallback_model_group = [fallbacks.pop(idx)]  # returns single-item list
+            fallback_model_group = [item]
     ## if none, check for generic fallback
     if fallback_model_group is None:
         if stripped_model_fallback is not None:
diff --git a/litellm/types/lar1.py b/litellm/types/lar1.py
new file mode 100644
index 00000000000..5998b665ece
--- /dev/null
+++ b/litellm/types/lar1.py
@@ -0,0 +1,39 @@
+from enum import Enum
+
+from pydantic import BaseModel, Field
+
+
+class LAR1Act(str, Enum):
+    INF = "INF"
+    OBS = "OBS"
+    RET = "RET"
+    GEN = "GEN"
+
+
+class LAR1Time(str, Enum):
+    NOW = "NOW"
+    MEM = "MEM"
+    CTX = "CTX"
+    PRE = "PRE"
+
+
+class LAR1Mind(str, Enum):
+    REF = "REF"
+    REC = "REC"
+    HYP = "HYP"
+    ACT = "ACT"
+
+
+class LAR1Evidence(str, Enum):
+    SYNTH = "SYNTH"
+    RETRIEVED = "RETRIEVED"
+    UNVERIFIED = "UNVERIFIED"
+    CONFIRMED = "CONFIRMED"
+
+
+class LAR1Metadata(BaseModel):
+    act: LAR1Act = LAR1Act.INF
+    time: LAR1Time = LAR1Time.NOW
+    mind: LAR1Mind = LAR1Mind.REF
+    confidence: float = Field(default=0.5, ge=0.0, le=1.0)
+    evidence: list[LAR1Evidence] = []
diff --git a/litellm/types/rerank.py b/litellm/types/rerank.py
index d2c252a1e92..376d6f66603 100644
--- a/litellm/types/rerank.py
+++ b/litellm/types/rerank.py
@@ -19,6 +19,10 @@ class RerankRequest(BaseModel):
     return_documents: Optional[bool] = None
     max_chunks_per_doc: Optional[int] = None
     max_tokens_per_doc: Optional[int] = None
+    # Optional task/query instruction passed through to providers that support it
+    # (e.g. hosted vLLM / Qwen3-Reranker, DeepInfra). Omitted from the outgoing
+    # request when None, so this is fully backward-compatible.
+    instruction: Optional[str] = None
 
 
 class OptionalRerankParams(TypedDict, total=False):
@@ -29,6 +33,7 @@ class OptionalRerankParams(TypedDict, total=False):
     return_documents: Optional[bool]
     max_chunks_per_doc: Optional[int]
     max_tokens_per_doc: Optional[int]
+    instruction: Optional[str]
 
 
 class RerankBilledUnits(TypedDict, total=False):
diff --git a/litellm/types/utils.py b/litellm/types/utils.py
index c3f99b1d18b..44c4ee3d05c 100644
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -2446,7 +2446,7 @@ class ImageResponse(OpenAIImageResponse, BaseLiteLLMOpenAIResponseObject):
 
 class TranscriptionUsageDurationObject(BaseModel):
     type: Literal["duration"]
-    seconds: int
+    seconds: float
 
 
 class TranscriptionUsageInputTokenDetailsObject(BaseModel):
diff --git a/litellm/utils.py b/litellm/utils.py
index e0aa8575473..cfff7e914c6 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -5854,6 +5854,9 @@ def _is_potential_model_name_in_model_cost(
     )
 
 
+_ABOVE_THRESHOLD_COST_KEY = re.compile(r"_above_\d+k?_tokens$")
+
+
 def _get_model_info_helper(
     model: str,
     custom_llm_provider: Optional[str] = None,
@@ -6031,7 +6034,7 @@ def _get_model_info_helper(
                 )
                 _output_cost_per_token = 0
 
-            return ModelInfoBase(
+            returned_model_info = ModelInfoBase(
                 key=key,
                 max_tokens=_model_info.get("max_tokens", None),
                 max_input_tokens=_model_info.get("max_input_tokens", None),
@@ -6248,6 +6251,13 @@ def _get_model_info_helper(
                 uses_embed_content=_model_info.get("uses_embed_content", None),
                 supports_image_size=_model_info.get("supports_image_size", None),
             )
+            for cost_key, cost_value in _model_info.items():
+                if (
+                    cost_key not in returned_model_info
+                    and _ABOVE_THRESHOLD_COST_KEY.search(cost_key) is not None
+                ):
+                    returned_model_info[cost_key] = cost_value  # type: ignore[literal-required]
+            return returned_model_info
     except Exception as e:
         verbose_logger.debug(f"Error getting model info: {e}")
         raise Exception(
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index a174c1b5efd..5d2ed4244e0 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -583,6 +583,15 @@
         "output_cost_per_token": 0.0,
         "output_vector_size": 1536
     },
+    "amazon.titan-embed-g1-text-02": {
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1536
+    },
     "amazon.titan-embed-text-v2:0": {
         "input_cost_per_token": 2e-08,
         "litellm_provider": "bedrock",
@@ -22570,7 +22579,7 @@
         "input_cost_per_token_batches": 3.75e-07,
         "input_cost_per_token_priority": 1.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -22618,7 +22627,7 @@
         "input_cost_per_token_batches": 3.75e-07,
         "input_cost_per_token_priority": 1.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -22664,7 +22673,7 @@
         "input_cost_per_token_flex": 1e-07,
         "input_cost_per_token_batches": 1e-07,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -22709,7 +22718,7 @@
         "input_cost_per_token_flex": 1e-07,
         "input_cost_per_token_batches": 1e-07,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -22750,9 +22759,9 @@
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 272000,
-        "max_tokens": 272000,
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,
@@ -22786,9 +22795,9 @@
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 272000,
-        "max_tokens": 272000,
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,
@@ -30087,6 +30096,22 @@
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
+    "openrouter/z-ai/glm-5.1": {
+        "input_cost_per_token": 1.05e-06,
+        "output_cost_per_token": 3.5e-06,
+        "cache_read_input_token_cost": 5.25e-07,
+        "cache_creation_input_token_cost": 0.0,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 202752,
+        "max_output_tokens": 65535,
+        "max_tokens": 65535,
+        "mode": "chat",
+        "source": "https://openrouter.ai/z-ai/glm-5.1",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "openrouter/minimax/minimax-m2.1": {
         "input_cost_per_token": 2.7e-07,
         "output_cost_per_token": 1.2e-06,
@@ -31586,13 +31611,13 @@
         "output_cost_per_token": 0.0
     },
     "sambanova/MiniMax-M2.7": {
-        "input_cost_per_token": 3e-07,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "sambanova",
-        "max_input_tokens": 204800,
+        "max_input_tokens": 196608,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token": 2.4e-06,
         "source": "https://cloud.sambanova.ai/plans/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -31609,6 +31634,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/DeepSeek-R1-Distill-Llama-70B": {
+        "deprecation_date": "2026-03-20",
         "input_cost_per_token": 7e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 131072,
@@ -31619,6 +31645,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/DeepSeek-V3-0324": {
+        "deprecation_date": "2026-04-14",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "sambanova",
         "max_input_tokens": 32768,
@@ -31649,6 +31676,7 @@
         "supports_vision": true
     },
     "sambanova/Llama-4-Scout-17B-16E-Instruct": {
+        "deprecation_date": "2025-06-19",
         "input_cost_per_token": 4e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 8192,
@@ -31665,6 +31693,7 @@
         "supports_tool_choice": true
     },
     "sambanova/Meta-Llama-3.1-405B-Instruct": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31678,6 +31707,7 @@
         "supports_tool_choice": true
     },
     "sambanova/Meta-Llama-3.1-8B-Instruct": {
+        "deprecation_date": "2026-04-14",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31691,6 +31721,7 @@
         "supports_tool_choice": true
     },
     "sambanova/Meta-Llama-3.2-1B-Instruct": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 4e-08,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31701,6 +31732,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/Meta-Llama-3.2-3B-Instruct": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 8e-08,
         "litellm_provider": "sambanova",
         "max_input_tokens": 4096,
@@ -31724,6 +31756,7 @@
         "supports_tool_choice": true
     },
     "sambanova/Meta-Llama-Guard-3-8B": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31734,6 +31767,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/QwQ-32B": {
+        "deprecation_date": "2025-06-25",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 16384,
@@ -31744,6 +31778,7 @@
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
     "sambanova/Qwen2-Audio-7B-Instruct": {
+        "deprecation_date": "2025-06-19",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 4096,
@@ -31755,6 +31790,7 @@
         "supports_audio_input": true
     },
     "sambanova/Qwen3-32B": {
+        "deprecation_date": "2026-04-06",
         "input_cost_per_token": 4e-07,
         "litellm_provider": "sambanova",
         "max_input_tokens": 8192,
@@ -31768,9 +31804,9 @@
         "supports_tool_choice": true
     },
     "sambanova/DeepSeek-V3.1": {
-        "max_tokens": 32768,
-        "max_input_tokens": 32768,
-        "max_output_tokens": 32768,
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
         "input_cost_per_token": 3e-06,
         "output_cost_per_token": 4.5e-06,
         "litellm_provider": "sambanova",
@@ -31784,13 +31820,36 @@
         "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
+        "input_cost_per_token": 2.2e-07,
+        "output_cost_per_token": 5.9e-07,
+        "litellm_provider": "sambanova",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "source": "https://cloud.sambanova.ai/plans/pricing"
+    },
+    "sambanova/DeepSeek-V3.2": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
         "input_cost_per_token": 3e-06,
         "output_cost_per_token": 4.5e-06,
         "litellm_provider": "sambanova",
         "mode": "chat",
         "supports_function_calling": true,
         "supports_tool_choice": true,
-        "supports_reasoning": true,
+        "source": "https://cloud.sambanova.ai/plans/pricing"
+    },
+    "sambanova/gemma-4-31B-it": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 1.15e-06,
+        "litellm_provider": "sambanova",
+        "mode": "chat",
+        "supports_vision": true,
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
       "snowflake/claude-3-5-sonnet": {
@@ -38121,6 +38180,21 @@
         "supports_tool_choice": true,
         "source": "https://docs.z.ai/guides/overview/pricing"
     },
+    "zai/glm-5.1": {
+        "cache_creation_input_token_cost": 0,
+        "cache_read_input_token_cost": 2.6e-07,
+        "input_cost_per_token": 1.4e-06,
+        "output_cost_per_token": 4.4e-06,
+        "litellm_provider": "zai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
     "zai/glm-5-code": {
         "cache_creation_input_token_cost": 0,
         "cache_read_input_token_cost": 3e-07,
@@ -38151,6 +38225,21 @@
         "supports_tool_choice": true,
         "source": "https://docs.z.ai/guides/overview/pricing"
     },
+    "zai/glm-4.7-flash": {
+        "cache_creation_input_token_cost": 0,
+        "cache_read_input_token_cost": 0,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0,
+        "litellm_provider": "zai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
     "zai/glm-4.6": {
         "cache_creation_input_token_cost": 0,
         "cache_read_input_token_cost": 1.1e-07,
diff --git a/tests/litellm/llms/deepseek/chat/test_deepseek_chat_transformation.py b/tests/litellm/llms/deepseek/chat/test_deepseek_chat_transformation.py
index a2f45e7188b..66d7e0bcbf9 100644
--- a/tests/litellm/llms/deepseek/chat/test_deepseek_chat_transformation.py
+++ b/tests/litellm/llms/deepseek/chat/test_deepseek_chat_transformation.py
@@ -166,3 +166,24 @@ class TestDeepSeekThinkingParams:
         )
 
         assert "thinking" not in result
+
+    def test_drop_unsupported_tools_removes_dangling_tool_choice(self):
+        optional_params = {
+            "tools": [
+                {"type": "namespace", "name": "local_shell"},
+                {"type": "function", "function": {"name": "get_weather"}},
+            ],
+            "tool_choice": {
+                "type": "function",
+                "function": {"name": "local_shell"},
+            },
+            "parallel_tool_calls": True,
+        }
+
+        result = self.config._drop_unsupported_tools(optional_params)
+
+        assert result["tools"] == [
+            {"type": "function", "function": {"name": "get_weather"}}
+        ]
+        assert "tool_choice" not in result
+        assert result["parallel_tool_calls"] is True
diff --git a/tests/llm_translation/test_bedrock_embedding.py b/tests/llm_translation/test_bedrock_embedding.py
index 92c22f582d9..2bc4192833b 100644
--- a/tests/llm_translation/test_bedrock_embedding.py
+++ b/tests/llm_translation/test_bedrock_embedding.py
@@ -34,6 +34,11 @@ img_base_64 = "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAGQAAABkBAMAAACCzIh
             "text",
             titan_embedding_response,
         ),  # V2 text model
+        (
+            "bedrock/amazon.titan-embed-g1-text-02",
+            "text",
+            titan_embedding_response,
+        ),  # G1 text model
         (
             "bedrock/amazon.titan-embed-image-v1",
             "image",
@@ -459,3 +464,13 @@ def test_bedrock_embedding_region_bug_reproduction():
             os.environ["AWS_REGION_NAME"] = original_region_name
         else:
             os.environ.pop("AWS_REGION_NAME", None)
+
+
+def test_bedrock_titan_g1_text_02_model_info():
+    """Test that amazon.titan-embed-g1-text-02 has correct pricing metadata"""
+    model_info = litellm.get_model_info("amazon.titan-embed-g1-text-02")
+    assert model_info is not None, "Model info should not be None"
+    assert model_info["litellm_provider"] == "bedrock"
+    assert model_info["mode"] == "embedding"
+    assert model_info["input_cost_per_token"] == 1e-07
+    assert model_info["max_input_tokens"] == 8192
diff --git a/tests/llm_translation/test_llm_response_utils/test_convert_dict_to_chat_completion.py b/tests/llm_translation/test_llm_response_utils/test_convert_dict_to_chat_completion.py
index 4d67f1e426a..5683d973ac9 100644
--- a/tests/llm_translation/test_llm_response_utils/test_convert_dict_to_chat_completion.py
+++ b/tests/llm_translation/test_llm_response_utils/test_convert_dict_to_chat_completion.py
@@ -1627,7 +1627,12 @@ class TestMissingChoicesGuard:
         assert "no 'choices'" in exc_info.value.message
 
     def test_convert_to_model_response_object_empty_choices_raises_api_error(self):
-        """Empty choices list raises APIError."""
+        """Empty choices list raises APIError, same as missing/null choices.
+
+        Provider-specific repair (e.g. github_copilot synthesizing choices for
+        Anthropic-native responses) happens before this guard, in the provider
+        config; the core utility keeps treating empty choices as an error.
+        """
         from litellm.exceptions import APIError
 
         response_object = {
@@ -1683,7 +1688,9 @@ class TestMissingChoicesGuard:
 
         assert "no 'choices'" in exc_info.value.message
 
-    def test_convert_to_model_response_object_stream_true_no_choices_raises_api_error(self):
+    def test_convert_to_model_response_object_stream_true_no_choices_raises_api_error(
+        self,
+    ):
         """Missing choices via stream=True path raises APIError when generator is consumed."""
         from litellm.exceptions import APIError
 
@@ -2475,6 +2482,13 @@ class TestConvertToModelResponseObjectCompletion:
     def test_model_response_none_raises(self):
         with pytest.raises(Exception):
             convert_to_model_response_object(
-                response_object={"choices": [{"message": {"content": "hi", "role": "assistant"}, "finish_reason": "stop"}]},
+                response_object={
+                    "choices": [
+                        {
+                            "message": {"content": "hi", "role": "assistant"},
+                            "finish_reason": "stop",
+                        }
+                    ]
+                },
                 model_response_object=None,
             )
diff --git a/tests/local_testing/test_router_custom_routing.py b/tests/local_testing/test_router_custom_routing.py
index 698ccac10dc..3ebd79a7b2a 100644
--- a/tests/local_testing/test_router_custom_routing.py
+++ b/tests/local_testing/test_router_custom_routing.py
@@ -80,6 +80,31 @@ class CustomRoutingStrategy(CustomRoutingStrategyBase):
         pass
 
 
+def test_reset_custom_routing_strategy():
+    """
+    Setting a custom routing strategy installs instance-level overrides for
+    get_available_deployment / async_get_available_deployment. Re-initializing the
+    routing strategy must clear them so the class implementations are used again.
+    """
+    router = _create_router()
+    router.set_custom_routing_strategy(CustomRoutingStrategy(router))
+
+    assert "get_available_deployment" in router.__dict__
+    assert "async_get_available_deployment" in router.__dict__
+
+    router._reset_custom_routing_strategy()
+
+    assert "get_available_deployment" not in router.__dict__
+    assert "async_get_available_deployment" not in router.__dict__
+    assert (
+        router.async_get_available_deployment.__func__
+        is Router.async_get_available_deployment
+    )
+
+    # idempotent: resetting again when nothing is overridden must not raise
+    router._reset_custom_routing_strategy()
+
+
 @pytest.mark.asyncio
 async def test_custom_routing():
     litellm.set_verbose = True
diff --git a/tests/test_litellm/integrations/focus/test_mavvrik_destination.py b/tests/test_litellm/integrations/focus/test_mavvrik_destination.py
index 797238ae238..574c6186e07 100644
--- a/tests/test_litellm/integrations/focus/test_mavvrik_destination.py
+++ b/tests/test_litellm/integrations/focus/test_mavvrik_destination.py
@@ -2,8 +2,8 @@
 
 from __future__ import annotations
 
-from datetime import datetime, timezone
-from unittest.mock import AsyncMock, MagicMock, patch
+from datetime import datetime, timedelta, timezone
+from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
@@ -34,6 +34,12 @@ def _dest(**overrides) -> FocusMavvrikDestination:
     return FocusMavvrikDestination(prefix="mavvrik_focus_exports", config=config)
 
 
+def _patch_resp(status: int = 204) -> MagicMock:
+    r = MagicMock()
+    r.status_code = status
+    return r
+
+
 def test_missing_api_key_raises():
     with pytest.raises(ValueError, match="MAVVRIK_API_KEY"):
         FocusMavvrikDestination(
@@ -83,11 +89,27 @@ def test_initializes_with_not_registered():
 
 
 @pytest.mark.asyncio
-async def test_deliver_skips_empty_content():
+async def test_deliver_skips_upload_but_advances_marker_for_empty_content():
     dest = _dest()
+
+    register_resp = MagicMock()
+    register_resp.status_code = 200
+    register_resp.json.return_value = {"metricsMarker": 0}
+
+    patch_resp = _patch_resp(204)
+
+    mock_http = MagicMock()
+    mock_http.client = MagicMock()
+    mock_http.client.request = AsyncMock(side_effect=[register_resp, patch_resp])
+    dest._http = mock_http
+
     await dest.deliver(content=b"", time_window=_make_window(), filename="usage.csv")
-    # _registered still False — _ensure_registered was never called
-    assert dest._registered is False
+
+    assert dest._registered is True
+    assert mock_http.client.request.call_count == 2
+    patch_call = mock_http.client.request.call_args_list[1]
+    assert patch_call.kwargs["method"] == "PATCH"
+    assert "metricsMarker" in patch_call.kwargs["json"]
 
 
 @pytest.mark.asyncio
@@ -112,9 +134,7 @@ async def test_large_content_uploads_in_multiple_chunks():
 
     signed_url_resp = MagicMock()
     signed_url_resp.status_code = 200
-    signed_url_resp.json.return_value = {
-        "url": "https://storage.googleapis.com/upload?sig=x"
-    }
+    signed_url_resp.json.return_value = {"url": "https://storage.googleapis.com/upload?sig=x"}
 
     init_resp = MagicMock()
     init_resp.status_code = 200
@@ -127,6 +147,8 @@ async def test_large_content_uploads_in_multiple_chunks():
     chunk2_resp = MagicMock()
     chunk2_resp.status_code = 200
 
+    patch_resp = _patch_resp(204)
+
     mock_http = MagicMock()
     mock_http.client = MagicMock()
     mock_http.client.request = AsyncMock(
@@ -136,6 +158,7 @@ async def test_large_content_uploads_in_multiple_chunks():
             init_resp,
             chunk1_resp,
             chunk2_resp,
+            patch_resp,
         ]
     )
     dest._http = mock_http
@@ -152,15 +175,20 @@ async def test_large_content_uploads_in_multiple_chunks():
         filename="usage.csv",
     )
 
-    # register + get_signed_url + init + 2 chunk PUTs = 5 calls
-    assert mock_http.client.request.call_count == 5
+    # register + get_signed_url + init + 2 chunk PUTs + PATCH = 6 calls
+    assert mock_http.client.request.call_count == 6
 
-    # Check Content-Range headers
-    put_calls = mock_http.client.request.call_args_list[3:]
+    # Check Content-Range headers on the chunk PUTs (calls 3 and 4)
+    put_calls = mock_http.client.request.call_args_list[3:5]
     assert "bytes" in put_calls[0].kwargs["headers"]["Content-Range"]
     assert "/*" in put_calls[0].kwargs["headers"]["Content-Range"]  # intermediate
     assert "/*" not in put_calls[1].kwargs["headers"]["Content-Range"]  # final
 
+    # Verify the PATCH call advanced metricsMarker
+    patch_call = mock_http.client.request.call_args_list[5]
+    assert patch_call.kwargs["method"] == "PATCH"
+    assert "metricsMarker" in patch_call.kwargs["json"]
+
 
 @pytest.mark.asyncio
 async def test_deliver_calls_register_get_url_and_upload():
@@ -180,12 +208,14 @@ async def test_deliver_calls_register_get_url_and_upload():
     upload_resp = MagicMock()
     upload_resp.status_code = 200
 
+    patch_resp = _patch_resp(204)
+
     mock_http = MagicMock()
     mock_http.client = MagicMock()
-    # All 4 calls go through self._http.client.request:
-    # 1. register, 2. get_signed_url, 3. GCS session init POST, 4. GCS PUT
+    # All 5 calls go through self._http.client.request:
+    # 1. register, 2. get_signed_url, 3. GCS session init POST, 4. GCS PUT, 5. PATCH marker
     mock_http.client.request = AsyncMock(
-        side_effect=[register_resp, signed_url_resp, init_resp, upload_resp]
+        side_effect=[register_resp, signed_url_resp, init_resp, upload_resp, patch_resp]
     )
     dest._http = mock_http
 
@@ -196,10 +226,14 @@ async def test_deliver_calls_register_get_url_and_upload():
     )
 
     assert dest._registered is True
-    assert mock_http.client.request.call_count == 4
+    assert mock_http.client.request.call_count == 5
     # Verify Content-Range header was set on the PUT
     put_call = mock_http.client.request.call_args_list[3]
     assert "Content-Range" in put_call.kwargs["headers"]
+    # Verify PATCH was called last with metricsMarker
+    patch_call = mock_http.client.request.call_args_list[4]
+    assert patch_call.kwargs["method"] == "PATCH"
+    assert "metricsMarker" in patch_call.kwargs["json"]
 
 
 @pytest.mark.asyncio
@@ -224,17 +258,19 @@ async def test_register_called_only_once_across_multiple_deliveries():
 
     mock_http = MagicMock()
     mock_http.client = MagicMock()
-    # First delivery:  register, get_signed_url, GCS init, GCS PUT
-    # Second delivery: get_signed_url, GCS init, GCS PUT  (register skipped)
+    # First delivery:  register, get_signed_url, GCS init, GCS PUT, PATCH
+    # Second delivery: get_signed_url, GCS init, GCS PUT, PATCH  (register skipped)
     mock_http.client.request = AsyncMock(
         side_effect=[
             register_resp,
             _signed_url_resp(),
             init_resp,
             upload_resp,
+            _patch_resp(204),
             _signed_url_resp(),
             init_resp,
             upload_resp,
+            _patch_resp(204),
         ]
     )
     dest._http = mock_http
@@ -243,8 +279,8 @@ async def test_register_called_only_once_across_multiple_deliveries():
     await dest.deliver(content=b"header\nrow1\n", time_window=window, filename="1.csv")
     await dest.deliver(content=b"header\nrow2\n", time_window=window, filename="2.csv")
 
-    # 7 total: register(1) + [get_url+init+put](2) × 2 deliveries
-    assert mock_http.client.request.call_count == 7
+    # 9 total: register(1) + [get_url+init+put+patch](4) × 2 deliveries
+    assert mock_http.client.request.call_count == 9
     # First call was register
     first_call = mock_http.client.request.call_args_list[0]
     assert first_call.kwargs["method"] == "POST"
@@ -343,9 +379,7 @@ async def test_deliver_raises_on_non_gcs_session_uri():
     signed_url_resp = MagicMock()
     signed_url_resp.status_code = 200
     # signed URL is valid GCS
-    signed_url_resp.json.return_value = {
-        "url": "https://storage.googleapis.com/upload?sig=abc"
-    }
+    signed_url_resp.json.return_value = {"url": "https://storage.googleapis.com/upload?sig=abc"}
 
     # Location header points to a non-GCS host
     init_resp = MagicMock()
@@ -355,9 +389,7 @@ async def test_deliver_raises_on_non_gcs_session_uri():
     mock_http = MagicMock()
     mock_http.client = MagicMock()
     # register, get_signed_url, GCS session init (returns bad Location)
-    mock_http.client.request = AsyncMock(
-        side_effect=[register_resp, signed_url_resp, init_resp]
-    )
+    mock_http.client.request = AsyncMock(side_effect=[register_resp, signed_url_resp, init_resp])
     dest._http = mock_http
 
     with pytest.raises(ValueError, match="GCS endpoint"):
@@ -447,10 +479,11 @@ async def test_export_window_passes_max_rows_as_limit(monkeypatch):
 
     # Mock the engine internals so _export_window runs through our new code path
     db_mock = MagicMock()
-    db_mock.get_usage_data = AsyncMock(return_value=pl.DataFrame())  # empty → no upload
+    db_mock.get_usage_data = AsyncMock(return_value=pl.DataFrame())  # empty deliver
 
     engine_mock = MagicMock()
     engine_mock._database = db_mock
+    engine_mock._destination.deliver = AsyncMock()
     logger._engine = engine_mock
 
     window = FocusTimeWindow(
@@ -545,6 +578,36 @@ async def test_run_scheduled_export_no_catchup_when_marker_is_current():
     await logger._run_scheduled_export()
 
     # Only one call — yesterday's normal run, no catch-up
+    assert db_mock.get_usage_data.call_count == 1
+    assert db_mock.get_usage_data.call_args.kwargs["start_time_utc"].date() == yesterday.date()
+
+
+@pytest.mark.asyncio
+async def test_run_scheduled_export_skips_catchup_when_marker_is_unparseable():
+    import polars as pl
+    from litellm.integrations.mavvrik_focus.mavvrik_focus_logger import (
+        MavvrikFocusLogger,
+    )
+    from litellm.integrations.focus.destinations.mavvrik_destination import (
+        FocusMavvrikDestination,
+    )
+
+    logger = MavvrikFocusLogger()
+    now = datetime.now(timezone.utc).replace(hour=0, minute=0, second=0, microsecond=0)
+    yesterday = now - timedelta(days=1)
+
+    dest_mock = MagicMock(spec=FocusMavvrikDestination)
+    dest_mock.get_metrics_marker = AsyncMock(return_value="not-a-date")
+
+    db_mock = MagicMock()
+    db_mock.get_usage_data = AsyncMock(return_value=pl.DataFrame())
+    engine_mock = MagicMock()
+    engine_mock._database = db_mock
+    engine_mock._destination = dest_mock
+    logger._engine = engine_mock
+
+    await logger._run_scheduled_export()
+
     assert db_mock.get_usage_data.call_count == 1
     assert (
         db_mock.get_usage_data.call_args.kwargs["start_time_utc"].date()
@@ -713,9 +776,7 @@ async def test_gcs_session_cancelled_on_chunk_failure():
 
     signed_url_resp = MagicMock()
     signed_url_resp.status_code = 200
-    signed_url_resp.json.return_value = {
-        "url": "https://storage.googleapis.com/upload?sig=x"
-    }
+    signed_url_resp.json.return_value = {"url": "https://storage.googleapis.com/upload?sig=x"}
 
     init_resp = MagicMock()
     init_resp.status_code = 200
@@ -749,3 +810,42 @@ async def test_gcs_session_cancelled_on_chunk_failure():
     delete_call = calls[4]
     assert delete_call.kwargs["method"] == "DELETE"
     assert "storage.googleapis.com/session" in delete_call.kwargs["url"]
+
+
+@pytest.mark.asyncio
+async def test_update_metrics_marker_raises_on_non_410_error():
+    dest = _dest()
+
+    fail_resp = MagicMock()
+    fail_resp.status_code = 500
+    fail_resp.text = "Internal Server Error"
+
+    mock_http = MagicMock()
+    mock_http.client = MagicMock()
+    mock_http.client.request = AsyncMock(return_value=fail_resp)
+    dest._http = mock_http
+
+    with pytest.raises(RuntimeError, match="failed to update metricsMarker"):
+        await dest._update_metrics_marker(1234567890)
+    assert mock_http.client.request.call_count == 1
+
+
+@pytest.mark.asyncio
+async def test_update_metrics_marker_raises_on_410():
+    """_update_metrics_marker must raise RuntimeError and reset _registered on 410."""
+    dest = _dest()
+    dest._registered = True
+
+    resp_410 = MagicMock()
+    resp_410.status_code = 410
+    resp_410.text = "Gone"
+
+    mock_http = MagicMock()
+    mock_http.client = MagicMock()
+    mock_http.client.request = AsyncMock(return_value=resp_410)
+    dest._http = mock_http
+
+    with pytest.raises(RuntimeError, match="disconnected"):
+        await dest._update_metrics_marker(1234567890)
+
+    assert dest._registered is False
diff --git a/tests/test_litellm/integrations/mavvrik_focus/test_mavvrik_focus_logger.py b/tests/test_litellm/integrations/mavvrik_focus/test_mavvrik_focus_logger.py
new file mode 100644
index 00000000000..cd21807e887
--- /dev/null
+++ b/tests/test_litellm/integrations/mavvrik_focus/test_mavvrik_focus_logger.py
@@ -0,0 +1,67 @@
+from datetime import datetime, timezone
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from litellm.integrations.focus.destinations.base import FocusTimeWindow
+from litellm.integrations.mavvrik_focus.mavvrik_focus_logger import MavvrikFocusLogger
+
+
+class _Frame:
+    def __init__(self, *, empty: bool) -> None:
+        self._empty = empty
+
+    def __len__(self) -> int:
+        return 0 if self._empty else 1
+
+    def is_empty(self) -> bool:
+        return self._empty
+
+
+def _window() -> FocusTimeWindow:
+    return FocusTimeWindow(
+        start_time=datetime(2026, 1, 1, tzinfo=timezone.utc),
+        end_time=datetime(2026, 1, 2, tzinfo=timezone.utc),
+        frequency="daily",
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    ("data_empty", "normalized_empty", "serialized_payload"),
+    (
+        (True, False, b"not-used"),
+        (False, True, b"not-used"),
+        (False, False, b""),
+    ),
+)
+async def test_export_window_delivers_empty_payload_for_empty_export(
+    data_empty: bool,
+    normalized_empty: bool,
+    serialized_payload: bytes,
+) -> None:
+    database = MagicMock()
+    database.get_usage_data = AsyncMock(return_value=_Frame(empty=data_empty))
+    transformer = MagicMock()
+    transformer.transform.return_value = _Frame(empty=normalized_empty)
+    serializer = MagicMock()
+    serializer.serialize.return_value = serialized_payload
+    destination = MagicMock()
+    destination.deliver = AsyncMock()
+    engine = MagicMock()
+    engine._database = database
+    engine._transformer = transformer
+    engine._serializer = serializer
+    engine._destination = destination
+    engine._build_filename.return_value = "metrics.csv"
+    logger = MavvrikFocusLogger()
+    logger._engine = engine
+    window = _window()
+
+    await logger._export_window(window=window, limit=None)
+
+    destination.deliver.assert_awaited_once_with(
+        content=b"",
+        time_window=window,
+        filename="metrics.csv",
+    )
diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
index a5d1934237f..72fee9bfb40 100644
--- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
@@ -384,6 +384,44 @@ def test_generic_cost_per_token_minimax_m3_above_512k_tokens():
     assert round(completion_cost, 10) == round(expected_completion, 10)
 
 
+def test_generic_cost_per_token_honors_non_standard_above_threshold():
+    """Regression for #30344: get_model_info must keep arbitrary
+    input/output_cost_per_token_above_<N>_tokens thresholds, not only the hard-coded
+    128k/200k/272k/512k set, so a custom tier boundary is applied past its limit."""
+    model = "litellm-test-non-standard-tier"
+    custom_llm_provider = "openai"
+    litellm.register_model(
+        {
+            model: {
+                "litellm_provider": custom_llm_provider,
+                "mode": "chat",
+                "input_cost_per_token": 1e-6,
+                "output_cost_per_token": 2e-6,
+                "input_cost_per_token_above_500k_tokens": 9e-6,
+                "output_cost_per_token_above_500k_tokens": 18e-6,
+            }
+        }
+    )
+
+    try:
+        prompt_tokens = 600000
+        completion_tokens = 1000
+        usage = Usage(
+            prompt_tokens=prompt_tokens,
+            completion_tokens=completion_tokens,
+            total_tokens=prompt_tokens + completion_tokens,
+        )
+        prompt_cost, completion_cost = generic_cost_per_token(
+            model=model,
+            usage=usage,
+            custom_llm_provider=custom_llm_provider,
+        )
+        assert round(prompt_cost, 10) == round(9e-6 * prompt_tokens, 10)
+        assert round(completion_cost, 10) == round(18e-6 * completion_tokens, 10)
+    finally:
+        litellm.model_cost.pop(model, None)
+
+
 def test_generic_cost_per_token_gpt55():
     """gpt-5.5: base pricing — $5/1M input, $30/1M output, $0.50/1M cached input."""
     model = "gpt-5.5"
diff --git a/tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_handler.py b/tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_handler.py
index 2fdd639e74d..f934c7184f8 100644
--- a/tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_handler.py
+++ b/tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_handler.py
@@ -74,6 +74,150 @@ def test_redacted_thinking_content_block_delta():
     assert "thinking_blocks" in model_response.choices[0].delta.provider_specific_fields
 
 
+def test_streaming_thinking_blocks_are_replayable_after_signature_delta():
+    model_response_iterator = ModelResponseIterator(
+        streaming_response=MagicMock(), sync_stream=True, json_mode=False
+    )
+    chunks = [
+        {
+            "type": "content_block_start",
+            "index": 0,
+            "content_block": {"type": "thinking", "thinking": ""},
+        },
+        {
+            "type": "content_block_delta",
+            "index": 0,
+            "delta": {"type": "thinking_delta", "thinking": "Step 1. "},
+        },
+        {
+            "type": "content_block_delta",
+            "index": 0,
+            "delta": {"type": "thinking_delta", "thinking": "Step 2."},
+        },
+        {
+            "type": "content_block_delta",
+            "index": 0,
+            "delta": {"type": "signature_delta", "signature": "sig-final"},
+        },
+    ]
+
+    parsed_chunks = [
+        model_response_iterator.chunk_parser(chunk=chunk) for chunk in chunks
+    ]
+    reasoning_content = "".join(
+        getattr(chunk.choices[0].delta, "reasoning_content", None) or ""
+        for chunk in parsed_chunks
+    )
+    thinking_blocks = tuple(
+        block
+        for chunk in parsed_chunks
+        for block in (getattr(chunk.choices[0].delta, "thinking_blocks", None) or [])
+    )
+    expected_delta_blocks = (
+        {"type": "thinking", "thinking": "Step 1. "},
+        {"type": "thinking", "thinking": "Step 2."},
+    )
+    expected_thinking_block = {
+        "type": "thinking",
+        "thinking": "Step 1. Step 2.",
+        "signature": "sig-final",
+    }
+
+    assert reasoning_content == "Step 1. Step 2."
+    assert thinking_blocks == (*expected_delta_blocks, expected_thinking_block)
+    assert parsed_chunks[1].choices[0].delta.provider_specific_fields == {
+        "thinking_blocks": [expected_delta_blocks[0]]
+    }
+    assert parsed_chunks[-1].choices[0].delta.provider_specific_fields == {
+        "thinking_blocks": [expected_thinking_block]
+    }
+
+
+def test_streaming_unsigned_thinking_deltas_keep_reasoning_content():
+    model_response_iterator = ModelResponseIterator(
+        streaming_response=MagicMock(), sync_stream=True, json_mode=False
+    )
+    chunks = [
+        {
+            "type": "content_block_start",
+            "index": 0,
+            "content_block": {"type": "thinking", "thinking": ""},
+        },
+        {
+            "type": "content_block_delta",
+            "index": 0,
+            "delta": {"type": "thinking_delta", "thinking": "Step 1. "},
+        },
+        {
+            "type": "content_block_delta",
+            "index": 0,
+            "delta": {"type": "thinking_delta", "thinking": "Step 2."},
+        },
+        {"type": "content_block_stop", "index": 0},
+    ]
+
+    parsed_chunks = [
+        model_response_iterator.chunk_parser(chunk=chunk) for chunk in chunks
+    ]
+    reasoning_content = "".join(
+        getattr(chunk.choices[0].delta, "reasoning_content", None) or ""
+        for chunk in parsed_chunks
+    )
+    thinking_blocks = tuple(
+        block
+        for chunk in parsed_chunks
+        for block in (getattr(chunk.choices[0].delta, "thinking_blocks", None) or [])
+    )
+
+    assert reasoning_content == "Step 1. Step 2."
+    assert thinking_blocks == (
+        {"type": "thinking", "thinking": "Step 1. "},
+        {"type": "thinking", "thinking": "Step 2."},
+    )
+
+
+def test_streaming_truncated_thinking_deltas_keep_reasoning_content():
+    model_response_iterator = ModelResponseIterator(
+        streaming_response=MagicMock(), sync_stream=True, json_mode=False
+    )
+    chunks = [
+        {
+            "type": "content_block_start",
+            "index": 0,
+            "content_block": {"type": "thinking", "thinking": ""},
+        },
+        {
+            "type": "content_block_delta",
+            "index": 0,
+            "delta": {"type": "thinking_delta", "thinking": "Step 1. "},
+        },
+        {
+            "type": "content_block_delta",
+            "index": 0,
+            "delta": {"type": "thinking_delta", "thinking": "Step 2."},
+        },
+    ]
+
+    parsed_chunks = [
+        model_response_iterator.chunk_parser(chunk=chunk) for chunk in chunks
+    ]
+    reasoning_content = "".join(
+        getattr(chunk.choices[0].delta, "reasoning_content", None) or ""
+        for chunk in parsed_chunks
+    )
+    thinking_blocks = tuple(
+        block
+        for chunk in parsed_chunks
+        for block in (getattr(chunk.choices[0].delta, "thinking_blocks", None) or [])
+    )
+
+    assert reasoning_content == "Step 1. Step 2."
+    assert thinking_blocks == (
+        {"type": "thinking", "thinking": "Step 1. "},
+        {"type": "thinking", "thinking": "Step 2."},
+    )
+
+
 def test_handle_json_mode_chunk_response_format_tool():
     model_response_iterator = ModelResponseIterator(
         streaming_response=MagicMock(), sync_stream=True, json_mode=True
diff --git a/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py b/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py
index 6b869076044..301bcba99f4 100644
--- a/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py
+++ b/tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py
@@ -158,6 +158,68 @@ def test_deepseek_cris():
     assert bedrock_route == "converse"
 
 
+def test_application_inference_profile_arn_routes_to_converse():
+    """
+    Regression for #18258: a bare application-inference-profile ARN passed as
+    `bedrock/arn:...` must route to converse. The ARN ends in an opaque id with
+    no provider substring, so the invoke path cannot build a provider-native
+    body and raises "Unknown provider=None". Converse needs no provider, so it
+    is the correct route.
+    """
+    route = BedrockModelInfo.get_bedrock_route(
+        model="bedrock/arn:aws:bedrock:us-west-2:123412341234:application-inference-profile/a1b2c3"
+    )
+    assert route == "converse"
+
+
+def test_explicit_invoke_prefix_wins_over_application_inference_profile_arn():
+    """
+    An explicit invoke/ prefix is respected even for an application-inference-profile
+    ARN; only the bare `bedrock/arn:...` form is auto-routed to converse. The
+    explicit invoke path remains a dead end for these ARNs (no provider can be
+    derived, so completion raises "Unknown provider=None") by design: a caller
+    that explicitly asks for invoke gets invoke. The auto-route only rescues the
+    documented bare form.
+    """
+    from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM
+
+    model = "bedrock/invoke/arn:aws:bedrock:us-west-2:123412341234:application-inference-profile/a1b2c3"
+    assert BedrockModelInfo.get_bedrock_route(model) == "invoke"
+    assert BaseAWSLLM.get_bedrock_invoke_provider(model) is None
+
+
+def test_system_defined_inference_profile_arn_still_routes_to_converse():
+    """
+    A system-defined cross-region inference-profile ARN embeds a known model, so
+    get_base_model resolves it and it already routes to converse. Guards that the
+    application-inference-profile fix does not change this working case.
+    """
+    route = BedrockModelInfo.get_bedrock_route(
+        model="bedrock/arn:aws:bedrock:us-east-1:123:inference-profile/us.anthropic.claude-3-5-sonnet-20240620-v1:0"
+    )
+    assert route == "converse"
+
+
+def test_other_opaque_arn_types_still_route_to_invoke():
+    """
+    Only application-inference-profile ARNs are auto-routed to converse. Other
+    opaque ARNs (provisioned-model, imported-model, custom-model-deployment)
+    also yield no invoke provider, but they are frequently invoke-only with
+    provider-specific body formats, so routing them to converse could break
+    them. Guards the deliberate scope against an over-broad "any opaque ARN ->
+    converse" generalization.
+    """
+    for arn_segment in (
+        "provisioned-model/abcdefgh1234",
+        "imported-model/abcdefgh1234",
+        "custom-model-deployment/abcdefgh1234",
+    ):
+        route = BedrockModelInfo.get_bedrock_route(
+            model=f"bedrock/arn:aws:bedrock:us-east-1:123412341234:{arn_segment}"
+        )
+        assert route == "invoke", f"{arn_segment} should stay on invoke route"
+
+
 def test_govcloud_cross_region_inference_prefix():
     """
     Test that GovCloud models with cross-region inference prefix (us-gov.) are parsed correctly
diff --git a/tests/test_litellm/llms/cohere/rerank/test_rerank_guardrail_handler.py b/tests/test_litellm/llms/cohere/rerank/test_rerank_guardrail_handler.py
index 88072cd7760..46c37e6af6c 100644
--- a/tests/test_litellm/llms/cohere/rerank/test_rerank_guardrail_handler.py
+++ b/tests/test_litellm/llms/cohere/rerank/test_rerank_guardrail_handler.py
@@ -2,10 +2,8 @@
 Unit tests for Cohere Rerank Guardrail Translation Handler
 """
 
-import asyncio
 import os
 import sys
-from typing import List, Optional, Tuple
 
 import pytest
 
@@ -94,6 +92,74 @@ class TestInputProcessing:
             "id": "doc2",
         }
 
+    @pytest.mark.asyncio
+    async def test_process_query_and_instruction(self):
+        """Both query and instruction are guardrailed; documents untouched"""
+        handler = CohereRerankHandler()
+        guardrail = MockGuardrail(guardrail_name="test")
+
+        data = {
+            "model": "qwen3-reranker",
+            "query": "What is machine learning?",
+            "instruction": "Rank by relevance to ML research",
+            "documents": ["Doc 1", "Doc 2"],
+        }
+
+        result = await handler.process_input_messages(data, guardrail)
+
+        # Both user-controlled text fields are scanned and written back
+        assert result["query"] == "What is machine learning? [GUARDRAILED]"
+        assert result["instruction"] == "Rank by relevance to ML research [GUARDRAILED]"
+        # Documents unchanged
+        assert result["documents"] == ["Doc 1", "Doc 2"]
+
+    @pytest.mark.asyncio
+    async def test_instruction_masked_with_pii(self):
+        """A masking guardrail rewrites instruction, not just query"""
+
+        class PIIMaskingGuardrail(CustomGuardrail):
+            async def apply_guardrail(
+                self, inputs: dict, request_data: dict, input_type: str, **kwargs
+            ) -> dict:
+                texts = inputs.get("texts", [])
+                return {"texts": [t.replace("John Doe", "[NAME_REDACTED]") for t in texts]}
+
+        handler = CohereRerankHandler()
+        guardrail = PIIMaskingGuardrail(guardrail_name="mask_pii")
+
+        data = {
+            "model": "qwen3-reranker",
+            "query": "find records",
+            "instruction": "prioritize anything authored by John Doe",
+            "documents": ["Doc 1"],
+        }
+
+        result = await handler.process_input_messages(data, guardrail)
+
+        # The sensitive value in instruction is sanitized before forwarding
+        assert "John Doe" not in result["instruction"]
+        assert "[NAME_REDACTED]" in result["instruction"]
+        assert result["documents"] == ["Doc 1"]
+
+    @pytest.mark.asyncio
+    async def test_non_string_instruction_not_scanned(self):
+        """A non-string instruction is left as-is (only strings are scanned)"""
+        handler = CohereRerankHandler()
+        guardrail = MockGuardrail(guardrail_name="test")
+
+        data = {
+            "model": "qwen3-reranker",
+            "query": "hello",
+            "instruction": 12345,  # invalid type; backend will reject it
+            "documents": ["Doc 1"],
+        }
+
+        result = await handler.process_input_messages(data, guardrail)
+
+        # Query still guardrailed; non-string instruction untouched
+        assert result["query"] == "hello [GUARDRAILED]"
+        assert result["instruction"] == 12345
+
     @pytest.mark.asyncio
     async def test_process_no_query(self):
         """Test processing when query is missing"""
diff --git a/tests/test_litellm/llms/deepseek/chat/__init__.py b/tests/test_litellm/llms/deepseek/chat/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/tests/test_litellm/llms/deepseek/chat/test_deepseek_chat_transformation.py b/tests/test_litellm/llms/deepseek/chat/test_deepseek_chat_transformation.py
new file mode 100644
index 00000000000..ec51e5d303d
--- /dev/null
+++ b/tests/test_litellm/llms/deepseek/chat/test_deepseek_chat_transformation.py
@@ -0,0 +1,103 @@
+from litellm.llms.deepseek.chat.transformation import DeepSeekChatConfig
+
+
+def _function_tool(name: str) -> dict:
+    return {
+        "type": "function",
+        "function": {"name": name, "parameters": {"type": "object"}},
+    }
+
+
+def test_drop_unsupported_tools_keeps_function_tools_only():
+    optional_params = {
+        "tools": [
+            _function_tool("shell"),
+            {"type": "namespace", "name": "container.exec"},
+            _function_tool("apply_patch"),
+        ],
+        "tool_choice": "auto",
+    }
+
+    result = DeepSeekChatConfig._drop_unsupported_tools(optional_params)
+
+    assert [tool["function"]["name"] for tool in result["tools"]] == [
+        "shell",
+        "apply_patch",
+    ]
+    assert all(tool["type"] == "function" for tool in result["tools"])
+    assert result["tool_choice"] == "auto"
+
+
+def test_drop_unsupported_tools_drops_dangling_tool_choice_when_none_survive():
+    optional_params = {
+        "tools": [{"type": "namespace", "name": "container.exec"}],
+        "tool_choice": "required",
+        "parallel_tool_calls": True,
+        "temperature": 0.2,
+    }
+
+    result = DeepSeekChatConfig._drop_unsupported_tools(optional_params)
+
+    assert "tools" not in result
+    assert "tool_choice" not in result
+    assert "parallel_tool_calls" not in result
+    assert result["temperature"] == 0.2
+
+
+def test_drop_unsupported_tools_is_noop_for_function_only():
+    optional_params = {
+        "tools": [_function_tool("shell")],
+        "tool_choice": "auto",
+    }
+
+    result = DeepSeekChatConfig._drop_unsupported_tools(optional_params)
+
+    assert result is optional_params
+
+
+def test_drop_unsupported_tools_is_noop_without_tools():
+    optional_params = {"temperature": 0.7}
+
+    result = DeepSeekChatConfig._drop_unsupported_tools(optional_params)
+
+    assert result is optional_params
+
+
+def test_transform_request_strips_unsupported_tools_from_body():
+    config = DeepSeekChatConfig()
+    body = config.transform_request(
+        model="deepseek-chat",
+        messages=[{"role": "user", "content": "hi"}],
+        optional_params={
+            "tools": [
+                _function_tool("shell"),
+                {"type": "namespace", "name": "container.exec"},
+            ],
+            "tool_choice": "auto",
+        },
+        litellm_params={},
+        headers={},
+    )
+
+    assert [tool["type"] for tool in body["tools"]] == ["function"]
+    assert body["tools"][0]["function"]["name"] == "shell"
+
+
+async def test_async_transform_request_strips_unsupported_tools_from_body():
+    config = DeepSeekChatConfig()
+    body = await config.async_transform_request(
+        model="deepseek-chat",
+        messages=[{"role": "user", "content": "hi"}],
+        optional_params={
+            "tools": [
+                _function_tool("shell"),
+                {"type": "namespace", "name": "container.exec"},
+            ],
+            "tool_choice": "auto",
+        },
+        litellm_params={},
+        headers={},
+    )
+
+    assert [tool["type"] for tool in body["tools"]] == ["function"]
+    assert body["tools"][0]["function"]["name"] == "shell"
diff --git a/tests/test_litellm/llms/github_copilot/test_github_copilot_transformation.py b/tests/test_litellm/llms/github_copilot/test_github_copilot_transformation.py
index 5673ad81551..f69ba7df938 100644
--- a/tests/test_litellm/llms/github_copilot/test_github_copilot_transformation.py
+++ b/tests/test_litellm/llms/github_copilot/test_github_copilot_transformation.py
@@ -878,3 +878,107 @@ class TestGithubCopilotTransformResponse:
                 litellm_params={},
                 encoding=None,
             )
+
+
+class TestGithubCopilotTransformParsedResponseDict:
+    """
+    Tests for GithubCopilotConfig.transform_parsed_response_dict, the hook the
+    OpenAI SDK handler calls on its parsed response. That handler bypasses
+    transform_response, so this is the seam that repairs empty-choices responses
+    from newer Copilot Claude models on the live completion path.
+
+    See: https://github.com/BerriAI/litellm/issues/30927
+    """
+
+    def test_synthesizes_choices_from_anthropic_content(self):
+        config = GithubCopilotConfig()
+
+        parsed = {
+            "id": "msg_vrtx_01",
+            "model": "claude-opus-4.8",
+            "object": "chat.completion",
+            "choices": [],
+            "content": [{"type": "text", "text": "Hello!"}],
+            "stop_reason": "end_turn",
+            "usage": {"input_tokens": 10, "output_tokens": 5},
+        }
+
+        repaired = config.transform_parsed_response_dict(parsed)
+
+        assert len(repaired["choices"]) == 1
+        choice = repaired["choices"][0]
+        assert choice["message"]["content"] == "Hello!"
+        assert choice["finish_reason"] == "stop"
+        assert repaired["usage"]["prompt_tokens"] == 10
+        assert repaired["usage"]["completion_tokens"] == 5
+        assert repaired["usage"]["total_tokens"] == 15
+
+    def test_passthrough_when_choices_present(self):
+        config = GithubCopilotConfig()
+
+        parsed = {
+            "id": "chatcmpl-1",
+            "choices": [
+                {
+                    "index": 0,
+                    "message": {"role": "assistant", "content": "ok"},
+                    "finish_reason": "stop",
+                }
+            ],
+        }
+
+        assert config.transform_parsed_response_dict(parsed) is parsed
+
+
+@patch("litellm.llms.openai.openai.OpenAIChatCompletion._get_openai_client")
+@patch(
+    "litellm.llms.openai.openai.OpenAIChatCompletion.make_sync_openai_chat_completion_request"
+)
+def test_openai_handler_repairs_github_copilot_empty_choices(
+    mock_request, mock_get_client
+):
+    """
+    The OpenAI SDK handler calls convert_to_model_response_object directly on the
+    SDK's parsed output, bypassing transform_response. convert raises APIError on
+    empty choices, so the handler must route github_copilot responses through
+    transform_parsed_response_dict first. Removing that wiring (or resolving a
+    config without the override) fails this test with APIError.
+
+    See: https://github.com/BerriAI/litellm/issues/30927
+    """
+    from litellm.llms.openai.openai import OpenAIChatCompletion
+
+    mock_get_client.return_value = MagicMock()
+
+    class _FakeSDKResponse:
+        def model_dump(self):
+            return {
+                "id": "msg_vrtx_01",
+                "model": "claude-opus-4.8",
+                "object": "chat.completion",
+                "choices": [],
+                "content": [{"type": "text", "text": "Hi there"}],
+                "stop_reason": "end_turn",
+                "usage": {"input_tokens": 12, "output_tokens": 3},
+            }
+
+    mock_request.return_value = ({}, _FakeSDKResponse())
+
+    result = OpenAIChatCompletion().completion(
+        model="claude-opus-4.8",
+        messages=[{"role": "user", "content": "Hi"}],
+        model_response=ModelResponse(),
+        timeout=60.0,
+        optional_params={},
+        litellm_params={},
+        logging_obj=MagicMock(),
+        custom_llm_provider="github_copilot",
+        client=MagicMock(),
+        api_key="gh.test-key-123456789",
+        acompletion=False,
+    )
+
+    assert isinstance(result, ModelResponse)
+    assert result.choices[0].message.content == "Hi there"
+    assert result.choices[0].finish_reason == "stop"
+    mock_request.assert_called_once()
diff --git a/tests/test_litellm/llms/hosted_vllm/test_hosted_vllm_rerank_transformation.py b/tests/test_litellm/llms/hosted_vllm/test_hosted_vllm_rerank_transformation.py
index 9e6fa608c50..6425e815db0 100644
--- a/tests/test_litellm/llms/hosted_vllm/test_hosted_vllm_rerank_transformation.py
+++ b/tests/test_litellm/llms/hosted_vllm/test_hosted_vllm_rerank_transformation.py
@@ -4,6 +4,7 @@ import sys
 import pytest
 
 from litellm.llms.hosted_vllm.rerank.transformation import HostedVLLMRerankConfig
+from litellm.rerank_api.rerank_utils import get_optional_rerank_params
 from litellm.types.rerank import (
     OptionalRerankParams,
     RerankBilledUnits,
@@ -37,6 +38,54 @@ class TestHostedVLLMRerankTransform:
         assert params["rank_fields"] == ["field1"]
         assert params["return_documents"] is True
 
+    def test_map_cohere_rerank_params_omits_instruction_when_absent(self):
+        # Backward-compat: when no instruction is supplied, it must not appear
+        # in the mapped params (and therefore not in the outgoing request body).
+        params = self.config.map_cohere_rerank_params(
+            non_default_params=None,
+            model=self.model,
+            drop_params=False,
+            query="test query",
+            documents=["doc1", "doc2"],
+        )
+        assert "instruction" not in params
+
+    def test_map_cohere_rerank_params_passes_instruction_when_set(self):
+        params = self.config.map_cohere_rerank_params(
+            non_default_params=None,
+            model=self.model,
+            drop_params=False,
+            query="test query",
+            documents=["doc1", "doc2"],
+            instruction="Rank by relevance to genomics",
+        )
+        assert params["instruction"] == "Rank by relevance to genomics"
+
+    def test_transform_request_includes_instruction_when_set(self):
+        body = self.config.transform_rerank_request(
+            model=self.model,
+            optional_rerank_params={
+                "query": "test query",
+                "documents": ["doc1", "doc2"],
+                "instruction": "Rank by relevance to genomics",
+            },
+            headers={},
+        )
+        assert body["instruction"] == "Rank by relevance to genomics"
+
+    def test_transform_request_omits_instruction_when_absent(self):
+        # exclude_none must drop the field entirely so the body matches the
+        # pre-existing (instruction-less) shape exactly.
+        body = self.config.transform_rerank_request(
+            model=self.model,
+            optional_rerank_params={
+                "query": "test query",
+                "documents": ["doc1", "doc2"],
+            },
+            headers={},
+        )
+        assert "instruction" not in body
+
     def test_map_cohere_rerank_params_raises_on_max_chunks_per_doc(self):
         with pytest.raises(
             ValueError, match="Hosted VLLM does not support max_chunks_per_doc"
@@ -74,6 +123,7 @@ class TestHostedVLLMRerankTransform:
         }
         result = self.config._transform_response(response_dict)
         assert result.id == "abc123"
+        assert result.results is not None
         assert len(result.results) == 2
         assert result.results[0]["index"] == 0
         assert result.results[0]["relevance_score"] == 0.9
@@ -94,3 +144,32 @@ class TestHostedVLLMRerankTransform:
         }
         with pytest.raises(ValueError, match="Missing required fields in the result="):
             self.config._transform_response(response_dict)
+
+
+class TestGetOptionalRerankParamsInstruction:
+    """`instruction` is threaded through get_optional_rerank_params only when set."""
+
+    def setup_method(self):
+        self.config = HostedVLLMRerankConfig()
+        self.model = "hosted-vllm-model"
+
+    def test_instruction_threaded_when_set(self):
+        params = get_optional_rerank_params(
+            rerank_provider_config=self.config,
+            model=self.model,
+            drop_params=False,
+            query="test query",
+            documents=["doc1", "doc2"],
+            instruction="Rank by relevance to genomics",
+        )
+        assert params["instruction"] == "Rank by relevance to genomics"
+
+    def test_instruction_absent_when_not_set(self):
+        params = get_optional_rerank_params(
+            rerank_provider_config=self.config,
+            model=self.model,
+            drop_params=False,
+            query="test query",
+            documents=["doc1", "doc2"],
+        )
+        assert "instruction" not in params
diff --git a/tests/test_litellm/llms/moonshot/test_moonshot_chat_transformation.py b/tests/test_litellm/llms/moonshot/test_moonshot_chat_transformation.py
index 95ade4290e9..417dd4a767c 100644
--- a/tests/test_litellm/llms/moonshot/test_moonshot_chat_transformation.py
+++ b/tests/test_litellm/llms/moonshot/test_moonshot_chat_transformation.py
@@ -305,6 +305,34 @@ class TestMoonshotConfig:
         assert len(result["messages"]) == 2
         assert result["messages"][1]["content"] == "Please select a tool to handle the current issue."
 
+    def test_tool_choice_required_does_not_mutate_input_messages(self):
+        """tool_choice='required' must not mutate the caller's messages list.
+
+        The handling appends a "select a tool" user message; building it in
+        place corrupts the caller's conversation history and makes
+        transform_request non-idempotent across retries.
+        """
+        config = MoonshotChatConfig()
+
+        messages = [{"role": "user", "content": "What's the weather like?"}]
+
+        for _ in range(2):
+            optional_params = {
+                "tool_choice": "required",
+                "tools": [{"type": "function", "function": {"name": "get_weather"}}],
+            }
+            result = config.transform_request(
+                model="moonshot-v1-8k",
+                messages=messages,
+                optional_params=optional_params,
+                litellm_params={},
+                headers={},
+            )
+            # The returned request carries the extra message.
+            assert len(result["messages"]) == 2
+            # The caller's list is untouched, so repeated calls stay idempotent.
+            assert messages == [{"role": "user", "content": "What's the weather like?"}]
+
     def test_tool_choice_non_required_preserved(self):
         """Test that non-'required' tool_choice values are preserved"""
         config = MoonshotChatConfig()
diff --git a/tests/test_litellm/llms/openai/transcriptions/test_transcription_duration_hidden.py b/tests/test_litellm/llms/openai/transcriptions/test_transcription_duration_hidden.py
index 2b287e456a1..703fa13cbc9 100644
--- a/tests/test_litellm/llms/openai/transcriptions/test_transcription_duration_hidden.py
+++ b/tests/test_litellm/llms/openai/transcriptions/test_transcription_duration_hidden.py
@@ -13,7 +13,52 @@ from litellm.cost_calculator import completion_cost
 from litellm.litellm_core_utils.llm_response_utils.convert_dict_to_response import (
     convert_to_model_response_object,
 )
-from litellm.types.utils import TranscriptionResponse
+from litellm.types.utils import (
+    TranscriptionResponse,
+    TranscriptionUsageDurationObject,
+)
+
+
+class TestDiarizedJsonUsageParsing:
+    """gpt-4o-transcribe / diarized_json returns a fractional `usage.seconds`."""
+
+    def test_fractional_duration_seconds_does_not_raise(self):
+        """
+        A diarized_json response carries usage={"type": "duration", "seconds": <float>}.
+        OpenAI specs `seconds` as a float, so a fractional value must parse cleanly
+        instead of raising and getting retried until the upstream rate-limits.
+        """
+        response_object = {
+            "text": "speaker_1: Olá",
+            "task": "transcribe",
+            "duration": 295.8,
+            "segments": [
+                {
+                    "id": "seg_001",
+                    "speaker": "speaker_1",
+                    "start": 0.0,
+                    "end": 1.0,
+                    "text": "Olá",
+                    "type": "transcript.text.segment",
+                }
+            ],
+            "usage": {"type": "duration", "seconds": 295.8},
+        }
+
+        result = convert_to_model_response_object(
+            response_object=response_object,
+            model_response_object=TranscriptionResponse(),
+            response_type="audio_transcription",
+        )
+
+        assert isinstance(result.usage, TranscriptionUsageDurationObject)
+        assert result.usage.seconds == 295.8
+
+    def test_usage_duration_object_accepts_float_seconds(self):
+        assert (
+            TranscriptionUsageDurationObject(type="duration", seconds=295.8).seconds
+            == 295.8
+        )
 
 
 class TestTranscriptionDurationNotInResponseBody:
diff --git a/tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py b/tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py
index 6d0b4509b45..de5250fc5f3 100644
--- a/tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py
+++ b/tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py
@@ -3787,3 +3787,298 @@ async def test_ui_view_spend_logs_metadata_invalid_json_falls_back_to_empty_dict
         assert body["data"][0]["metadata"] == {}
     finally:
         app.dependency_overrides.pop(ps.user_api_key_auth, None)
+
+
+class _FakeColdStorageLogger:
+    """Injectable cold storage logger that records the object key it was asked for."""
+
+    def __init__(self, payload):
+        self._payload = payload
+        self.requested_object_keys = []
+
+    async def get_proxy_server_request_from_cold_storage_with_object_key(
+        self, object_key
+    ):
+        self.requested_object_keys.append(object_key)
+        return self._payload
+
+
+def _cold_storage_handler(payload):
+    from litellm.proxy.spend_tracking.cold_storage_handler import ColdStorageHandler
+
+    logger = _FakeColdStorageLogger(payload)
+    return ColdStorageHandler(cold_storage_logger=logger), logger
+
+
+@pytest.mark.parametrize(
+    "value, expected",
+    [
+        (None, False),
+        ("", False),
+        ("   ", False),
+        ("{}", False),
+        ("[]", False),
+        ("null", False),
+        ('{"a": 1}', True),
+        ({}, False),
+        ({"a": 1}, True),
+        ([], False),
+        ([1], True),
+        (5, True),
+    ],
+)
+def test_spend_log_field_has_content(value, expected):
+    assert spend_management_endpoints._spend_log_field_has_content(value) is expected
+
+
+@pytest.mark.parametrize(
+    "metadata, expected",
+    [
+        (None, None),
+        ("{}", None),
+        ("not-json", None),
+        ({"cold_storage_object_key": ""}, None),
+        ({"cold_storage_object_key": "k/req-1.json"}, "k/req-1.json"),
+        ('{"cold_storage_object_key": "k/req-2.json"}', "k/req-2.json"),
+    ],
+)
+def test_cold_storage_object_key_from_metadata(metadata, expected):
+    assert (
+        spend_management_endpoints._cold_storage_object_key_from_metadata(metadata)
+        == expected
+    )
+
+
+@pytest.mark.asyncio
+async def test_resolve_payload_prefers_pg_and_skips_cold_storage():
+    handler, logger = _cold_storage_handler({"messages": "X", "response": "Y"})
+    row = {
+        "messages": "{}",
+        "response": '{"choices": [{"message": {"content": "hi"}}]}',
+        "proxy_server_request": "{}",
+        "metadata": {"cold_storage_object_key": "k/req.json"},
+    }
+
+    resolved = await spend_management_endpoints._resolve_request_response_payload(
+        row, cold_storage_handler=handler
+    )
+
+    assert resolved.response == '{"choices": [{"message": {"content": "hi"}}]}'
+    assert logger.requested_object_keys == []
+
+
+@pytest.mark.asyncio
+async def test_resolve_payload_fetches_from_cold_storage_when_pg_empty():
+    cold_payload = {
+        "messages": [{"role": "user", "content": "what is 2+2"}],
+        "response": {"choices": [{"message": {"content": "4"}}]},
+        "proxy_server_request": {"body": {"model": "gpt-4o-mini"}},
+    }
+    handler, logger = _cold_storage_handler(cold_payload)
+    row = {
+        "messages": "{}",
+        "response": "{}",
+        "proxy_server_request": "{}",
+        "metadata": {"cold_storage_object_key": "llm-gateway/prod/req-42.json"},
+    }
+
+    resolved = await spend_management_endpoints._resolve_request_response_payload(
+        row, cold_storage_handler=handler
+    )
+
+    assert logger.requested_object_keys == ["llm-gateway/prod/req-42.json"]
+    assert resolved.messages == cold_payload["messages"]
+    assert resolved.response == cold_payload["response"]
+    assert resolved.proxy_server_request == cold_payload["proxy_server_request"]
+
+
+@pytest.mark.asyncio
+async def test_resolve_payload_metadata_as_json_string():
+    cold_payload = {"messages": "in", "response": "out", "proxy_server_request": None}
+    handler, logger = _cold_storage_handler(cold_payload)
+    row = {
+        "messages": "{}",
+        "response": "{}",
+        "proxy_server_request": "{}",
+        "metadata": json.dumps({"cold_storage_object_key": "k/str-meta.json"}),
+    }
+
+    resolved = await spend_management_endpoints._resolve_request_response_payload(
+        row, cold_storage_handler=handler
+    )
+
+    assert logger.requested_object_keys == ["k/str-meta.json"]
+    assert resolved.response == "out"
+
+
+@pytest.mark.asyncio
+async def test_resolve_payload_no_object_key_returns_empty_without_fetch():
+    handler, logger = _cold_storage_handler({"messages": "should-not-be-used"})
+    row = {
+        "messages": "{}",
+        "response": "{}",
+        "proxy_server_request": "{}",
+        "metadata": {},
+    }
+
+    resolved = await spend_management_endpoints._resolve_request_response_payload(
+        row, cold_storage_handler=handler
+    )
+
+    assert logger.requested_object_keys == []
+    assert resolved == spend_management_endpoints.RequestResponsePayload(
+        "{}", "{}", "{}"
+    )
+
+
+@pytest.mark.asyncio
+async def test_resolve_payload_cold_storage_miss_falls_back_to_pg_values():
+    handler, logger = _cold_storage_handler(None)
+    row = {
+        "messages": "{}",
+        "response": "{}",
+        "proxy_server_request": "{}",
+        "metadata": {"cold_storage_object_key": "k/missing.json"},
+    }
+
+    resolved = await spend_management_endpoints._resolve_request_response_payload(
+        row, cold_storage_handler=handler
+    )
+
+    assert logger.requested_object_keys == ["k/missing.json"]
+    assert resolved == spend_management_endpoints.RequestResponsePayload(
+        "{}", "{}", "{}"
+    )
+
+
+@pytest.mark.asyncio
+async def test_resolve_payload_cold_storage_exception_falls_back_to_pg_values():
+    """A backend error during fetch degrades to PG values instead of bubbling a 500."""
+
+    class _RaisingLogger:
+        async def get_proxy_server_request_from_cold_storage_with_object_key(
+            self, object_key
+        ):
+            raise RuntimeError("cold storage backend unavailable")
+
+    from litellm.proxy.spend_tracking.cold_storage_handler import ColdStorageHandler
+
+    handler = ColdStorageHandler(cold_storage_logger=_RaisingLogger())
+    row = {
+        "messages": "{}",
+        "response": "{}",
+        "proxy_server_request": "{}",
+        "metadata": {"cold_storage_object_key": "k/boom.json"},
+    }
+
+    resolved = await spend_management_endpoints._resolve_request_response_payload(
+        row, cold_storage_handler=handler
+    )
+
+    assert resolved == spend_management_endpoints.RequestResponsePayload(
+        "{}", "{}", "{}"
+    )
+
+
+@pytest.mark.asyncio
+async def test_cold_storage_handler_uses_injected_logger():
+    from litellm.proxy.spend_tracking.cold_storage_handler import ColdStorageHandler
+
+    logger = _FakeColdStorageLogger({"messages": "in", "response": "out"})
+    handler = ColdStorageHandler(cold_storage_logger=logger)
+
+    result = await handler.get_proxy_server_request_from_cold_storage_with_object_key(
+        object_key="k/req.json"
+    )
+
+    assert result == {"messages": "in", "response": "out"}
+    assert logger.requested_object_keys == ["k/req.json"]
+
+
+@pytest.mark.asyncio
+async def test_cold_storage_handler_returns_none_when_no_logger_configured(monkeypatch):
+    from litellm.proxy.spend_tracking.cold_storage_handler import ColdStorageHandler
+
+    monkeypatch.setattr(litellm, "cold_storage_custom_logger", None, raising=False)
+    handler = ColdStorageHandler()
+
+    result = await handler.get_proxy_server_request_from_cold_storage_with_object_key(
+        object_key="k/req.json"
+    )
+
+    assert result is None
+
+
+@pytest.mark.asyncio
+async def test_cold_storage_handler_resolves_configured_logger_from_registry(monkeypatch):
+    from litellm.proxy.spend_tracking.cold_storage_handler import ColdStorageHandler
+
+    logger = _FakeColdStorageLogger({"messages": "from-registry"})
+    monkeypatch.setattr(litellm, "cold_storage_custom_logger", "s3_v2", raising=False)
+    monkeypatch.setattr(
+        litellm.logging_callback_manager,
+        "get_active_custom_logger_for_callback_name",
+        lambda name: logger if name == "s3_v2" else None,
+    )
+    handler = ColdStorageHandler()
+
+    result = await handler.get_proxy_server_request_from_cold_storage_with_object_key(
+        object_key="k/req.json"
+    )
+
+    assert result == {"messages": "from-registry"}
+    assert logger.requested_object_keys == ["k/req.json"]
+
+
+def test_ui_view_request_response_reads_from_cold_storage(client, monkeypatch):
+    """End-to-end: a placeholder row with a cold_storage_object_key is served from
+    cold storage through the detail endpoint."""
+    from types import SimpleNamespace
+
+    placeholder_row = {
+        "messages": "{}",
+        "response": "{}",
+        "proxy_server_request": "{}",
+        "metadata": {"cold_storage_object_key": "k/cold.json"},
+    }
+
+    async def _query_raw(_sql, *_args):
+        return [placeholder_row]
+
+    fake_prisma = SimpleNamespace(db=SimpleNamespace(query_raw=_query_raw))
+    monkeypatch.setattr("litellm.proxy.proxy_server.prisma_client", fake_prisma)
+
+    cold_logger = _FakeColdStorageLogger(
+        {
+            "messages": [{"role": "user", "content": "hi"}],
+            "response": {"choices": [{"message": {"content": "hello"}}]},
+            "proxy_server_request": None,
+        }
+    )
+    monkeypatch.setattr(litellm, "cold_storage_custom_logger", "s3_v2", raising=False)
+    monkeypatch.setattr(
+        litellm.logging_callback_manager,
+        "get_active_additional_logging_utils_from_custom_logger",
+        lambda: [],
+    )
+    monkeypatch.setattr(
+        litellm.logging_callback_manager,
+        "get_active_custom_logger_for_callback_name",
+        lambda name: cold_logger if name == "s3_v2" else None,
+    )
+
+    app.dependency_overrides[ps.user_api_key_auth] = lambda: UserAPIKeyAuth(
+        user_role=LitellmUserRoles.PROXY_ADMIN, user_id="admin_1"
+    )
+    try:
+        response = client.get(
+            "/spend/logs/ui/req-cold",
+            headers={"Authorization": "Bearer sk-test"},
+        )
+        assert response.status_code == 200
+        body = response.json()
+        assert body["messages"] == [{"role": "user", "content": "hi"}]
+        assert body["response"] == {"choices": [{"message": {"content": "hello"}}]}
+        assert cold_logger.requested_object_keys == ["k/cold.json"]
+    finally:
+        app.dependency_overrides.pop(ps.user_api_key_auth, None)
diff --git a/tests/test_litellm/router_strategy/test_lar1_routing.py b/tests/test_litellm/router_strategy/test_lar1_routing.py
new file mode 100644
index 00000000000..4710bbb6896
--- /dev/null
+++ b/tests/test_litellm/router_strategy/test_lar1_routing.py
@@ -0,0 +1,460 @@
+import pytest
+from unittest.mock import AsyncMock
+
+from litellm import Router
+from litellm.router_strategy.lar1_routing import (
+    LAR1RoutingStrategy,
+    _normalize_thresholds,
+    _parse_lar1_metadata,
+    apply_lar1_routing_strategy,
+    lar1_thresholds_from_args,
+    DEFAULT_THRESHOLDS,
+)
+
+
+def _model_list():
+    return [
+        {
+            "model_name": "agent-router",
+            "litellm_params": {
+                "model": "openai/gpt-4o",
+                "api_key": "fake-key",
+            },
+            "model_info": {"id": "cloud-smart", "type": "cloud-smart"},
+        },
+        {
+            "model_name": "agent-router",
+            "litellm_params": {
+                "model": "openai/gpt-4o-mini",
+                "api_key": "fake-key",
+            },
+            "model_info": {"id": "cloud-fast", "type": "cloud-fast"},
+        },
+        {
+            "model_name": "agent-router",
+            "litellm_params": {
+                "model": "ollama/qwythos",
+                "api_key": "fake-key",
+            },
+            "model_info": {"id": "local", "type": "local"},
+        },
+        {
+            "model_name": "agent-router",
+            "litellm_params": {
+                "model": "ollama/mythos",
+                "api_key": "fake-key",
+            },
+            "model_info": {"id": "deep", "type": "deep"},
+        },
+    ]
+
+
+def _create_test_router():
+    return Router(model_list=_model_list())
+
+
+@pytest.mark.asyncio
+async def test_low_confidence_routes_to_cloud_smart():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.2}}},
+    )
+    assert result["model_info"]["type"] == "cloud-smart"
+
+
+@pytest.mark.asyncio
+async def test_high_confidence_routes_to_deep():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.8}}},
+    )
+    assert result["model_info"]["type"] == "deep"
+
+
+@pytest.mark.asyncio
+async def test_unverified_evidence_fallback():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={
+            "metadata": {
+                "lar1": {"confidence": 0.9, "evidence": ["UNVERIFIED"]},
+            }
+        },
+    )
+    assert result["model_info"]["type"] == "cloud-smart"
+
+
+@pytest.mark.asyncio
+async def test_custom_thresholds():
+    router = _create_test_router()
+    custom_strategy = LAR1RoutingStrategy(
+        router,
+        thresholds={"low": 0.1, "medium": 0.3, "high": 0.9},
+    )
+
+    result = await custom_strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.85}}},
+    )
+    assert result["model_info"]["type"] == "local"
+
+
+@pytest.mark.asyncio
+async def test_mem_time_routes_to_cloud_fast():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={
+            "metadata": {
+                "lar1": {"confidence": 0.9, "time": "MEM"},
+            }
+        },
+    )
+    assert result["model_info"]["type"] == "cloud-fast"
+
+
+@pytest.mark.asyncio
+async def test_invalid_confidence_falls_back_to_local():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={
+            "metadata": {"lar1": {"confidence": "not-a-number"}},
+        },
+    )
+    assert result["model_info"]["type"] == "local"
+
+
+@pytest.mark.asyncio
+async def test_no_metadata_defaults_to_local():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={},
+    )
+    assert result["model_info"]["type"] == "local"
+
+
+@pytest.mark.asyncio
+async def test_router_init_with_lar1_routing_strategy():
+    router = Router(
+        model_list=_model_list(),
+        routing_strategy="lar1",
+        routing_strategy_args={
+            "confidence_threshold_low": 0.1,
+            "confidence_threshold_medium": 0.3,
+            "confidence_threshold_high": 0.9,
+        },
+    )
+
+    result = await router.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.85}}},
+    )
+    assert result["model_info"]["type"] == "local"
+    assert router.routing_strategy == "lar1"
+
+
+@pytest.mark.asyncio
+async def test_router_init_lar1_default_thresholds():
+    router = Router(model_list=_model_list(), routing_strategy="lar1")
+
+    result = await router.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.4}}},
+    )
+    assert result["model_info"]["type"] == "cloud-fast"
+    assert router.routing_strategy == "lar1"
+
+
+@pytest.mark.asyncio
+async def test_mid_confidence_routes_to_cloud_fast():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.4}}},
+    )
+    assert result["model_info"]["type"] == "cloud-fast"
+
+
+@pytest.mark.asyncio
+async def test_no_router_returns_none():
+    strategy = LAR1RoutingStrategy()
+
+    result = await strategy.async_get_available_deployment(model="agent-router")
+    assert result is None
+
+
+@pytest.mark.asyncio
+async def test_request_kwargs_none_uses_defaults():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs=None,
+    )
+    assert result["model_info"]["type"] == "local"
+
+
+@pytest.mark.asyncio
+async def test_invalid_lar1_metadata_type_uses_defaults(caplog):
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    with caplog.at_level("WARNING"):
+        result = await strategy.async_get_available_deployment(
+            model="agent-router",
+            request_kwargs={"metadata": {"lar1": "not-a-dict"}},
+        )
+
+    assert result["model_info"]["type"] == "local"
+    assert "Invalid lar1 metadata type" in caplog.text
+
+
+@pytest.mark.asyncio
+async def test_confirmed_evidence_routes_by_confidence():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={
+            "metadata": {
+                "lar1": {"confidence": 0.8, "evidence": ["CONFIRMED"]},
+            }
+        },
+    )
+    assert result["model_info"]["type"] == "deep"
+
+
+@pytest.mark.asyncio
+async def test_empty_healthy_deployments_returns_none():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+    router.async_get_healthy_deployments = AsyncMock(return_value=[])
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.8}}},
+    )
+    assert result is None
+
+
+@pytest.mark.asyncio
+async def test_specific_deployment_dict_short_circuit():
+    deployment = {
+        "model_info": {"type": "deep"},
+        "litellm_params": {"model": "ollama/mythos"},
+    }
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+    router.async_get_healthy_deployments = AsyncMock(return_value=deployment)
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        specific_deployment=True,
+        request_kwargs={},
+    )
+    assert result == deployment
+
+
+@pytest.mark.asyncio
+async def test_non_dict_healthy_deployment_returns_none():
+    router = _create_test_router()
+    strategy = LAR1RoutingStrategy(router)
+    router.async_get_healthy_deployments = AsyncMock(return_value=[None])
+
+    result = await strategy.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={},
+    )
+    assert result is None
+
+
+def test_parse_lar1_metadata_defaults_when_missing():
+    metadata = _parse_lar1_metadata({})
+    assert metadata.confidence == 0.5
+    assert metadata.time.value == "NOW"
+
+
+def test_select_deployment_empty_list():
+    strategy = LAR1RoutingStrategy()
+    selected, exact_match = strategy._select_deployment("local", [])
+    assert selected is None
+    assert exact_match is False
+
+
+def test_select_deployment_skips_non_dict_entries():
+    strategy = LAR1RoutingStrategy()
+    deployment = {"model_info": {"type": "local"}}
+    selected, exact_match = strategy._select_deployment(
+        "local",
+        ["skip-me", deployment],
+    )
+    assert selected == deployment
+    assert exact_match is True
+
+
+def test_select_deployment_fallback_uses_first_dict():
+    strategy = LAR1RoutingStrategy()
+    deployment = {"model_info": {"type": "local"}}
+    selected, exact_match = strategy._select_deployment(
+        "cloud-smart",
+        ["skip-me", deployment],
+    )
+    assert selected == deployment
+    assert exact_match is False
+
+
+def test_select_deployment_all_non_dict_returns_none():
+    strategy = LAR1RoutingStrategy()
+    selected, exact_match = strategy._select_deployment("local", ["a", None])
+    assert selected is None
+    assert exact_match is False
+
+
+def test_lar1_thresholds_from_args_uses_defaults():
+    assert lar1_thresholds_from_args({}) == DEFAULT_THRESHOLDS
+
+
+def test_lar1_thresholds_from_args_ignores_invalid_values():
+    assert lar1_thresholds_from_args(
+        {
+            "confidence_threshold_low": "bad",
+            "confidence_threshold_medium": 0.4,
+            "confidence_threshold_high": 0.8,
+        }
+    ) == {"low": 0.3, "medium": 0.4, "high": 0.8}
+
+
+@pytest.mark.asyncio
+async def test_update_settings_switches_to_lar1_routing():
+    router = Router(model_list=_model_list(), routing_strategy="simple-shuffle")
+    router.update_settings(
+        routing_strategy="lar1",
+        routing_strategy_args={
+            "confidence_threshold_low": 0.1,
+            "confidence_threshold_medium": 0.3,
+            "confidence_threshold_high": 0.9,
+        },
+    )
+
+    result = await router.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.85}}},
+    )
+    assert router.routing_strategy == "lar1"
+    assert result["model_info"]["type"] == "local"
+
+
+def test_update_settings_switching_from_lar1_restores_default_selectors():
+    router = Router(model_list=_model_list(), routing_strategy="lar1")
+
+    router.update_settings(routing_strategy="simple-shuffle")
+
+    assert router.routing_strategy == "simple-shuffle"
+    assert "get_available_deployment" not in router.__dict__
+    assert "async_get_available_deployment" not in router.__dict__
+    result = router.get_available_deployment(model="agent-router")
+    assert result["model_name"] == "agent-router"
+
+
+@pytest.mark.asyncio
+async def test_update_settings_routing_strategy_args_relinks_lar1():
+    router = Router(model_list=_model_list(), routing_strategy="lar1")
+
+    router.update_settings(
+        routing_strategy_args={
+            "confidence_threshold_low": 0.1,
+            "confidence_threshold_medium": 0.3,
+            "confidence_threshold_high": 0.9,
+        },
+    )
+
+    result = await router.async_get_available_deployment(
+        model="agent-router",
+        request_kwargs={"metadata": {"lar1": {"confidence": 0.85}}},
+    )
+    assert result["model_info"]["type"] == "local"
+
+
+def test_apply_lar1_routing_strategy_wires_custom_selector():
+    router = Router(model_list=_model_list(), routing_strategy="simple-shuffle")
+    apply_lar1_routing_strategy(router, {"confidence_threshold_high": 0.9})
+    assert router.routing_strategy == "lar1"
+    with pytest.raises(NotImplementedError, match="async routing"):
+        router.get_available_deployment(model="agent-router")
+
+
+def test_apply_lar1_invalid_thresholds_leaves_router_unchanged():
+    router = Router(model_list=_model_list(), routing_strategy="simple-shuffle")
+
+    with pytest.raises(ValueError, match="LAR-1 thresholds must satisfy"):
+        apply_lar1_routing_strategy(
+            router,
+            {
+                "confidence_threshold_low": 0.9,
+                "confidence_threshold_medium": 0.5,
+                "confidence_threshold_high": 0.7,
+            },
+        )
+
+    assert router.routing_strategy == "simple-shuffle"
+    assert "async_get_available_deployment" not in router.__dict__
+    result = router.get_available_deployment(model="agent-router")
+    assert result["model_name"] == "agent-router"
+
+
+def test_invalid_threshold_order_raises():
+    with pytest.raises(ValueError, match="LAR-1 thresholds must satisfy"):
+        _normalize_thresholds({"low": 0.5, "medium": 0.3, "high": 0.7})
+
+
+def test_get_available_deployment_raises_not_implemented():
+    strategy = LAR1RoutingStrategy()
+    with pytest.raises(NotImplementedError, match="async routing"):
+        strategy.get_available_deployment(model="agent-router")
+
+
+@pytest.mark.asyncio
+async def test_missing_target_type_falls_back_with_warning(caplog):
+    router = Router(
+        model_list=[
+            {
+                "model_name": "agent-router",
+                "litellm_params": {
+                    "model": "openai/gpt-4o",
+                    "api_key": "fake-key",
+                },
+                "model_info": {"id": "only-local", "type": "local"},
+            }
+        ]
+    )
+    strategy = LAR1RoutingStrategy(router)
+
+    with caplog.at_level("WARNING"):
+        result = await strategy.async_get_available_deployment(
+            model="agent-router",
+            request_kwargs={"metadata": {"lar1": {"confidence": 0.2}}},
+        )
+
+    assert result["model_info"]["type"] == "local"
+    assert "No deployment for type 'cloud-smart'" in caplog.text
diff --git a/tests/test_litellm/router_utils/test_fallback_event_handlers.py b/tests/test_litellm/router_utils/test_fallback_event_handlers.py
index ca647bdce55..98a34de295c 100644
--- a/tests/test_litellm/router_utils/test_fallback_event_handlers.py
+++ b/tests/test_litellm/router_utils/test_fallback_event_handlers.py
@@ -2,7 +2,10 @@ import json
 
 import pytest
 
-from litellm.router_utils.fallback_event_handlers import run_async_fallback
+from litellm.router_utils.fallback_event_handlers import (
+    get_fallback_model_group,
+    run_async_fallback,
+)
 
 
 class StreamingWrapper:
@@ -137,3 +140,16 @@ async def test_run_async_fallback_skips_original_model_group():
     )
 
     assert response._hidden_params["additional_headers"]["x-litellm-attempted-fallbacks"] == 1
+
+
+def test_get_fallback_model_group_does_not_mutate_fallbacks():
+    """A string fallback must be resolved without mutating the caller's
+    fallbacks list, which is the live router config shared across requests."""
+    fallbacks = [{"gpt-3.5-turbo": ["claude-3-haiku"]}, "gpt-4o-mini"]
+
+    fallback_model_group, _ = get_fallback_model_group(
+        fallbacks=fallbacks, model_group="unmatched-model"
+    )
+
+    assert fallback_model_group == ["gpt-4o-mini"]
+    assert fallbacks == [{"gpt-3.5-turbo": ["claude-3-haiku"]}, "gpt-4o-mini"]
diff --git a/tests/test_litellm/test_gpt_image_cost_calculator.py b/tests/test_litellm/test_gpt_image_cost_calculator.py
index 6644b1389cf..c371f7442be 100644
--- a/tests/test_litellm/test_gpt_image_cost_calculator.py
+++ b/tests/test_litellm/test_gpt_image_cost_calculator.py
@@ -381,5 +381,93 @@ class TestCompletionCostIntegration:
         assert abs(cost - expected_cost) < 1e-6, f"Expected {expected_cost}, got {cost}"
 
 
+class TestGPTImage2OutputImageTokensNoBreakdown:
+    """
+    Regression test: the OpenAI Images endpoints (/v1/images/generations and
+    /v1/images/edits) return usage with NO output token breakdown — litellm's
+    ImageUsage has no ``output_tokens_details`` field. Before the fix, the
+    generated-image OUTPUT tokens were priced at the text rate
+    (``output_cost_per_token`` = $10/1M for gpt-image-2) instead of the image rate
+    (``output_cost_per_image_token`` = $30/1M), a ~3x undercount on the dominant
+    cost component.
+    """
+
+    def test_gpt_image_2_output_priced_as_image_when_no_breakdown(self):
+        from litellm.llms.openai.image_generation.cost_calculator import (
+            cost_calculator,
+        )
+
+        # Mirrors a real gpt-image-2 /v1/images/edits response: input breakdown is
+        # present, but there is no usable output token breakdown.
+        usage = ImageUsage(
+            input_tokens=3987,
+            output_tokens=5488,
+            total_tokens=9475,
+            input_tokens_details=ImageUsageInputTokensDetails(
+                text_tokens=943,
+                image_tokens=3044,
+            ),
+        )
+
+        image_response = ImageResponse(
+            created=1234567890,
+            data=[ImageObject(b64_json="test")],
+        )
+        image_response.usage = usage
+        image_response._hidden_params = {"custom_llm_provider": "openai"}
+
+        cost = cost_calculator(
+            model="gpt-image-2",
+            image_response=image_response,
+            custom_llm_provider="openai",
+        )
+
+        # gpt-image-2 pricing:
+        #   text input:   943  * $5/1M  = 0.004715
+        #   image input:  3044 * $8/1M  = 0.024352
+        #   image output: 5488 * $30/1M = 0.164640  (NOT text output $10/1M = 0.054880)
+        expected_cost = 943 * 5e-6 + 3044 * 8e-6 + 5488 * 3e-5
+        assert abs(cost - expected_cost) < 1e-6, (
+            f"Expected {expected_cost}, got {cost}. Generated image output tokens "
+            f"are likely being priced at the text output_cost_per_token rate."
+        )
+
+    def test_gpt_image_2_chat_usage_without_breakdown_is_costed_not_zero(self):
+        """A chat ``Usage`` with ``completion_tokens_details=None`` must still be
+        costed via ``generic_cost_per_token`` (output at the text rate) rather than
+        erroring or silently returning 0.0."""
+        from litellm.llms.openai.image_generation.cost_calculator import (
+            cost_calculator,
+        )
+
+        usage = Usage(
+            prompt_tokens=600,
+            completion_tokens=5000,
+            total_tokens=5600,
+            prompt_tokens_details=PromptTokensDetailsWrapper(
+                text_tokens=100,
+                image_tokens=500,
+            ),
+        )
+
+        image_response = ImageResponse(
+            created=1234567890,
+            data=[ImageObject(b64_json="test")],
+        )
+        image_response.usage = usage
+        image_response._hidden_params = {"custom_llm_provider": "openai"}
+
+        cost = cost_calculator(
+            model="gpt-image-2",
+            image_response=image_response,
+            custom_llm_provider="openai",
+        )
+
+        # No output breakdown -> output priced at the text rate (output_cost_per_token):
+        #   text in 100*$5/1M + image in 500*$8/1M + output 5000*$10/1M
+        expected_cost = 100 * 5e-6 + 500 * 8e-6 + 5000 * 1e-5
+        assert abs(cost - expected_cost) < 1e-6, f"Expected {expected_cost}, got {cost}"
+
+
 if __name__ == "__main__":
     pytest.main([__file__, "-v"])
diff --git a/ui/litellm-dashboard/src/components/UsagePage/utils/value_formatters.tsx b/ui/litellm-dashboard/src/components/UsagePage/utils/value_formatters.tsx
index 4048c0f1c4a..a1fb3ec8bb4 100644
--- a/ui/litellm-dashboard/src/components/UsagePage/utils/value_formatters.tsx
+++ b/ui/litellm-dashboard/src/components/UsagePage/utils/value_formatters.tsx
@@ -1,6 +1,9 @@
 export function valueFormatter(number: number) {
-  if (number >= 1000000) {
-    return (number / 1000000).toFixed(2) + "M";
+  if (number >= 1_000_000_000) {
+    return (number / 1_000_000_000).toFixed(2) + "B";
+  }
+  if (number >= 1_000_000) {
+    return (number / 1_000_000).toFixed(2) + "M";
   }
   if (number >= 1000) {
     return number / 1000 + "k";
@@ -10,8 +13,11 @@ export function valueFormatter(number: number) {
 
 export function valueFormatterSpend(number: number) {
   if (number === 0) return "$0";
-  if (number >= 1000000) {
-    return "$" + number / 1000000 + "M";
+  if (number >= 1_000_000_000) {
+    return "$" + parseFloat((number / 1_000_000_000).toFixed(2)) + "B";
+  }
+  if (number >= 1_000_000) {
+    return "$" + parseFloat((number / 1_000_000).toFixed(2)) + "M";
   }
   if (number >= 1000) {
     return "$" + number / 1000 + "k";
diff --git a/ui/litellm-dashboard/src/components/VirtualKeysPage/VirtualKeysTable.tsx b/ui/litellm-dashboard/src/components/VirtualKeysPage/VirtualKeysTable.tsx
index 299f8a05f71..0c95d5dcfb7 100644
--- a/ui/litellm-dashboard/src/components/VirtualKeysPage/VirtualKeysTable.tsx
+++ b/ui/litellm-dashboard/src/components/VirtualKeysPage/VirtualKeysTable.tsx
@@ -467,10 +467,15 @@ export function VirtualKeysTable({ teams, organizations, onSortChange, currentSo
         enableSorting: true,
         cell: (info) => {
           const maxBudget = info.getValue() as number | null;
-          if (maxBudget === null) {
-            return "Unlimited";
+          if (maxBudget !== null) {
+            return `$${formatNumberWithCommas(maxBudget)}`;
           }
-          return `$${formatNumberWithCommas(maxBudget)}`;
+          const teamId = info.row.original.team_id;
+          const team = teams?.find((t) => t.team_id === teamId);
+          if (team?.max_budget != null) {
+            return `$${formatNumberWithCommas(team.max_budget)} (Team)`;
+          }
+          return "Unlimited";
         },
       },
       {
diff --git a/ui/litellm-dashboard/src/components/activity_metrics.tsx b/ui/litellm-dashboard/src/components/activity_metrics.tsx
index bd16c2f7219..9c7b62d78d1 100644
--- a/ui/litellm-dashboard/src/components/activity_metrics.tsx
+++ b/ui/litellm-dashboard/src/components/activity_metrics.tsx
@@ -295,6 +295,7 @@ export const ActivityMetrics: React.FC<ActivityMetricsProps> = ({ modelMetrics,
               valueFormatter={valueFormatter}
               customTooltip={CustomTooltip}
               showLegend={false}
+              yAxisWidth={80}
             />
           </Card>
           <Card>
@@ -311,9 +312,10 @@ export const ActivityMetrics: React.FC<ActivityMetricsProps> = ({ modelMetrics,
               index="date"
               categories={["metrics.successful_requests", "metrics.failed_requests"]}
               colors={["emerald", "red"]}
-              valueFormatter={(number: number) => number.toLocaleString()}
+              valueFormatter={valueFormatter}
               customTooltip={CustomTooltip}
               showLegend={false}
+              yAxisWidth={80}
             />
           </Card>
         </Grid>
diff --git a/ui/litellm-dashboard/src/components/templates/key_info_view.budget_display.test.tsx b/ui/litellm-dashboard/src/components/templates/key_info_view.budget_display.test.tsx
index 77abde3d870..5407d37fcf1 100644
--- a/ui/litellm-dashboard/src/components/templates/key_info_view.budget_display.test.tsx
+++ b/ui/litellm-dashboard/src/components/templates/key_info_view.budget_display.test.tsx
@@ -1,7 +1,7 @@
 import { renderWithProviders } from "../../../tests/test-utils";
 import { screen, waitFor } from "@testing-library/react";
 import { beforeEach, describe, expect, it, vi } from "vitest";
-import { KeyResponse } from "../key_team_helpers/key_list";
+import { KeyResponse, Team } from "../key_team_helpers/key_list";
 import KeyInfoView from "./key_info_view";
 import useAuthorized from "@/app/(dashboard)/hooks/useAuthorized";
 import useTeams from "@/app/(dashboard)/hooks/useTeams";
@@ -103,8 +103,26 @@ const baseAuthorized = {
   userEmail: null,
   disabledPersonalKeyCreation: null,
   showSSOBanner: false,
+  isLoading: false,
+  isAuthorized: true,
 };
 
+const makeTeam = (overrides: Partial<Team>): Team => ({
+  team_id: "team-default",
+  team_alias: "Default Team",
+  models: [],
+  max_budget: null,
+  budget_duration: null,
+  tpm_limit: null,
+  rpm_limit: null,
+  organization_id: "",
+  created_at: "2026-01-01T00:00:00Z",
+  keys: [],
+  members_with_roles: [],
+  spend: 0,
+  ...overrides,
+});
+
 describe("KeyInfoView overview budget display (LIT-2845)", () => {
   beforeEach(() => {
     vi.mocked(useTeams).mockReturnValue({ teams: [], setTeams: vi.fn() });
@@ -151,7 +169,64 @@ describe("KeyInfoView overview budget display (LIT-2845)", () => {
   it("renders 'Unlimited' when max_budget is null", async () => {
     renderWithProviders(
       <KeyInfoView
-        keyData={{ ...MOCK_KEY_DATA, max_budget: null }}
+        keyData={{ ...MOCK_KEY_DATA, max_budget: null } as unknown as KeyResponse}
+        onClose={() => {}}
+        keyId={"test-key-id"}
+        onKeyDataUpdate={() => {}}
+        teams={[]}
+      />,
+    );
+    await waitFor(() => {
+      expect(screen.getByText(/of Unlimited/)).toBeInTheDocument();
+    });
+  });
+
+  it("renders team budget with alias and duration when key has no own budget but team has one", async () => {
+    vi.mocked(useTeams).mockReturnValue({
+      teams: [makeTeam({ team_id: "team-123", team_alias: "Test Budget", max_budget: 1200, budget_duration: "30d" })],
+      setTeams: vi.fn(),
+    });
+    renderWithProviders(
+      <KeyInfoView
+        keyData={{ ...MOCK_KEY_DATA, max_budget: null, team_id: "team-123" } as unknown as KeyResponse}
+        onClose={() => {}}
+        keyId={"test-key-id"}
+        onKeyDataUpdate={() => {}}
+        teams={[]}
+      />,
+    );
+    await waitFor(() => {
+      expect(screen.getByText(/of \$1,200\.00 \(Team: Test Budget \/ 30d\)/)).toBeInTheDocument();
+    });
+  });
+
+  it("renders team budget without duration when team has no budget_duration", async () => {
+    vi.mocked(useTeams).mockReturnValue({
+      teams: [makeTeam({ team_id: "team-456", team_alias: "No Duration Team", max_budget: 500 })],
+      setTeams: vi.fn(),
+    });
+    renderWithProviders(
+      <KeyInfoView
+        keyData={{ ...MOCK_KEY_DATA, max_budget: null, team_id: "team-456" } as unknown as KeyResponse}
+        onClose={() => {}}
+        keyId={"test-key-id"}
+        onKeyDataUpdate={() => {}}
+        teams={[]}
+      />,
+    );
+    await waitFor(() => {
+      expect(screen.getByText(/of \$500\.00 \(Team: No Duration Team\)/)).toBeInTheDocument();
+    });
+  });
+
+  it("renders 'Unlimited' when key has no budget and team also has no budget", async () => {
+    vi.mocked(useTeams).mockReturnValue({
+      teams: [makeTeam({ team_id: "team-789", team_alias: "Free Team" })],
+      setTeams: vi.fn(),
+    });
+    renderWithProviders(
+      <KeyInfoView
+        keyData={{ ...MOCK_KEY_DATA, max_budget: null, team_id: "team-789" } as unknown as KeyResponse}
         onClose={() => {}}
         keyId={"test-key-id"}
         onKeyDataUpdate={() => {}}
diff --git a/ui/litellm-dashboard/src/components/templates/key_info_view.tsx b/ui/litellm-dashboard/src/components/templates/key_info_view.tsx
index 018880b70aa..4244ae2d794 100644
--- a/ui/litellm-dashboard/src/components/templates/key_info_view.tsx
+++ b/ui/litellm-dashboard/src/components/templates/key_info_view.tsx
@@ -411,6 +411,15 @@ export default function KeyInfoView({
     });
   };
 
+  const parentTeam = currentKeyData.team_id ? teamsData?.find((team) => team.team_id === currentKeyData.team_id) : null;
+
+  const budgetDisplay =
+    currentKeyData.max_budget !== null
+      ? `$${formatNumberWithCommas(currentKeyData.max_budget, 2)}`
+      : parentTeam?.max_budget != null
+        ? `$${formatNumberWithCommas(parentTeam.max_budget, 2)} (Team: ${parentTeam.team_alias || parentTeam.team_id}${parentTeam.budget_duration ? ` / ${parentTeam.budget_duration}` : ""})`
+        : "Unlimited";
+
   return (
     <div className="w-full h-full overflow-y-auto p-4">
       <KeyInfoHeader
@@ -520,12 +529,7 @@ export default function KeyInfoView({
                 <Text>Spend</Text>
                 <div className="mt-2">
                   <Title>${formatNumberWithCommas(currentKeyData.spend, 4)}</Title>
-                  <Text>
-                    of{" "}
-                    {currentKeyData.max_budget !== null
-                      ? `$${formatNumberWithCommas(currentKeyData.max_budget, 2)}`
-                      : "Unlimited"}
-                  </Text>
+                  <Text>of {budgetDisplay}</Text>
                 </div>
               </Card>
 
diff --git a/ui/litellm-dashboard/src/components/view_logs/LogDetailsDrawer/PrettyMessagesView.test.tsx b/ui/litellm-dashboard/src/components/view_logs/LogDetailsDrawer/PrettyMessagesView.test.tsx
index b73dcafcdc3..e7295ed7a72 100644
--- a/ui/litellm-dashboard/src/components/view_logs/LogDetailsDrawer/PrettyMessagesView.test.tsx
+++ b/ui/litellm-dashboard/src/components/view_logs/LogDetailsDrawer/PrettyMessagesView.test.tsx
@@ -27,6 +27,17 @@ describe("PrettyMessagesView", () => {
     expect(screen.getByText("Hi there!")).toBeInTheDocument();
   });
 
+  it("renders input when request is a bare messages array (cold storage payload)", () => {
+    const request = [{ role: "user", content: "Write me a poem" }];
+    const response = {
+      choices: [{ message: { role: "assistant", content: "A quiet moment." } }],
+    };
+
+    render(<PrettyMessagesView request={request} response={response} />);
+    expect(screen.getByText("Write me a poem")).toBeInTheDocument();
+    expect(screen.getByText("A quiet moment.")).toBeInTheDocument();
+  });
+
   it("should render the realtime pretty view for realtime API responses", () => {
     const request = {};
     const response = {
diff --git a/ui/litellm-dashboard/src/components/view_logs/LogDetailsDrawer/prettyMessagesUtils.ts b/ui/litellm-dashboard/src/components/view_logs/LogDetailsDrawer/prettyMessagesUtils.ts
index 32ae294b1ee..09b8f551c1d 100644
--- a/ui/litellm-dashboard/src/components/view_logs/LogDetailsDrawer/prettyMessagesUtils.ts
+++ b/ui/litellm-dashboard/src/components/view_logs/LogDetailsDrawer/prettyMessagesUtils.ts
@@ -39,18 +39,24 @@ export const ROLE_STYLES: Record<string, RoleStyle> = {
  * Parse request messages and response message from log data
  */
 export const parseMessages = (request: any, response: any): ParsedMessages => {
-  // Parse request messages
+  // Parse request messages. `request` is either the raw request body
+  // ({ messages: [...] }) or, when prompts come from cold storage, the bare
+  // messages array itself.
   const requestMessages: ParsedMessage[] = [];
 
-  if (request?.messages && Array.isArray(request.messages)) {
-    request.messages.forEach((msg: any) => {
-      requestMessages.push({
-        role: msg.role || "user",
-        content: parseMessageContent(msg.content),
-        toolCallId: msg.tool_call_id,
-      });
+  const requestMessageList = Array.isArray(request)
+    ? request
+    : Array.isArray(request?.messages)
+      ? request.messages
+      : [];
+
+  requestMessageList.forEach((msg: any) => {
+    requestMessages.push({
+      role: msg.role || "user",
+      content: parseMessageContent(msg.content),
+      toolCallId: msg.tool_call_id,
     });
-  }
+  });
 
   // Parse response message
   let responseMessage: ParsedMessage | null = null;