Merge remote-tracking branch 'upstream/litellm_internal_staging' into litellm_remove_redundant_model_cost_backup_file

# Conflicts:
#	litellm/model_prices_and_context_window_backup.json

.github/workflows/check-lazy-openapi-snapshot.yml

@@ -1,75 +0,0 @@
-name: Check Lazy OpenAPI Snapshot
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - "litellm_**"
-
-permissions:
-  contents: read
-  checks: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  verify:
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    steps:
-      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
-        with:
-          persist-credentials: false
-
-      - name: Set up Python
-        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
-        with:
-          python-version: "3.12"
-
-      - name: Set up uv
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
-        with:
-          version: "0.10.9"
-
-      - name: Cache uv dependencies
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
-        with:
-          path: |
-            ~/.cache/uv
-            .venv
-          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-uv-
-
-      - name: Install dependencies
-        run: uv sync --frozen --all-groups --all-extras
-
-      - name: Regenerate snapshot to /tmp
-        id: regen
-        run: |
-          cp litellm/proxy/_lazy_openapi_snapshot.json /tmp/snapshot.committed.json
-          uv run --no-sync python -m litellm.proxy._lazy_openapi_snapshot
-          mv litellm/proxy/_lazy_openapi_snapshot.json /tmp/snapshot.fresh.json
-          mv /tmp/snapshot.committed.json litellm/proxy/_lazy_openapi_snapshot.json
-
-      - name: Compare
-        id: diff
-        continue-on-error: true
-        run: |
-          diff -q /tmp/snapshot.fresh.json litellm/proxy/_lazy_openapi_snapshot.json
-
-      - name: Mark neutral if drift
-        if: steps.diff.outcome == 'failure'
-        uses: LouisBrunner/checks-action@6b626ffbad7cc56fd58627f774b9067e6118af23 # v2.0.0
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          name: lazy-openapi-snapshot
-          conclusion: neutral
-          output: |
-            {
-              "title": "Lazy openapi snapshot is stale",
-              "summary": "Run `python -m litellm.proxy._lazy_openapi_snapshot` and commit the regenerated `litellm/proxy/_lazy_openapi_snapshot.json`. Not blocking — the snapshot will regenerate at release if not committed."
-            }

.github/workflows/create-release.yml

@@ -4,7 +4,7 @@ on:
   workflow_dispatch:
     inputs:
       tag:
-        description: "Release tag (e.g. 1.84.0, 1.84.0rc1, 1.84.0.dev42, 1.84.0.post1; legacy v1.83.10-stable still accepted)"
+        description: "Release tag (e.g. 1.84.0, 1.84.0rc1, 1.84.0.dev42, 1.84.0-dev.2, 1.84.0.post1; legacy v1.83.10-stable still accepted)"
         required: true
         type: string
       commit_hash:
@@ -46,9 +46,11 @@ jobs:
             const commitHash = process.env.COMMIT_HASH;
 
             // Mark RC / dev / nightly / alpha / beta tags as GitHub pre-releases.
+            // Accept both PEP 440 (`.dev`) and SemVer (`-dev`) separators so tags
+            // like `1.84.0.dev2` and `1.84.0-dev.2` are both detected.
             // PEP 440 post-releases (e.g. `1.84.0.post1`) and legacy `-stable[.patch.N]`
             // are stable maintenance releases, not pre-releases.
-            const isPrerelease = /(?:rc|nightly|alpha|beta|\.dev)/i.test(tag);
+            const isPrerelease = /(?:rc|nightly|alpha|beta|[-.]dev)/i.test(tag);
 
             const cosignSection = [
               `## Verify Docker Image Signature`,

.gitignore

@@ -90,7 +90,6 @@ test.py
 litellm_config.yaml
 !.github/observatory/litellm_config.yaml
 .cursor
-.vscode/launch.json
 litellm/proxy/to_delete_loadtest_work/*
 update_model_cost_map.py
 litellm/model_prices_and_context_window_backup.json
@@ -101,4 +100,5 @@ STABILIZATION_TODO.md
 **/test-results
 **/playwright-report
 **/*.storageState.json
-**/coverage
+**/coverage
+test-config

Dockerfile

@@ -1,9 +1,9 @@
 # Base image for building
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:3258be472764337fd13095bcbb3182da170243b5819fd67ad4c0754590588b31
 
 # Runtime image
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
-ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:3258be472764337fd13095bcbb3182da170243b5819fd67ad4c0754590588b31
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 
 FROM $UV_IMAGE AS uvbin
 

Makefile

@@ -185,3 +185,6 @@ test-llm-translation-single: install-test-deps
 	$(UV_RUN) pytest tests/llm_translation/$(FILE) \
 		--junitxml=test-results/junit.xml \
 		-v --tb=short --maxfail=100 --timeout=300
+
+test-llm-translation-flush-vcr-cache:
+	$(UV_RUN) python tests/_flush_vcr_cache.py

README.md

@@ -68,7 +68,7 @@ Managing LLM calls across providers gets complicated fast — different SDKs, au
     <td><img height="60" alt="Stripe" src="https://github.com/user-attachments/assets/f7296d4f-9fbd-460d-9d05-e4df31697c4b" /></td>
     <td><img height="60" alt="image" src="https://github.com/user-attachments/assets/436fca71-988b-40bb-b5fe-8450c80fdbd0" /></td>
     <td><img height="60" alt="Google ADK" src="https://github.com/user-attachments/assets/caf270a2-5aee-45c4-8222-41a2070c4f19" /></td>
-    <td><img height="60" alt="Greptile" src="https://github.com/user-attachments/assets/0be4bd8a-7cfa-48d3-9090-f415fe948280" /></td>
+    <td><img height="60" alt="Greptile" src="https://github.com/user-attachments/assets/3db0ae72-0843-4005-a56d-bba1dde2193d" /></td>
     <td><img height="60" alt="OpenHands" src="https://github.com/user-attachments/assets/a6150c4c-149e-4cae-888b-8b92be6e003f" /></td>
     <td><h2>Netflix</h2></td>
     <td><img height="60" alt="OpenAI Agents SDK" src="https://github.com/user-attachments/assets/c02f7be0-8c2e-4d27-aea7-7c024bfaebc0" /></td>

docker/Dockerfile.alpine

@@ -3,7 +3,7 @@ ARG LITELLM_BUILD_IMAGE=python:3.11-alpine@sha256:f07e2ace46f560f09a6eeec7b4913b
 
 # Runtime image
 ARG LITELLM_RUNTIME_IMAGE=python:3.11-alpine@sha256:f07e2ace46f560f09a6eeec7b4913b80ee99546e749ef82342a419a326620856
-ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 
 FROM $UV_IMAGE AS uvbin
 

docker/Dockerfile.database

@@ -1,9 +1,9 @@
 # Base image for building
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:3258be472764337fd13095bcbb3182da170243b5819fd67ad4c0754590588b31
 
 # Runtime image
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
-ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:3258be472764337fd13095bcbb3182da170243b5819fd67ad4c0754590588b31
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 
 FROM $UV_IMAGE AS uvbin
 

docker/Dockerfile.dev

@@ -3,7 +3,7 @@ ARG LITELLM_BUILD_IMAGE=python:3.13-slim@sha256:739e7213785e88c0f702dcdc12c0973a
 
 # Runtime image
 ARG LITELLM_RUNTIME_IMAGE=python:3.13-slim@sha256:739e7213785e88c0f702dcdc12c0973afcbd606dbf021a589cab77d6b00b579d
-ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 
 FROM $UV_IMAGE AS uvbin
 

docker/Dockerfile.health_check

@@ -1,4 +1,4 @@
-ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 FROM $UV_IMAGE AS uvbin
 
 FROM python:3.13-slim@sha256:739e7213785e88c0f702dcdc12c0973afcbd606dbf021a589cab77d6b00b579d

docker/Dockerfile.non_root

@@ -1,8 +1,8 @@
 # Base images
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:3258be472764337fd13095bcbb3182da170243b5819fd67ad4c0754590588b31
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:3258be472764337fd13095bcbb3182da170243b5819fd67ad4c0754590588b31
 ARG PROXY_EXTRAS_SOURCE=published
-ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 
 FROM $UV_IMAGE AS uvbin
 

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

@@ -0,0 +1,196 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Crusoe
+
+## Overview
+
+| Property | Details |
+|-------|-------|
+| Description | Crusoe Cloud provides GPU-accelerated inference for open-source large language models, optimized for performance and cost efficiency. |
+| Provider Route on LiteLLM | `crusoe/` |
+| Link to Provider Doc | [Crusoe Managed Inference Documentation ↗](https://docs.crusoecloud.com/managed-inference/overview/index.html) |
+| Base URL | `https://managed-inference-api-proxy.crusoecloud.com/v1` |
+| Supported Operations | [`/chat/completions`](#sample-usage) |
+
+<br />
+<br />
+
+**We support ALL Crusoe models, just set `crusoe/` as a prefix when sending completion requests**
+
+## Available Models
+
+| Model | Description | Context Window |
+|-------|-------------|----------------|
+| `crusoe/deepseek-ai/DeepSeek-R1-0528` | DeepSeek R1 reasoning model (May 2025) | 163,840 tokens |
+| `crusoe/deepseek-ai/DeepSeek-V3-0324` | DeepSeek V3 chat model (March 2025) | 163,840 tokens |
+| `crusoe/google/gemma-3-12b-it` | Google Gemma 3 12B instruction-tuned | 131,072 tokens |
+| `crusoe/meta-llama/Llama-3.3-70B-Instruct` | Llama 3.3 70B instruction-tuned | 131,072 tokens |
+| `crusoe/moonshotai/Kimi-K2-Thinking` | Kimi K2 extended thinking model | 262,144 tokens |
+| `crusoe/openai/gpt-oss-120b` | OpenAI 120B open-source model | 131,072 tokens |
+| `crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507` | Qwen3 235B MoE instruction-tuned | 262,144 tokens |
+
+## Required Variables
+
+```python showLineNumbers title="Environment Variables"
+os.environ["CRUSOE_API_KEY"] = ""  # your Crusoe API key
+```
+
+## Usage - LiteLLM Python SDK
+
+### Non-streaming
+
+```python showLineNumbers title="Crusoe Non-streaming Completion"
+import os
+import litellm
+from litellm import completion
+
+os.environ["CRUSOE_API_KEY"] = ""  # your Crusoe API key
+
+messages = [{"content": "Hello, how are you?", "role": "user"}]
+
+# Crusoe call
+response = completion(
+    model="crusoe/meta-llama/Llama-3.3-70B-Instruct",
+    messages=messages
+)
+
+print(response)
+```
+
+### Streaming
+
+```python showLineNumbers title="Crusoe Streaming Completion"
+import os
+import litellm
+from litellm import completion
+
+os.environ["CRUSOE_API_KEY"] = ""  # your Crusoe API key
+
+messages = [{"content": "Write a short story about AI", "role": "user"}]
+
+# Crusoe call with streaming
+response = completion(
+    model="crusoe/meta-llama/Llama-3.3-70B-Instruct",
+    messages=messages,
+    stream=True
+)
+
+for chunk in response:
+    print(chunk)
+```
+
+### Function Calling
+
+```python showLineNumbers title="Crusoe Function Calling"
+import os
+import litellm
+from litellm import completion
+
+os.environ["CRUSOE_API_KEY"] = ""  # your Crusoe API key
+
+tools = [{
+    "type": "function",
+    "function": {
+        "name": "get_weather",
+        "description": "Get the current weather in a location",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "location": {
+                    "type": "string",
+                    "description": "The city and state, e.g. San Francisco, CA"
+                }
+            },
+            "required": ["location"]
+        }
+    }
+}]
+
+messages = [{"role": "user", "content": "What's the weather in Boston?"}]
+
+response = completion(
+    model="crusoe/meta-llama/Llama-3.3-70B-Instruct",
+    messages=messages,
+    tools=tools,
+    tool_choice="auto"
+)
+
+print(response)
+```
+
+## Usage - LiteLLM Proxy Server
+
+```yaml showLineNumbers title="config.yaml"
+model_list:
+  - model_name: llama-3.3-70b
+    litellm_params:
+      model: crusoe/meta-llama/Llama-3.3-70B-Instruct
+      api_key: os.environ/CRUSOE_API_KEY
+  - model_name: deepseek-r1
+    litellm_params:
+      model: crusoe/deepseek-ai/DeepSeek-R1-0528
+      api_key: os.environ/CRUSOE_API_KEY
+  - model_name: deepseek-v3
+    litellm_params:
+      model: crusoe/deepseek-ai/DeepSeek-V3-0324
+      api_key: os.environ/CRUSOE_API_KEY
+  - model_name: qwen3-235b
+    litellm_params:
+      model: crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507
+      api_key: os.environ/CRUSOE_API_KEY
+  - model_name: kimi-k2
+    litellm_params:
+      model: crusoe/moonshotai/Kimi-K2-Thinking
+      api_key: os.environ/CRUSOE_API_KEY
+```
+
+## Custom API Base
+
+**Option 1: Environment variable**
+
+```python showLineNumbers title="Custom API Base via env var"
+import os
+from litellm import completion
+
+os.environ["CRUSOE_API_BASE"] = "https://custom.crusoecloud.com/v1"
+os.environ["CRUSOE_API_KEY"] = ""  # your API key
+
+response = completion(
+    model="crusoe/meta-llama/Llama-3.3-70B-Instruct",
+    messages=[{"content": "Hello!", "role": "user"}],
+)
+```
+
+**Option 2: Pass directly**
+
+```python showLineNumbers title="Custom API Base via parameter"
+from litellm import completion
+
+response = completion(
+    model="crusoe/meta-llama/Llama-3.3-70B-Instruct",
+    messages=[{"content": "Hello!", "role": "user"}],
+    api_base="https://custom.crusoecloud.com/v1",
+    api_key="your-api-key",
+)
+```
+
+## Supported OpenAI Parameters
+
+- `temperature`
+- `max_tokens`
+- `max_completion_tokens`
+- `top_p`
+- `frequency_penalty`
+- `presence_penalty`
+- `stop`
+- `n`
+- `stream`
+- `tools`
+- `tool_choice`
+- `response_format`
+- `seed`
+- `user`
+- `logit_bias`
+- `logprobs`
+- `top_logprobs`

enterprise/litellm_enterprise/proxy/auth/custom_sso_handler.py

@@ -10,28 +10,21 @@ has already authenticated the user) and you need to extract user information fro
 custom headers or other request attributes.
 """
 
-from typing import TYPE_CHECKING, Dict, Optional, Union, cast
+from typing import cast
 
 from fastapi import Request
 from fastapi.responses import RedirectResponse
 
-if TYPE_CHECKING:
-    from fastapi_sso.sso.base import OpenID
-else:
-    from typing import Any as OpenID
-
-from litellm.proxy.management_endpoints.types import CustomOpenID
-
 
 class EnterpriseCustomSSOHandler:
     """
     Enterprise Custom SSO Handler for LiteLLM Proxy
-    
+
     This class provides methods for handling custom SSO authentication flows
     where users can implement their own authentication logic by processing
     request headers and returning user information in OpenID format.
     """
-    
+
     @staticmethod
     async def handle_custom_ui_sso_sign_in(
         request: Request,
@@ -40,16 +33,16 @@ class EnterpriseCustomSSOHandler:
         Allow a user to execute their custom code to parse incoming request headers and return a OpenID object
 
         Use this when you have an OAuth proxy in front of LiteLLM (where the OAuth proxy has already authenticated the user)
-        
+
         Args:
             request: The FastAPI request object containing headers and other request data
-            
+
         Returns:
             RedirectResponse: Redirect response that sends the user to the LiteLLM UI with authentication token
-            
+
         Raises:
             ValueError: If custom_ui_sso_sign_in_handler is not configured
-            
+
         Example:
             This method is typically called when a user has already been authenticated by an
             external OAuth proxy and the proxy has added custom headers containing user information.
@@ -60,27 +53,44 @@ class EnterpriseCustomSSOHandler:
         from litellm.integrations.custom_sso_handler import CustomSSOLoginHandler
         from litellm.proxy.proxy_server import (
             CommonProxyErrors,
+            general_settings,
             premium_user,
             user_custom_ui_sso_sign_in_handler,
         )
+        from litellm.proxy.auth.trusted_proxy_utils import (
+            require_trusted_proxy_request,
+        )
+
         if premium_user is not True:
             raise ValueError(CommonProxyErrors.not_premium_user.value)
-        
+
         if user_custom_ui_sso_sign_in_handler is None:
-            raise ValueError("custom_ui_sso_sign_in_handler is not configured. Please set it in general_settings.")
-        
-        custom_sso_login_handler = cast(CustomSSOLoginHandler, user_custom_ui_sso_sign_in_handler)
-        openid_response: OpenID = await custom_sso_login_handler.handle_custom_ui_sso_sign_in(
+            raise ValueError(
+                "custom_ui_sso_sign_in_handler is not configured. Please set it in general_settings."
+            )
+
+        require_trusted_proxy_request(
             request=request,
+            general_settings=general_settings,
+            feature_name="Custom UI SSO",
         )
-        
+
+        custom_sso_login_handler = cast(
+            CustomSSOLoginHandler, user_custom_ui_sso_sign_in_handler
+        )
+        openid_response: OpenID = (
+            await custom_sso_login_handler.handle_custom_ui_sso_sign_in(
+                request=request,
+            )
+        )
+
         # Import here to avoid circular imports
         from litellm.proxy.management_endpoints.ui_sso import SSOAuthenticationHandler
-        
+
         return await SSOAuthenticationHandler.get_redirect_response_from_openid(
             result=openid_response,
             request=request,
             received_response=None,
             generic_client_id=None,
             ui_access_mode=None,
-        ) 
+        )

enterprise/litellm_enterprise/proxy/management_endpoints/project_endpoints.py

@@ -588,24 +588,21 @@ async def update_project(  # noqa: PLR0915
                 param="project_id",
             )
 
-        # Validate team exists and get team object for limit + permission checks
-        team_id_to_check = data.team_id or existing_project.team_id
-        team_obj_for_checks = None
-        if team_id_to_check is not None:
-            team_obj_for_checks = await _validate_team_exists(
-                team_id=team_id_to_check, prisma_client=prisma_client
+        # Permission to *edit* the project must be evaluated against the
+        # project's CURRENT team. Sourcing the team from `data.team_id`
+        # would let an admin of any team pass the check by supplying their
+        # own team_id, hijacking the project (VERIA-55).
+        target_team_id = data.team_id or existing_project.team_id
+        target_team_obj = None
+        if target_team_id is not None:
+            target_team_obj = await _validate_team_exists(
+                team_id=target_team_id, prisma_client=prisma_client
             )
 
-        # Check if user has permission to update this project
         has_permission = await _check_user_permission_for_project(
             user_api_key_dict=user_api_key_dict,
             team_id=existing_project.team_id,
             prisma_client=prisma_client,
-            team_object=(
-                LiteLLM_TeamTable(**team_obj_for_checks.model_dump())
-                if team_obj_for_checks
-                else None
-            ),
         )
 
         if not has_permission:
@@ -614,10 +611,32 @@ async def update_project(  # noqa: PLR0915
                 detail={"error": "Only admins or team admins can update projects"},
             )
 
+        # Reassigning to a different team also requires admin rights on the
+        # destination team — otherwise a team admin could shed projects into
+        # an unsuspecting team's namespace.
+        if data.team_id is not None and data.team_id != existing_project.team_id:
+            can_assign_to_target = await _check_user_permission_for_project(
+                user_api_key_dict=user_api_key_dict,
+                team_id=data.team_id,
+                prisma_client=prisma_client,
+                team_object=(
+                    LiteLLM_TeamTable(**target_team_obj.model_dump())
+                    if target_team_obj
+                    else None
+                ),
+            )
+            if not can_assign_to_target:
+                raise HTTPException(
+                    status_code=403,
+                    detail={
+                        "error": "Cannot reassign project to a team you are not an admin of"
+                    },
+                )
+
         # Validate project limits against team limits
-        if team_obj_for_checks is not None:
+        if target_team_obj is not None:
             _check_team_project_limits(
-                team_object=LiteLLM_TeamTable(**team_obj_for_checks.model_dump()),
+                team_object=LiteLLM_TeamTable(**target_team_obj.model_dump()),
                 data=data,
             )
 
@@ -857,10 +876,16 @@ async def project_info(
                 where={"team_id": project.team_id}
             )
             if team:
-                is_team_member = (
-                    user_api_key_dict.user_id in team.admins
-                    or user_api_key_dict.user_id in team.members
-                )
+                caller_user_id = user_api_key_dict.user_id
+                for m in team.members_with_roles or []:
+                    m_user_id = (
+                        m.get("user_id")
+                        if isinstance(m, dict)
+                        else getattr(m, "user_id", None)
+                    )
+                    if m_user_id == caller_user_id:
+                        is_team_member = True
+                        break
 
         if not (is_admin or is_team_member):
             raise HTTPException(
@@ -911,20 +936,20 @@ async def list_projects(
                 include={"litellm_budget_table": True, "object_permission": True}
             )
         else:
-            # Get projects for teams the user belongs to
-            user_teams = await prisma_client.db.litellm_teamtable.find_many(
-                where={
-                    "OR": [
-                        {"members": {"has": user_api_key_dict.user_id}},
-                        {"admins": {"has": user_api_key_dict.user_id}},
-                    ]
-                }
+            # Look up the user's team memberships via the reverse-index on
+            # LiteLLM_UserTable.teams (maintained by team_member_add alongside
+            # members_with_roles). This avoids a full scan of all team rows.
+            user_record = await prisma_client.db.litellm_usertable.find_unique(
+                where={"user_id": user_api_key_dict.user_id},
+            )
+            user_team_ids = (
+                user_record.teams
+                if user_record is not None and user_record.teams
+                else []
             )
 
-            team_ids = [team.team_id for team in user_teams]
-
             projects = await prisma_client.db.litellm_projecttable.find_many(
-                where={"team_id": {"in": team_ids}},
+                where={"team_id": {"in": user_team_ids}},
                 include={"litellm_budget_table": True, "object_permission": True},
             )
 

litellm/__init__.py

@@ -166,7 +166,7 @@ langfuse_default_tags: Optional[List[str]] = None
 langsmith_batch_size: Optional[int] = None
 prometheus_initialize_budget_metrics: Optional[bool] = False
 prometheus_latency_buckets: Optional[List[float]] = None
-require_auth_for_metrics_endpoint: Optional[bool] = False
+require_auth_for_metrics_endpoint: Optional[bool] = True
 argilla_batch_size: Optional[int] = None
 datadog_use_v1: Optional[bool] = False  # if you want to use v1 datadog logged payload.
 gcs_pub_sub_use_v1: Optional[bool] = (
@@ -280,6 +280,7 @@ ssl_security_level: Optional[str] = None
 ssl_certificate: Optional[str] = None
 user_url_validation: bool = True
 user_url_allowed_hosts: List[str] = []
+provider_url_destination_allowed_hosts: List[str] = []
 ssl_ecdh_curve: Optional[str] = (
     None  # Set to 'X25519' to disable PQC and improve performance
 )
@@ -288,6 +289,7 @@ disable_token_counter: bool = False
 disable_add_transform_inline_image_block: bool = False
 disable_add_user_agent_to_request_tags: bool = False
 disable_anthropic_gemini_context_caching_transform: bool = False
+disable_vertex_batch_output_transformation: bool = False
 extra_spend_tag_headers: Optional[List[str]] = None
 in_memory_llm_clients_cache: "LLMClientCache"
 safe_memory_mode: bool = False
@@ -330,6 +332,9 @@ enable_model_config_credential_overrides: bool = False
 enable_key_alias_format_validation: bool = (
     False  # opt-in validation of key_alias format on /key/generate and /key/update
 )
+enable_gemini_default_thinking_level_low: bool = (
+    False  # opt-in: force thinkingLevel low/minimal for Gemini 3 thinking param mapping
+)
 ####################
 logging: bool = True
 enable_loadbalancing_on_batch_endpoints: Optional[bool] = None

litellm/_logging.py

@@ -1,12 +1,12 @@
 import ast
 import logging
 import os
-import re
 import sys
 from datetime import datetime
 from logging import Formatter
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, Optional
 
+from litellm.litellm_core_utils.secret_redaction import redact_string
 from litellm.litellm_core_utils.safe_json_dumps import safe_dumps
 from litellm.litellm_core_utils.safe_json_loads import safe_json_loads
 
@@ -21,74 +21,11 @@ _ENABLE_SECRET_REDACTION = (
     os.getenv("LITELLM_DISABLE_REDACT_SECRETS", "").lower() != "true"
 )
 
-_REDACTED = "REDACTED"
-
-
-def _build_secret_patterns() -> re.Pattern:
-    patterns: List[str] = [
-        # ── PEM private key / certificate blocks ──
-        r"-----BEGIN[A-Z \-]*PRIVATE KEY-----[\s\S]*?-----END[A-Z \-]*PRIVATE KEY-----",
-        # ── GCP OAuth2 access tokens (ya29.*) ──
-        r"\bya29\.[A-Za-z0-9_.~+/-]+",
-        # ── Credential %s formatting (space separator, no key= prefix) ──
-        r"(?:client_secret|azure_password|azure_username)\s+[^\s,'\"})\]{}>]+",
-        # AWS access key IDs
-        r"(?:AKIA|ASIA)[0-9A-Z]{16}",
-        # AWS secrets / session tokens / access key IDs (key=value)
-        r"(?:aws_secret_access_key|aws_session_token|aws_access_key_id)"
-        r"\s*[:=]\s*[A-Za-z0-9/+=]{20,}",
-        # Bearer tokens (OAuth, JWT, etc.)
-        r"Bearer\s+[A-Za-z0-9\-._~+/]{10,}=*",
-        # Basic auth headers
-        r"Basic\s+[A-Za-z0-9+/]{10,}={0,2}",
-        # OpenAI / Anthropic sk- prefixed keys
-        r"sk-[A-Za-z0-9\-_]{20,}",
-        # Generic api_key / api-key / apikey (handles 'key': 'value' dict repr)
-        r"(?:api[_-]?key)['\"]?\s*[:=]\s*['\"]?[^\s,'\"})\]{}>]{8,}",
-        # x-api-key / api-key header values (handles 'key': 'value' dict repr)
-        r"(?:x-api-key|api-key)['\"]?\s*[:=]\s*['\"]?[^\s,'\"})\]{}>]+",
-        # Anthropic internal header keys
-        r"x-ak-[A-Za-z0-9\-_]{20,}",
-        # Google API keys
-        r"AIza[0-9A-Za-z\-_]{35}",
-        # Password / secret params (handles key=value and 'key': 'value')
-        # Word boundary prevents O(n^2) backtracking on long word-char runs.
-        r"(?:^|(?<=\W))\w*(?:password|passwd|client_secret|secret_key|_secret)"
-        r"['\"]?\s*[:=]\s*['\"]?[^\s,'\"})\]{}>]+",
-        # Database connection string credentials (scheme://user:pass@host)
-        r"(?<=://)[^\s'\"]*:[^\s'\"@]+(?=@)",
-        # Databricks personal access tokens
-        r"dapi[0-9a-f]{32}",
-        # ── Key-name-based redaction ──
-        # Catches secrets inside dicts/config dumps by matching on the KEY name
-        # regardless of what the value looks like.
-        # e.g. 'master_key': 'any-value-here', "database_url": "postgres://..."
-        # private_key with PEM-aware value capture
-        r"""private_key['\"]?\s*[:=]\s*['\"]?(?:-----BEGIN[A-Z \-]*PRIVATE KEY-----[\s\S]*?-----END[A-Z \-]*PRIVATE KEY-----|[^\s,'\"})\]{}>]+)""",
-        r"(?:master_key|database_url|db_url|connection_string|"
-        r"signing_key|encryption_key|"
-        r"auth_token|access_token|refresh_token|"
-        r"slack_webhook_url|webhook_url|"
-        r"database_connection_string|"
-        r"huggingface_token|jwt_secret)"
-        r"""['\"]?\s*[:=]\s*['\"]?[^\s,'\"})\]{}>]+""",
-        # ── Raw JWTs (without Bearer prefix) ──
-        r"\beyJ[A-Za-z0-9_-]{10,}\.[A-Za-z0-9_-]+\.[A-Za-z0-9_-]*",
-        # ── Azure SAS tokens in URLs ──
-        r"[?&]sig=[A-Za-z0-9%+/=]+",
-        # ── Full JSON service-account blobs (single-line and multi-line) ──
-        r'\{[^{}]*"type"\s*:\s*"service_account"[^{}]*(?:\{[^{}]*\}[^{}]*)*\}',
-    ]
-    return re.compile("|".join(patterns), re.IGNORECASE)
-
-
-_SECRET_RE = _build_secret_patterns()
-
 
 def _redact_string(value: str) -> str:
     if not _ENABLE_SECRET_REDACTION:
         return value
-    return _SECRET_RE.sub(_REDACTED, value)
+    return redact_string(value)
 
 
 def redact_secrets(value: str) -> str:

litellm/anthropic_beta_headers_config.json

@@ -72,7 +72,7 @@
     "computer-use-2025-11-24": "computer-use-2025-11-24",
     "context-1m-2025-08-07": "context-1m-2025-08-07",
     "context-management-2025-06-27": null,
-    "effort-2025-11-24": null,
+    "effort-2025-11-24": "effort-2025-11-24",
     "fast-mode-2026-02-01": null,
     "files-api-2025-04-14": null,
     "fine-grained-tool-streaming-2025-05-14": null,
@@ -103,7 +103,7 @@
     "computer-use-2025-11-24": "computer-use-2025-11-24",
     "context-1m-2025-08-07": "context-1m-2025-08-07",
     "context-management-2025-06-27": null,
-    "effort-2025-11-24": null,
+    "effort-2025-11-24": "effort-2025-11-24",
     "fast-mode-2026-02-01": null,
     "files-api-2025-04-14": null,
     "fine-grained-tool-streaming-2025-05-14": null,

litellm/batches/batch_utils.py

@@ -387,6 +387,27 @@ def _get_batch_job_total_usage_from_file_content(
     )
 
 
+def _get_models_from_batch_input_file_content(
+    file_content_dictionary: List[dict],
+) -> List[str]:
+    """Extract the distinct ``body.model`` values from a batch *input* file.
+
+    Used by the proxy's batch pre-call hook to enforce that the caller is
+    authorized for every model named inside the JSONL — not just the one
+    on the outer request — so the proxy's per-key model allowlist isn't
+    bypassed by smuggling expensive models into the batch file.
+    """
+    models: List[str] = []
+    seen: set = set()
+    for _item in file_content_dictionary:
+        body = _item.get("body") or {}
+        model = body.get("model")
+        if model and model not in seen:
+            seen.add(model)
+            models.append(model)
+    return models
+
+
 def _get_batch_job_input_file_usage(
     file_content_dictionary: List[dict],
     custom_llm_provider: Literal["openai", "azure", "vertex_ai"] = "openai",
@@ -403,11 +424,25 @@ def _get_batch_job_input_file_usage(
     for _item in file_content_dictionary:
         body = _item.get("body", {})
         model = body.get("model", model_name or "")
-        messages = body.get("messages", [])
 
+        # Chat completion payloads.
+        messages = body.get("messages")
         if messages:
-            item_tokens = token_counter(model=model, messages=messages)
-            prompt_tokens += item_tokens
+            prompt_tokens += token_counter(model=model, messages=messages)
+            continue
+
+        # Text completion payloads (`prompt`).
+        prompt = body.get("prompt")
+        if prompt:
+            prompt_tokens += _count_prompt_or_input_tokens(model=model, value=prompt)
+            continue
+
+        # Embedding payloads (`input`).
+        input_data = body.get("input")
+        if input_data:
+            prompt_tokens += _count_prompt_or_input_tokens(
+                model=model, value=input_data
+            )
 
     return Usage(
         total_tokens=prompt_tokens + completion_tokens,
@@ -416,6 +451,43 @@ def _get_batch_job_input_file_usage(
     )
 
 
+def _count_prompt_or_input_tokens(model: str, value: Any) -> int:
+    """Token-count a ``prompt`` / ``input`` field that the OpenAI batch
+    schema allows in four shapes:
+
+    - ``str``: a single text prompt.
+    - ``list[str]``: multiple text prompts.
+    - ``list[int]``: a pre-tokenized prompt (each int counts as 1 token).
+    - ``list[list[int]]``: multiple pre-tokenized prompts.
+
+    Pre-fix only the string shapes were counted, so a caller could send
+    a large ``list[list[int]]`` payload and slip past TPM rate limits
+    with a recorded cost of zero tokens.
+    """
+    if isinstance(value, str):
+        return token_counter(model=model, text=value)
+    if isinstance(value, list):
+        total = 0
+        for chunk in value:
+            if isinstance(chunk, str):
+                total += token_counter(model=model, text=chunk)
+            elif isinstance(chunk, int):
+                # Single pre-tokenized prompt at the top level: each
+                # int counts as one token.
+                total += 1
+            elif isinstance(chunk, list):
+                # Nested pre-tokenized prompt: every int contributes a
+                # token. Mixed string/int items still count.
+                total += sum(1 if isinstance(t, int) else 0 for t in chunk)
+                total += sum(
+                    token_counter(model=model, text=t)
+                    for t in chunk
+                    if isinstance(t, str)
+                )
+        return total
+    return 0
+
+
 def _get_batch_job_usage_from_response_body(response_body: dict) -> Usage:
     """
     Get the tokens of a batch job from the response body

litellm/caching/caching.py

@@ -432,9 +432,10 @@ class Cache:
             str: The final hashed cache key with the redis namespace.
         """
         dynamic_cache_control: DynamicCacheControl = kwargs.get("cache", {})
+        metadata = kwargs.get("metadata") or {}
         namespace = (
             dynamic_cache_control.get("namespace")
-            or kwargs.get("metadata", {}).get("redis_namespace")
+            or metadata.get("redis_namespace")
             or self.namespace
         )
         if namespace:

litellm/caching/caching_handler.py

@@ -87,6 +87,18 @@ class CachingHandlerResponse(BaseModel):
 in_memory_cache_obj = InMemoryCache()
 
 
+def _should_defer_streaming_cache_hit_callbacks(*, kwargs: Dict[str, Any]) -> bool:
+    """
+    When stream=True, do not run success callbacks at cache-hit time.
+
+    Cached chat/text completion replay uses CustomStreamWrapper; cached Responses
+    replay uses CachedResponsesAPIStreamingIterator. Both invoke logging success
+    handlers when the stream finishes; firing them here too would double-count
+    spend and callback records.
+    """
+    return kwargs.get("stream", False) is True
+
+
 class LLMCachingHandler:
     def __init__(
         self,
@@ -99,6 +111,7 @@ class LLMCachingHandler:
         self.async_streaming_chunks: List[ModelResponse] = []
         self.sync_streaming_chunks: List[ModelResponse] = []
         self.request_kwargs = request_kwargs
+        self.preset_cache_key: Optional[str] = None
         self.original_function = original_function
         self.start_time = start_time
         if litellm.cache is not None and isinstance(litellm.cache.cache, RedisCache):
@@ -206,7 +219,7 @@ class LLMCachingHandler:
                         custom_llm_provider=kwargs.get("custom_llm_provider", None),
                         args=args,
                     )
-                    if kwargs.get("stream", False) is False:
+                    if not _should_defer_streaming_cache_hit_callbacks(kwargs=kwargs):
                         # LOG SUCCESS
                         self._async_log_cache_hit_on_callbacks(
                             logging_obj=logging_obj,
@@ -215,11 +228,12 @@ class LLMCachingHandler:
                             end_time=end_time,
                             cache_hit=cache_hit,
                         )
-                    cache_key = litellm.cache.get_cache_key(**kwargs)
-                    if (
-                        isinstance(cached_result, BaseModel)
-                        or isinstance(cached_result, CustomStreamWrapper)
-                    ) and hasattr(cached_result, "_hidden_params"):
+                    cache_key = (
+                        self.preset_cache_key
+                        or self.request_kwargs.get("cache_key")
+                        or litellm.cache.get_cache_key(**self.request_kwargs)
+                    )
+                    if hasattr(cached_result, "_hidden_params"):
                         cached_result._hidden_params["cache_key"] = cache_key  # type: ignore
                     return CachingHandlerResponse(cached_result=cached_result)
                 elif (
@@ -265,8 +279,6 @@ class LLMCachingHandler:
         kwargs: Dict[str, Any],
         args: Optional[Tuple[Any, ...]] = None,
     ) -> CachingHandlerResponse:
-        from litellm.utils import CustomStreamWrapper
-
         cached_result: Optional[Any] = None
 
         # Check if caching should be performed BEFORE doing expensive kwargs copy
@@ -282,6 +294,11 @@ class LLMCachingHandler:
                     args,
                 )
             )
+            if new_kwargs.get("metadata") is None:
+                new_kwargs.pop("metadata", None)
+            if new_kwargs.get("stream") is True and "cache_key" not in new_kwargs:
+                new_kwargs["cache_key"] = litellm.cache.get_cache_key(**new_kwargs)
+            self.request_kwargs = new_kwargs
             print_verbose("Checking Sync Cache")
             cached_result = litellm.cache.get_cache(**new_kwargs)
             if cached_result is not None:
@@ -322,17 +339,19 @@ class LLMCachingHandler:
                         is_async=False,
                     )
 
-                    logging_obj.handle_sync_success_callbacks_for_async_calls(
-                        result=cached_result,
-                        start_time=start_time,
-                        end_time=end_time,
-                        cache_hit=cache_hit,
+                    if not _should_defer_streaming_cache_hit_callbacks(kwargs=kwargs):
+                        logging_obj.handle_sync_success_callbacks_for_async_calls(
+                            result=cached_result,
+                            start_time=start_time,
+                            end_time=end_time,
+                            cache_hit=cache_hit,
+                        )
+                    cache_key = (
+                        self.preset_cache_key
+                        or self.request_kwargs.get("cache_key")
+                        or litellm.cache.get_cache_key(**self.request_kwargs)
                     )
-                    cache_key = litellm.cache.get_cache_key(**kwargs)
-                    if (
-                        isinstance(cached_result, BaseModel)
-                        or isinstance(cached_result, CustomStreamWrapper)
-                    ) and hasattr(cached_result, "_hidden_params"):
+                    if hasattr(cached_result, "_hidden_params"):
                         cached_result._hidden_params["cache_key"] = cache_key  # type: ignore
                     return CachingHandlerResponse(cached_result=cached_result)
         return CachingHandlerResponse(cached_result=cached_result)
@@ -686,6 +705,11 @@ class LLMCachingHandler:
                 args,
             )
         )
+        if new_kwargs.get("metadata") is None:
+            new_kwargs.pop("metadata", None)
+        if new_kwargs.get("stream") is True and "cache_key" not in new_kwargs:
+            new_kwargs["cache_key"] = litellm.cache.get_cache_key(**new_kwargs)
+        self.request_kwargs = new_kwargs
         cached_result: Optional[Any] = None
         if call_type == CallTypes.aembedding.value:
             if isinstance(new_kwargs["input"], str):
@@ -710,14 +734,26 @@ class LLMCachingHandler:
                 if all(result is None for result in cached_result):
                     cached_result = None
         else:
+            request_kwargs = new_kwargs.copy()
+            request_cache_key = request_kwargs.pop("cache_key", None)
             if litellm.cache._supports_async() is True:
                 ## check if dual cache is supported ##
+                self.preset_cache_key = (
+                    request_cache_key or litellm.cache.get_cache_key(**request_kwargs)
+                )
                 cached_result = await litellm.cache.async_get_cache(
-                    dynamic_cache_object=self.dual_cache, **new_kwargs
+                    dynamic_cache_object=self.dual_cache,
+                    cache_key=self.preset_cache_key,
+                    **request_kwargs,
                 )
             else:  # fallback for caches that don't support async
+                self.preset_cache_key = (
+                    request_cache_key or litellm.cache.get_cache_key(**request_kwargs)
+                )
                 cached_result = litellm.cache.get_cache(
-                    dynamic_cache_object=self.dual_cache, **new_kwargs
+                    dynamic_cache_object=self.dual_cache,
+                    cache_key=self.preset_cache_key,
+                    **request_kwargs,
                 )
         return cached_result
 
@@ -825,8 +861,27 @@ class LLMCachingHandler:
         elif (call_type == "aresponses" or call_type == "responses") and isinstance(
             cached_result, dict
         ):
-            # Convert cached dict back to ResponsesAPIResponse object
-            cached_result = ResponsesAPIResponse(**cached_result)
+            from litellm.responses.streaming_iterator import (
+                CachedResponsesAPIStreamingIterator,
+            )
+
+            response_obj = ResponsesAPIResponse(**cached_result)
+            if (
+                hasattr(response_obj, "_hidden_params")
+                and response_obj._hidden_params is not None
+                and isinstance(response_obj._hidden_params, dict)
+            ):
+                response_obj._hidden_params["cache_hit"] = True
+
+            if kwargs.get("stream", False) is True:
+                cached_result = CachedResponsesAPIStreamingIterator(
+                    response=response_obj,
+                    logging_obj=logging_obj,
+                    request_data=kwargs,
+                    call_type=call_type,
+                )
+            else:
+                cached_result = response_obj
 
         if (
             hasattr(cached_result, "_hidden_params")

litellm/caching/dual_cache.py

@@ -92,6 +92,25 @@ class DualCache(BaseCache):
         if default_redis_ttl is not None:
             self.default_redis_ttl = default_redis_ttl
 
+    def attach_redis_cache(
+        self,
+        redis_cache: Optional[RedisCache] = None,
+        *,
+        default_redis_ttl: Optional[float] = None,
+    ) -> None:
+        """
+        Attach a Redis backend if this DualCache does not already have one.
+
+        No-op when ``redis_cache`` is None or when Redis was already set (constructor
+        or a prior attach). Use this for lazy wiring after a shared Redis client exists.
+        Does not backfill in-memory-only keys to Redis.
+        """
+        if redis_cache is None or self.redis_cache is not None:
+            return
+        self.redis_cache = redis_cache
+        if default_redis_ttl is not None:
+            self.default_redis_ttl = default_redis_ttl
+
     def set_cache(self, key, value, local_only: bool = False, **kwargs):
         # Update both Redis and in-memory cache
         try:

litellm/caching/qdrant_semantic_cache.py

@@ -11,17 +11,23 @@ Has 4 methods:
 import ast
 import asyncio
 import json
-from typing import Any, cast
+import os
+from typing import Any, Dict, cast
 
 import litellm
 from litellm._logging import print_verbose
 from litellm.constants import QDRANT_SCALAR_QUANTILE, QDRANT_VECTOR_SIZE
+from litellm.litellm_core_utils.prompt_templates.common_utils import (
+    get_str_from_messages,
+)
 from litellm.types.utils import EmbeddingResponse
 
 from .base_cache import BaseCache
 
 
 class QdrantSemanticCache(BaseCache):
+    CACHE_KEY_FIELD_NAME = "litellm_cache_key"
+
     def __init__(  # noqa: PLR0915
         self,
         qdrant_api_base=None,
@@ -33,8 +39,6 @@ class QdrantSemanticCache(BaseCache):
         host_type=None,
         vector_size=None,
     ):
-        import os
-
         from litellm.llms.custom_httpx.http_handler import (
             _get_httpx_client,
             get_async_httpx_client,
@@ -115,7 +119,9 @@ class QdrantSemanticCache(BaseCache):
             print_verbose(
                 f"Collection already exists.\nCollection details:{self.collection_info}"
             )
+            self._ensure_cache_key_payload_index()
         else:
+            quantization_params: Dict[str, Any]
             if quantization_config is None or quantization_config == "binary":
                 quantization_params = {
                     "binary": {
@@ -156,6 +162,7 @@ class QdrantSemanticCache(BaseCache):
                 print_verbose(
                     f"New collection created.\nCollection details:{self.collection_info}"
                 )
+                self._ensure_cache_key_payload_index()
             else:
                 raise Exception("Error while creating new collection")
 
@@ -170,15 +177,94 @@ class QdrantSemanticCache(BaseCache):
             cached_response = ast.literal_eval(cached_response)
         return cached_response
 
+    def _get_qdrant_cache_key_filter(self, key: str) -> dict:
+        return {
+            "must": [
+                {
+                    "key": self.CACHE_KEY_FIELD_NAME,
+                    "match": {"value": str(key)},
+                }
+            ]
+        }
+
+    def _add_cache_key_filter_to_search_data(self, data: dict, key: str) -> None:
+        data["filter"] = self._get_qdrant_cache_key_filter(key)
+
+    def _ensure_cache_key_payload_index(self) -> None:
+        try:
+            response = self.sync_client.put(
+                url=f"{self.qdrant_api_base}/collections/{self.collection_name}/index",
+                headers=self.headers,
+                json={
+                    "field_name": self.CACHE_KEY_FIELD_NAME,
+                    "field_schema": "keyword",
+                },
+            )
+            if response.status_code not in (200, 201):
+                print_verbose(
+                    "Qdrant semantic-cache could not create cache-key payload index: "
+                    f"{response.text}"
+                )
+        except Exception as exc:
+            print_verbose(
+                "Qdrant semantic-cache could not create cache-key payload index: "
+                f"{str(exc)}"
+            )
+
+    def _payload_matches_cache_key(self, payload: dict, key: str) -> bool:
+        # Pre-isolation points stored only prompt + response with no cache-key
+        # payload field. Reassigning them to a caller's key would risk
+        # cross-scope hits, so they're treated as misses and re-populated on
+        # the next set_cache.
+        cached_key = payload.get(self.CACHE_KEY_FIELD_NAME)
+        return cached_key is not None and str(cached_key) == str(key)
+
+    async def _get_async_embedding(self, prompt: str, **kwargs) -> Any:
+        llm_model_list = None
+        llm_router = None
+
+        try:
+            from litellm.proxy.proxy_server import (
+                llm_model_list as proxy_llm_model_list,
+                llm_router as proxy_llm_router,
+            )
+
+            llm_model_list = proxy_llm_model_list
+            llm_router = proxy_llm_router
+        except ImportError:
+            pass
+
+        router_model_names = (
+            [m["model_name"] for m in llm_model_list]
+            if llm_model_list is not None
+            else []
+        )
+        if llm_router is not None and self.embedding_model in router_model_names:
+            user_api_key = kwargs.get("metadata", {}).get("user_api_key", "")
+            return await llm_router.aembedding(
+                model=self.embedding_model,
+                input=prompt,
+                cache={"no-store": True, "no-cache": True},
+                metadata={
+                    "user_api_key": user_api_key,
+                    "semantic-cache-embedding": True,
+                    "trace_id": kwargs.get("metadata", {}).get("trace_id", None),
+                },
+            )
+
+        return await litellm.aembedding(
+            model=self.embedding_model,
+            input=prompt,
+            cache={"no-store": True, "no-cache": True},
+        )
+
     def set_cache(self, key, value, **kwargs):
         print_verbose(f"qdrant semantic-cache set_cache, kwargs: {kwargs}")
         from litellm._uuid import uuid
 
         # get the prompt
         messages = kwargs["messages"]
-        prompt = ""
-        for message in messages:
-            prompt += message["content"]
+        prompt = get_str_from_messages(messages)
 
         # create an embedding for prompt
         embedding_response = cast(
@@ -202,6 +288,7 @@ class QdrantSemanticCache(BaseCache):
                     "id": str(uuid.uuid4()),
                     "vector": embedding,
                     "payload": {
+                        self.CACHE_KEY_FIELD_NAME: str(key),
                         "text": prompt,
                         "response": value,
                     },
@@ -220,9 +307,7 @@ class QdrantSemanticCache(BaseCache):
 
         # get the messages
         messages = kwargs["messages"]
-        prompt = ""
-        for message in messages:
-            prompt += message["content"]
+        prompt = get_str_from_messages(messages)
 
         # convert to embedding
         embedding_response = cast(
@@ -249,6 +334,7 @@ class QdrantSemanticCache(BaseCache):
             "limit": 1,
             "with_payload": True,
         }
+        self._add_cache_key_filter_to_search_data(data=data, key=key)
 
         search_response = self.sync_client.post(
             url=f"{self.qdrant_api_base}/collections/{self.collection_name}/points/search",
@@ -258,21 +344,33 @@ class QdrantSemanticCache(BaseCache):
         results = search_response.json()["result"]
 
         if results is None:
+            kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
             return None
         if isinstance(results, list):
             if len(results) == 0:
+                kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
                 return None
 
         similarity = results[0]["score"]
-        cached_prompt = results[0]["payload"]["text"]
+        payload = results[0]["payload"]
+        if not self._payload_matches_cache_key(payload=payload, key=key):
+            print_verbose("Qdrant semantic-cache hit did not match cache key scope")
+            kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
+            return None
+
+        cached_prompt = payload["text"]
 
         # check similarity, if more than self.similarity_threshold, return results
         print_verbose(
             f"semantic cache: similarity threshold: {self.similarity_threshold}, similarity: {similarity}, prompt: {prompt}, closest_cached_prompt: {cached_prompt}"
         )
+
+        # update kwargs["metadata"] with similarity, don't rewrite the original metadata
+        kwargs.setdefault("metadata", {})["semantic-similarity"] = similarity
+
         if similarity >= self.similarity_threshold:
             # cache hit !
-            cached_value = results[0]["payload"]["response"]
+            cached_value = payload["response"]
             print_verbose(
                 f"got a cache hit, similarity: {similarity}, Current prompt: {prompt}, cached_prompt: {cached_prompt}"
             )
@@ -285,40 +383,12 @@ class QdrantSemanticCache(BaseCache):
     async def async_set_cache(self, key, value, **kwargs):
         from litellm._uuid import uuid
 
-        from litellm.proxy.proxy_server import llm_model_list, llm_router
-
         print_verbose(f"async qdrant semantic-cache set_cache, kwargs: {kwargs}")
 
         # get the prompt
         messages = kwargs["messages"]
-        prompt = ""
-        for message in messages:
-            prompt += message["content"]
-        # create an embedding for prompt
-        router_model_names = (
-            [m["model_name"] for m in llm_model_list]
-            if llm_model_list is not None
-            else []
-        )
-        if llm_router is not None and self.embedding_model in router_model_names:
-            user_api_key = kwargs.get("metadata", {}).get("user_api_key", "")
-            embedding_response = await llm_router.aembedding(
-                model=self.embedding_model,
-                input=prompt,
-                cache={"no-store": True, "no-cache": True},
-                metadata={
-                    "user_api_key": user_api_key,
-                    "semantic-cache-embedding": True,
-                    "trace_id": kwargs.get("metadata", {}).get("trace_id", None),
-                },
-            )
-        else:
-            # convert to embedding
-            embedding_response = await litellm.aembedding(
-                model=self.embedding_model,
-                input=prompt,
-                cache={"no-store": True, "no-cache": True},
-            )
+        prompt = get_str_from_messages(messages)
+        embedding_response = await self._get_async_embedding(prompt, **kwargs)
 
         # get the embedding
         embedding = embedding_response["data"][0]["embedding"]
@@ -332,6 +402,7 @@ class QdrantSemanticCache(BaseCache):
                     "id": str(uuid.uuid4()),
                     "vector": embedding,
                     "payload": {
+                        self.CACHE_KEY_FIELD_NAME: str(key),
                         "text": prompt,
                         "response": value,
                     },
@@ -348,38 +419,12 @@ class QdrantSemanticCache(BaseCache):
 
     async def async_get_cache(self, key, **kwargs):
         print_verbose(f"async qdrant semantic-cache get_cache, kwargs: {kwargs}")
-        from litellm.proxy.proxy_server import llm_model_list, llm_router
 
         # get the messages
         messages = kwargs["messages"]
-        prompt = ""
-        for message in messages:
-            prompt += message["content"]
+        prompt = get_str_from_messages(messages)
 
-        router_model_names = (
-            [m["model_name"] for m in llm_model_list]
-            if llm_model_list is not None
-            else []
-        )
-        if llm_router is not None and self.embedding_model in router_model_names:
-            user_api_key = kwargs.get("metadata", {}).get("user_api_key", "")
-            embedding_response = await llm_router.aembedding(
-                model=self.embedding_model,
-                input=prompt,
-                cache={"no-store": True, "no-cache": True},
-                metadata={
-                    "user_api_key": user_api_key,
-                    "semantic-cache-embedding": True,
-                    "trace_id": kwargs.get("metadata", {}).get("trace_id", None),
-                },
-            )
-        else:
-            # convert to embedding
-            embedding_response = await litellm.aembedding(
-                model=self.embedding_model,
-                input=prompt,
-                cache={"no-store": True, "no-cache": True},
-            )
+        embedding_response = await self._get_async_embedding(prompt, **kwargs)
 
         # get the embedding
         embedding = embedding_response["data"][0]["embedding"]
@@ -396,6 +441,7 @@ class QdrantSemanticCache(BaseCache):
             "limit": 1,
             "with_payload": True,
         }
+        self._add_cache_key_filter_to_search_data(data=data, key=key)
 
         search_response = await self.async_client.post(
             url=f"{self.qdrant_api_base}/collections/{self.collection_name}/points/search",
@@ -414,7 +460,13 @@ class QdrantSemanticCache(BaseCache):
                 return None
 
         similarity = results[0]["score"]
-        cached_prompt = results[0]["payload"]["text"]
+        payload = results[0]["payload"]
+        if not self._payload_matches_cache_key(payload=payload, key=key):
+            print_verbose("Qdrant semantic-cache hit did not match cache key scope")
+            kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
+            return None
+
+        cached_prompt = payload["text"]
 
         # check similarity, if more than self.similarity_threshold, return results
         print_verbose(
@@ -426,7 +478,7 @@ class QdrantSemanticCache(BaseCache):
 
         if similarity >= self.similarity_threshold:
             # cache hit !
-            cached_value = results[0]["payload"]["response"]
+            cached_value = payload["response"]
             print_verbose(
                 f"got a cache hit, similarity: {similarity}, Current prompt: {prompt}, cached_prompt: {cached_prompt}"
             )

litellm/caching/redis_cache.py

@@ -551,6 +551,13 @@ class RedisCache(BaseCache):
     async def async_set_cache(self, key, value, **kwargs):
         from redis.asyncio import Redis
 
+        if key is None:
+            verbose_logger.debug(
+                "LiteLLM Redis Caching: async set() skipped — key is None, value=%r",
+                value,
+            )
+            return None
+
         start_time = time.time()
         try:
             _redis_client: Redis = self.init_async_client()  # type: ignore
@@ -569,8 +576,9 @@ class RedisCache(BaseCache):
                 )
             )
             verbose_logger.error(
-                "LiteLLM Redis Caching: async set() - Got exception from REDIS %s, Writing value=%s",
+                "LiteLLM Redis Caching: async set() - Got exception from REDIS %s, key=%r, value=%r",
                 str(e),
+                key,
                 value,
             )
             raise e

litellm/caching/redis_semantic_cache.py

@@ -35,6 +35,7 @@ class RedisSemanticCache(BaseCache):
     """
 
     DEFAULT_REDIS_INDEX_NAME: str = "litellm_semantic_cache_index"
+    CACHE_KEY_FIELD_NAME: str = "litellm_cache_key"
 
     def __init__(
         self,
@@ -66,8 +67,8 @@ class RedisSemanticCache(BaseCache):
             Exception: If similarity_threshold is not provided or required Redis
                 connection information is missing
         """
-        from redisvl.extensions.llmcache import SemanticCache
-        from redisvl.utils.vectorize import CustomTextVectorizer
+        from redisvl.extensions.llmcache import SemanticCache  # type: ignore[import-not-found, import-untyped]
+        from redisvl.utils.vectorize import CustomTextVectorizer  # type: ignore[import-not-found, import-untyped]
 
         if index_name is None:
             index_name = self.DEFAULT_REDIS_INDEX_NAME
@@ -109,14 +110,94 @@ class RedisSemanticCache(BaseCache):
         # Initialize the Redis vectorizer and cache
         cache_vectorizer = CustomTextVectorizer(self._get_embedding)
 
-        self.llmcache = SemanticCache(
-            name=index_name,
+        self.llmcache = self._init_semantic_cache(
+            semantic_cache_cls=SemanticCache,
+            index_name=index_name,
             redis_url=redis_url,
-            vectorizer=cache_vectorizer,
-            distance_threshold=self.distance_threshold,
-            overwrite=False,
+            cache_vectorizer=cache_vectorizer,
         )
 
+    @classmethod
+    def _cache_key_filterable_field(cls) -> Dict[str, str]:
+        return {
+            "name": cls.CACHE_KEY_FIELD_NAME,
+            "type": "tag",
+        }
+
+    def _init_semantic_cache(
+        self,
+        semantic_cache_cls: Any,
+        index_name: str,
+        redis_url: str,
+        cache_vectorizer: Any,
+    ) -> Any:
+        def _is_schema_mismatch(exc: ValueError) -> bool:
+            error_message = str(exc).lower()
+            return any(
+                phrase in error_message
+                for phrase in ("schema does not match", "index schema")
+            )
+
+        try:
+            return semantic_cache_cls(
+                name=index_name,
+                redis_url=redis_url,
+                vectorizer=cache_vectorizer,
+                distance_threshold=self.distance_threshold,
+                filterable_fields=[self._cache_key_filterable_field()],
+                overwrite=False,
+            )
+        except ValueError as exc:
+            if not _is_schema_mismatch(exc):
+                raise
+
+            isolated_index_name = f"{index_name}_isolated"
+            print_verbose(
+                "Redis semantic-cache existing index schema is not isolated; "
+                f"using isolated index - {isolated_index_name}"
+            )
+            try:
+                return semantic_cache_cls(
+                    name=isolated_index_name,
+                    redis_url=redis_url,
+                    vectorizer=cache_vectorizer,
+                    distance_threshold=self.distance_threshold,
+                    filterable_fields=[self._cache_key_filterable_field()],
+                    overwrite=False,
+                )
+            except ValueError as isolated_exc:
+                if not _is_schema_mismatch(isolated_exc):
+                    raise
+
+                print_verbose(
+                    "Redis semantic-cache isolated index schema is stale; "
+                    f"recreating isolated index - {isolated_index_name}"
+                )
+                return semantic_cache_cls(
+                    name=isolated_index_name,
+                    redis_url=redis_url,
+                    vectorizer=cache_vectorizer,
+                    distance_threshold=self.distance_threshold,
+                    filterable_fields=[self._cache_key_filterable_field()],
+                    overwrite=True,
+                )
+
+    def _get_cache_filters(self, key: str) -> Dict[str, str]:
+        return {self.CACHE_KEY_FIELD_NAME: str(key)}
+
+    def _get_cache_key_filter_expression(self, key: str) -> Any:
+        from redisvl.query.filter import Tag  # type: ignore[import-not-found, import-untyped]
+
+        return Tag(self.CACHE_KEY_FIELD_NAME) == str(key)
+
+    def _cache_hit_matches_key(self, cache_hit: Dict[str, Any], key: str) -> bool:
+        # Pre-isolation entries with no ``litellm_cache_key`` field cannot be
+        # safely reassigned to a caller's scope and are treated as misses.
+        cached_key = cache_hit.get(self.CACHE_KEY_FIELD_NAME)
+        if isinstance(cached_key, bytes):
+            cached_key = cached_key.decode("utf-8")
+        return cached_key is not None and str(cached_key) == str(key)
+
     def _get_ttl(self, **kwargs) -> Optional[int]:
         """
         Get the TTL (time-to-live) value for cache entries.
@@ -188,7 +269,7 @@ class RedisSemanticCache(BaseCache):
         Store a value in the semantic cache.
 
         Args:
-            key: The cache key (not directly used in semantic caching)
+            key: The cache key used to isolate semantic cache entries
             value: The response value to cache
             **kwargs: Additional arguments including 'messages' for the prompt
                 and optional 'ttl' for time-to-live
@@ -206,12 +287,15 @@ class RedisSemanticCache(BaseCache):
             prompt = get_str_from_messages(messages)
             value_str = str(value)
 
+            store_kwargs: Dict[str, Any] = {
+                "filters": self._get_cache_filters(key),
+            }
+
             # Get TTL and store in Redis semantic cache
             ttl = self._get_ttl(**kwargs)
             if ttl is not None:
-                self.llmcache.store(prompt, value_str, ttl=int(ttl))
-            else:
-                self.llmcache.store(prompt, value_str)
+                store_kwargs["ttl"] = int(ttl)
+            self.llmcache.store(prompt, value_str, **store_kwargs)
         except Exception as e:
             print_verbose(
                 f"Error setting {value_str or value} in the Redis semantic cache: {str(e)}"
@@ -222,7 +306,7 @@ class RedisSemanticCache(BaseCache):
         Retrieve a semantically similar cached response.
 
         Args:
-            key: The cache key (not directly used in semantic caching)
+            key: The cache key used to isolate semantic cache entries
             **kwargs: Additional arguments including 'messages' for the prompt
 
         Returns:
@@ -235,18 +319,29 @@ class RedisSemanticCache(BaseCache):
             messages = kwargs.get("messages", [])
             if not messages:
                 print_verbose("No messages provided for semantic cache lookup")
+                kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
                 return None
 
             prompt = get_str_from_messages(messages)
-            # Check the cache for semantically similar prompts
-            results = self.llmcache.check(prompt=prompt)
+            # Check the cache for semantically similar prompts in this exact
+            # LiteLLM cache-key scope.
+            check_kwargs: Dict[str, Any] = {
+                "prompt": prompt,
+                "filter_expression": self._get_cache_key_filter_expression(key),
+            }
+            results = self.llmcache.check(**check_kwargs)
 
             # Return None if no similar prompts found
             if not results:
+                kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
                 return None
 
             # Process the best matching result
             cache_hit = results[0]
+            if not self._cache_hit_matches_key(cache_hit=cache_hit, key=key):
+                print_verbose("Redis semantic-cache hit did not match cache key scope")
+                kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
+                return None
             vector_distance = float(cache_hit["vector_distance"])
 
             # Convert vector distance back to similarity score
@@ -257,6 +352,9 @@ class RedisSemanticCache(BaseCache):
             cached_prompt = cache_hit["prompt"]
             cached_response = cache_hit["response"]
 
+            # update kwargs["metadata"] with similarity, don't rewrite the original metadata
+            kwargs.setdefault("metadata", {})["semantic-similarity"] = similarity
+
             print_verbose(
                 f"Cache hit: similarity threshold: {self.similarity_threshold}, "
                 f"actual similarity: {similarity}, "
@@ -267,6 +365,7 @@ class RedisSemanticCache(BaseCache):
             return self._get_cache_logic(cached_response=cached_response)
         except Exception as e:
             print_verbose(f"Error retrieving from Redis semantic cache: {str(e)}")
+            kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
 
     async def _get_async_embedding(self, prompt: str, **kwargs) -> List[float]:
         """
@@ -321,7 +420,7 @@ class RedisSemanticCache(BaseCache):
         Asynchronously store a value in the semantic cache.
 
         Args:
-            key: The cache key (not directly used in semantic caching)
+            key: The cache key used to isolate semantic cache entries
             value: The response value to cache
             **kwargs: Additional arguments including 'messages' for the prompt
                 and optional 'ttl' for time-to-live
@@ -341,21 +440,20 @@ class RedisSemanticCache(BaseCache):
             # Generate embedding for the value (response) to cache
             prompt_embedding = await self._get_async_embedding(prompt, **kwargs)
 
+            store_kwargs: Dict[str, Any] = {
+                "vector": prompt_embedding,
+                "filters": self._get_cache_filters(key),
+            }
+
             # Get TTL and store in Redis semantic cache
             ttl = self._get_ttl(**kwargs)
             if ttl is not None:
-                await self.llmcache.astore(
-                    prompt,
-                    value_str,
-                    vector=prompt_embedding,  # Pass through custom embedding
-                    ttl=ttl,
-                )
-            else:
-                await self.llmcache.astore(
-                    prompt,
-                    value_str,
-                    vector=prompt_embedding,  # Pass through custom embedding
-                )
+                store_kwargs["ttl"] = ttl
+            await self.llmcache.astore(
+                prompt,
+                value_str,
+                **store_kwargs,
+            )
         except Exception as e:
             print_verbose(f"Error in async_set_cache: {str(e)}")
 
@@ -364,7 +462,7 @@ class RedisSemanticCache(BaseCache):
         Asynchronously retrieve a semantically similar cached response.
 
         Args:
-            key: The cache key (not directly used in semantic caching)
+            key: The cache key used to isolate semantic cache entries
             **kwargs: Additional arguments including 'messages' for the prompt
 
         Returns:
@@ -385,17 +483,25 @@ class RedisSemanticCache(BaseCache):
             # Generate embedding for the prompt
             prompt_embedding = await self._get_async_embedding(prompt, **kwargs)
 
-            # Check the cache for semantically similar prompts
-            results = await self.llmcache.acheck(prompt=prompt, vector=prompt_embedding)
+            # Check the cache for semantically similar prompts in this exact
+            # LiteLLM cache-key scope.
+            check_kwargs: Dict[str, Any] = {
+                "prompt": prompt,
+                "vector": prompt_embedding,
+                "filter_expression": self._get_cache_key_filter_expression(key),
+            }
+            results = await self.llmcache.acheck(**check_kwargs)
 
             # handle results / cache hit
             if not results:
-                kwargs.setdefault("metadata", {})[
-                    "semantic-similarity"
-                ] = 0.0  # TODO why here but not above??
+                kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
                 return None
 
             cache_hit = results[0]
+            if not self._cache_hit_matches_key(cache_hit=cache_hit, key=key):
+                print_verbose("Redis semantic-cache hit did not match cache key scope")
+                kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0
+                return None
             vector_distance = float(cache_hit["vector_distance"])
 
             # Convert vector distance back to similarity

litellm/constants.py

@@ -202,6 +202,12 @@ DEFAULT_REASONING_EFFORT_MEDIUM_THINKING_BUDGET = int(
 DEFAULT_REASONING_EFFORT_HIGH_THINKING_BUDGET = int(
     os.getenv("DEFAULT_REASONING_EFFORT_HIGH_THINKING_BUDGET", 4096)
 )
+DEFAULT_REASONING_EFFORT_XHIGH_THINKING_BUDGET = int(
+    os.getenv("DEFAULT_REASONING_EFFORT_XHIGH_THINKING_BUDGET", 8192)
+)
+DEFAULT_REASONING_EFFORT_MAX_THINKING_BUDGET = int(
+    os.getenv("DEFAULT_REASONING_EFFORT_MAX_THINKING_BUDGET", 16384)
+)
 MAX_TOKEN_TRIMMING_ATTEMPTS = int(
     os.getenv("MAX_TOKEN_TRIMMING_ATTEMPTS", 10)
 )  # Maximum number of attempts to trim the message
@@ -399,6 +405,8 @@ BEDROCK_MAX_POLICY_SIZE = int(os.getenv("BEDROCK_MAX_POLICY_SIZE", 75))
 BEDROCK_MIN_THINKING_BUDGET_TOKENS = int(
     os.getenv("BEDROCK_MIN_THINKING_BUDGET_TOKENS", 1024)
 )
+# Anthropic's Messages API rejects thinking.budget_tokens < 1024.
+ANTHROPIC_MIN_THINKING_BUDGET_TOKENS = 1024
 REPLICATE_POLLING_DELAY_SECONDS = float(
     os.getenv("REPLICATE_POLLING_DELAY_SECONDS", 0.5)
 )
@@ -419,9 +427,6 @@ CACHED_STREAMING_CHUNK_DELAY = float(os.getenv("CACHED_STREAMING_CHUNK_DELAY", 0
 AUDIO_SPEECH_CHUNK_SIZE = int(
     os.getenv("AUDIO_SPEECH_CHUNK_SIZE", 8192)
 )  # chunk_size for audio speech streaming. Balance between latency and memory usage
-MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB = int(
-    os.getenv("MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB", 512)
-)
 DEFAULT_MAX_TOKENS_FOR_TRITON = int(os.getenv("DEFAULT_MAX_TOKENS_FOR_TRITON", 2000))
 #### Networking settings ####
 # Sentinel used when `REQUEST_TIMEOUT` is unset: `litellm.request_timeout` keeps this

litellm/cost_calculator.py

@@ -513,7 +513,10 @@ def cost_per_token(  # noqa: PLR0915
         return fireworks_ai_cost_per_token(model=model, usage=usage_block)
     elif custom_llm_provider == "azure":
         return azure_openai_cost_per_token(
-            model=model, usage=usage_block, response_time_ms=response_time_ms
+            model=model,
+            usage=usage_block,
+            response_time_ms=response_time_ms,
+            service_tier=service_tier,
         )
     elif custom_llm_provider == "gemini":
         return gemini_cost_per_token(
@@ -539,6 +542,7 @@ def cost_per_token(  # noqa: PLR0915
             usage=usage_block,
             response_time_ms=response_time_ms,
             request_model=request_model,
+            service_tier=service_tier,
         )
     else:
         model_info = _cached_get_model_info_helper(

litellm/files/main.py

@@ -10,6 +10,7 @@ import contextvars
 import time
 import uuid as uuid_module
 from functools import partial
+from types import MappingProxyType
 from typing import Any, Coroutine, Dict, Literal, Optional, Union, cast
 
 import httpx
@@ -85,6 +86,16 @@ bedrock_files_instance = BedrockFilesHandler()
 #################################################
 
 
+def _add_trusted_model_credentials_to_litellm_params(
+    litellm_params_dict: Dict[str, Any], kwargs: Dict[str, Any]
+) -> None:
+    trusted_model_credentials = kwargs.get("_litellm_internal_model_credentials")
+    if isinstance(trusted_model_credentials, type(MappingProxyType({}))):
+        litellm_params_dict["_litellm_internal_model_credentials"] = (
+            trusted_model_credentials
+        )
+
+
 @client
 async def acreate_file(
     file: FileTypes,
@@ -373,6 +384,10 @@ def file_retrieve(
             )
             if provider_config is not None:
                 litellm_params_dict = get_litellm_params(**kwargs)
+                _add_trusted_model_credentials_to_litellm_params(
+                    litellm_params_dict=litellm_params_dict,
+                    kwargs=kwargs,
+                )
                 litellm_params_dict["api_key"] = optional_params.api_key
                 litellm_params_dict["api_base"] = optional_params.api_base
 
@@ -497,6 +512,10 @@ def file_delete(
             pass
         optional_params = GenericLiteLLMParams(**kwargs)
         litellm_params_dict = get_litellm_params(**kwargs)
+        _add_trusted_model_credentials_to_litellm_params(
+            litellm_params_dict=litellm_params_dict,
+            kwargs=kwargs,
+        )
         ### TIMEOUT LOGIC ###
         timeout = optional_params.timeout or kwargs.get("request_timeout", 600) or 600
         # set timeout for 10 minutes by default
@@ -846,6 +865,10 @@ def file_content(
     try:
         optional_params = GenericLiteLLMParams(**kwargs)
         litellm_params_dict = get_litellm_params(**kwargs)
+        _add_trusted_model_credentials_to_litellm_params(
+            litellm_params_dict=litellm_params_dict,
+            kwargs=kwargs,
+        )
         ### TIMEOUT LOGIC ###
         timeout = optional_params.timeout or kwargs.get("request_timeout", 600) or 600
         client = kwargs.get("client")
@@ -993,6 +1016,7 @@ def file_content(
                 vertex_location=vertex_ai_location,
                 timeout=timeout,
                 max_retries=optional_params.max_retries,
+                litellm_params=litellm_params_dict,
             )
         elif custom_llm_provider == "bedrock":
             response = bedrock_files_instance.file_content(

litellm/integrations/arize/_utils.py

@@ -220,23 +220,57 @@ def _set_structured_outputs(span: "Span", response_obj, msg_attrs, span_attrs):
             safe_set_attribute(span, f"{prefix}.{msg_attrs.MESSAGE_ROLE}", message_role)
 
 
+def _safe_get(obj, key, default=None):
+    """Read ``key`` from a dict-like or Pydantic-model-like object.
+
+    The arize/langfuse_otel logger receives ``usage`` objects from many sources:
+    plain dicts, litellm ``Usage`` (which exposes ``.get``), and raw OpenAI
+    Pydantic models (e.g. ``openai.types.completion_usage.CompletionUsage`` and
+    nested ``CompletionTokensDetails`` / ``OutputTokensDetails``) which do NOT
+    expose ``.get``. Calling ``.get`` on the latter raised ``AttributeError`` —
+    see https://github.com/BerriAI/litellm/issues/13672.
+    """
+    if obj is None:
+        return default
+    getter = getattr(obj, "get", None)
+    if callable(getter):
+        try:
+            return getter(key, default)
+        except TypeError:
+            # Some objects expose `.get` with a different signature
+            pass
+    return getattr(obj, key, default)
+
+
 def _set_usage_outputs(span: "Span", response_obj, span_attrs):
     usage = response_obj and response_obj.get("usage")
     if not usage:
         return
 
     safe_set_attribute(
-        span, span_attrs.LLM_TOKEN_COUNT_TOTAL, usage.get("total_tokens")
+        span, span_attrs.LLM_TOKEN_COUNT_TOTAL, _safe_get(usage, "total_tokens")
+    )
+    completion_tokens = _safe_get(usage, "completion_tokens") or _safe_get(
+        usage, "output_tokens"
     )
-    completion_tokens = usage.get("completion_tokens") or usage.get("output_tokens")
     if completion_tokens:
         safe_set_attribute(
             span, span_attrs.LLM_TOKEN_COUNT_COMPLETION, completion_tokens
         )
-    prompt_tokens = usage.get("prompt_tokens") or usage.get("input_tokens")
+    prompt_tokens = _safe_get(usage, "prompt_tokens") or _safe_get(
+        usage, "input_tokens"
+    )
     if prompt_tokens:
         safe_set_attribute(span, span_attrs.LLM_TOKEN_COUNT_PROMPT, prompt_tokens)
-    reasoning_tokens = usage.get("output_tokens_details", {}).get("reasoning_tokens")
+
+    # Reasoning tokens live in `completion_tokens_details` for Chat Completions
+    # API (Usage) and in `output_tokens_details` for Responses API
+    # (ResponseAPIUsage). Both nested objects may be plain Pydantic models
+    # without `.get`.
+    token_details = _safe_get(usage, "completion_tokens_details") or _safe_get(
+        usage, "output_tokens_details"
+    )
+    reasoning_tokens = _safe_get(token_details, "reasoning_tokens")
     if reasoning_tokens:
         safe_set_attribute(
             span,

litellm/integrations/arize/arize_phoenix_client.py

@@ -2,11 +2,23 @@
 Arize Phoenix API client for fetching prompt versions from Arize Phoenix.
 """
 
+import urllib.parse
 from typing import Any, Dict, Optional
 
 from litellm.llms.custom_httpx.http_handler import HTTPHandler
 
 
+def _sanitize_id(identifier: str) -> str:
+    """Reject path traversal characters and URL-encode the identifier."""
+    if any(c in identifier for c in ("/", "\\", "#", "?")):
+        raise ValueError(
+            f"Invalid identifier {identifier!r}: contains disallowed characters"
+        )
+    if ".." in identifier:
+        raise ValueError(f"Invalid identifier {identifier!r}: path traversal detected")
+    return urllib.parse.quote(identifier, safe="")
+
+
 class ArizePhoenixClient:
     """
     Client for interacting with Arize Phoenix API to fetch prompt versions.
@@ -53,7 +65,8 @@ class ArizePhoenixClient:
         Returns:
             Dictionary containing prompt version data, or None if not found
         """
-        url = f"{self.api_base}/v1/prompt_versions/{prompt_version_id}"
+        safe_id = _sanitize_id(prompt_version_id)
+        url = f"{self.api_base}/v1/prompt_versions/{safe_id}"
 
         try:
             # Use the underlying httpx client directly to avoid query param extraction

litellm/integrations/bitbucket/bitbucket_client.py

@@ -3,11 +3,27 @@ BitBucket API client for fetching .prompt files from BitBucket repositories.
 """
 
 import base64
+import urllib.parse
 from typing import Any, Dict, List, Optional
 
 from litellm.llms.custom_httpx.http_handler import HTTPHandler
 
 
+def _sanitize_file_path(file_path: str) -> str:
+    """Reject path traversal and URL-encode each path segment."""
+    if "#" in file_path or "?" in file_path:
+        raise ValueError(
+            f"Invalid file path {file_path!r}: contains URL special characters"
+        )
+    parts = file_path.split("/")
+    for part in parts:
+        if part == "..":
+            raise ValueError(
+                f"Invalid file path {file_path!r}: path traversal detected"
+            )
+    return "/".join(urllib.parse.quote(part, safe="") for part in parts)
+
+
 class BitBucketClient:
     """
     Client for interacting with BitBucket API to fetch .prompt files.
@@ -72,7 +88,8 @@ class BitBucketClient:
         Returns:
             File content as string, or None if file not found
         """
-        url = f"{self.base_url}/repositories/{self.workspace}/{self.repository}/src/{self.branch}/{file_path}"
+        safe_path = _sanitize_file_path(file_path)
+        url = f"{self.base_url}/repositories/{self.workspace}/{self.repository}/src/{self.branch}/{safe_path}"
 
         try:
             response = self.http_handler.get(url, headers=self.headers)
@@ -119,7 +136,8 @@ class BitBucketClient:
         Returns:
             List of file paths
         """
-        url = f"{self.base_url}/repositories/{self.workspace}/{self.repository}/src/{self.branch}/{directory_path}"
+        safe_dir = _sanitize_file_path(directory_path) if directory_path else ""
+        url = f"{self.base_url}/repositories/{self.workspace}/{self.repository}/src/{self.branch}/{safe_dir}"
 
         try:
             response = self.http_handler.get(url, headers=self.headers)
@@ -211,7 +229,8 @@ class BitBucketClient:
         Returns:
             Dictionary containing file metadata, or None if file not found
         """
-        url = f"{self.base_url}/repositories/{self.workspace}/{self.repository}/src/{self.branch}/{file_path}"
+        safe_path = _sanitize_file_path(file_path)
+        url = f"{self.base_url}/repositories/{self.workspace}/{self.repository}/src/{self.branch}/{safe_path}"
 
         try:
             # Use GET with Range header to get just the headers (HEAD equivalent)

litellm/integrations/custom_sso_handler.py

@@ -18,6 +18,17 @@ class CustomSSOLoginHandler(CustomLogger):
         self,
         request: Request,
     ) -> OpenID:
+        from litellm.proxy.auth.trusted_proxy_utils import (
+            require_trusted_proxy_request,
+        )
+        from litellm.proxy.proxy_server import general_settings
+
+        require_trusted_proxy_request(
+            request=request,
+            general_settings=general_settings,
+            feature_name="Custom UI SSO",
+        )
+
         request_headers_dict = dict(request.headers)
         return OpenID(
             id=request_headers_dict.get("x-litellm-user-id"),

litellm/integrations/gcs_bucket/gcs_bucket.py

@@ -6,12 +6,14 @@ import time
 from litellm._uuid import uuid
 from datetime import datetime, timedelta, timezone
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
-from urllib.parse import quote
 
 from litellm._logging import verbose_logger
 from litellm.constants import LITELLM_ASYNCIO_QUEUE_MAXSIZE
 from litellm.integrations.additional_logging_utils import AdditionalLoggingUtils
 from litellm.integrations.gcs_bucket.gcs_bucket_base import GCSBucketBase
+from litellm.litellm_core_utils.cloud_storage_security import (
+    sanitize_cloud_object_component,
+)
 from litellm.proxy._types import CommonProxyErrors
 from litellm.types.integrations.base_health_check import IntegrationHealthCheckStatus
 from litellm.types.integrations.gcs_bucket import *
@@ -335,7 +337,11 @@ class GCSBucketLogger(GCSBucketBase, AdditionalLoggingUtils):
         _litellm_params = kwargs.get("litellm_params", None) or {}
         _metadata = _litellm_params.get("metadata", None) or {}
         if "gcs_log_id" in _metadata:
-            object_name = _metadata["gcs_log_id"]
+            safe_log_id = sanitize_cloud_object_component(
+                _metadata.get("gcs_log_id"), fallback=""
+            )
+            if safe_log_id:
+                object_name = f"{current_date}/custom-{uuid.uuid4().hex}-{safe_log_id}"
 
         return object_name
 
@@ -367,8 +373,7 @@ class GCSBucketLogger(GCSBucketBase, AdditionalLoggingUtils):
                     request_date_str=date_str,
                     response_id=request_id,
                 )
-                encoded_object_name = quote(object_name, safe="")
-                response = await self.download_gcs_object(encoded_object_name)
+                response = await self.download_gcs_object(object_name)
 
                 if response is not None:
                     loaded_response = json.loads(response)

litellm/integrations/gcs_bucket/gcs_bucket_base.py

@@ -11,6 +11,10 @@ from litellm.integrations.gcs_bucket.gcs_bucket_mock_client import (
 
 from litellm._logging import verbose_logger
 from litellm.integrations.custom_batch_logger import CustomBatchLogger
+from litellm.litellm_core_utils.cloud_storage_security import (
+    encode_gcs_object_name_for_url,
+    split_configured_cloud_bucket_name,
+)
 from litellm.llms.custom_httpx.http_handler import (
     get_async_httpx_client,
     httpxSpecialProvider,
@@ -133,8 +137,8 @@ class GCSBucketBase(CustomBatchLogger):
             - Returns: bucket_name="my-bucket", object_name="my-folder/dev/my-object"
 
         """
-        if "/" in bucket_name:
-            bucket_name, prefix = bucket_name.split("/", 1)
+        bucket_name, prefix = split_configured_cloud_bucket_name(bucket_name)
+        if prefix:
             object_name = f"{prefix}/{object_name}"
             return bucket_name, object_name
         return bucket_name, object_name
@@ -248,6 +252,7 @@ class GCSBucketBase(CustomBatchLogger):
                 bucket_name=bucket_name,
                 object_name=object_name,
             )
+            object_name = encode_gcs_object_name_for_url(object_name)
 
             url = f"https://storage.googleapis.com/storage/v1/b/{bucket_name}/o/{object_name}?alt=media"
 
@@ -288,6 +293,7 @@ class GCSBucketBase(CustomBatchLogger):
                 bucket_name=bucket_name,
                 object_name=object_name,
             )
+            object_name = encode_gcs_object_name_for_url(object_name)
 
             url = f"https://storage.googleapis.com/storage/v1/b/{bucket_name}/o/{object_name}"
 
@@ -334,10 +340,11 @@ class GCSBucketBase(CustomBatchLogger):
             bucket_name=bucket_name,
             object_name=object_name,
         )
+        encoded_object_name = encode_gcs_object_name_for_url(object_name)
 
         response = await self.async_httpx_client.post(
             headers=headers,
-            url=f"https://storage.googleapis.com/upload/storage/v1/b/{bucket_name}/o?uploadType=media&name={object_name}",
+            url=f"https://storage.googleapis.com/upload/storage/v1/b/{bucket_name}/o?uploadType=media&name={encoded_object_name}",
             data=json_logged_payload,
         )
 

litellm/integrations/langfuse/langfuse.py

@@ -90,6 +90,29 @@ def _extract_cache_read_input_tokens(usage_obj) -> int:
     return cache_read_input_tokens
 
 
+def resolve_langfuse_credentials(
+    langfuse_public_key=None,
+    langfuse_secret=None,
+    langfuse_secret_key=None,
+    langfuse_host=None,
+    allow_env_credentials: bool = True,
+):
+    if allow_env_credentials is False and langfuse_host is not None:
+        secret_key = langfuse_secret or langfuse_secret_key
+        public_key = langfuse_public_key
+    else:
+        secret_key = (
+            langfuse_secret or langfuse_secret_key or os.getenv("LANGFUSE_SECRET_KEY")
+        )
+        public_key = langfuse_public_key or os.getenv("LANGFUSE_PUBLIC_KEY")
+
+    resolved_host = langfuse_host or os.getenv(
+        "LANGFUSE_HOST", "https://cloud.langfuse.com"
+    )
+
+    return public_key, secret_key, resolved_host
+
+
 class LangFuseLogger:
     # Class variables or attributes
     def __init__(
@@ -98,6 +121,7 @@ class LangFuseLogger:
         langfuse_secret=None,
         langfuse_host=None,
         flush_interval=1,
+        allow_env_credentials: bool = True,
     ):
         try:
             import langfuse
@@ -106,11 +130,13 @@ class LangFuseLogger:
             raise Exception(
                 f"\033[91mLangfuse not installed, try running 'pip install langfuse' to fix this error: {e}\n{traceback.format_exc()}\033[0m"
             )
-        # Instance variables
-        self.secret_key = langfuse_secret or os.getenv("LANGFUSE_SECRET_KEY")
-        self.public_key = langfuse_public_key or os.getenv("LANGFUSE_PUBLIC_KEY")
-        self.langfuse_host = langfuse_host or os.getenv(
-            "LANGFUSE_HOST", "https://cloud.langfuse.com"
+        self.public_key, self.secret_key, self.langfuse_host = (
+            resolve_langfuse_credentials(
+                langfuse_public_key=langfuse_public_key,
+                langfuse_secret=langfuse_secret,
+                langfuse_host=langfuse_host,
+                allow_env_credentials=allow_env_credentials,
+            )
         )
         if not (
             self.langfuse_host.startswith("http://")
@@ -160,9 +186,10 @@ class LangFuseLogger:
                 project_id = None
 
         if os.getenv("UPSTREAM_LANGFUSE_SECRET_KEY") is not None:
+            upstream_langfuse_debug_env = os.getenv("UPSTREAM_LANGFUSE_DEBUG")
             upstream_langfuse_debug = (
-                str_to_bool(self.upstream_langfuse_debug)
-                if self.upstream_langfuse_debug is not None
+                str_to_bool(upstream_langfuse_debug_env)
+                if upstream_langfuse_debug_env is not None
                 else None
             )
             self.upstream_langfuse_secret_key = os.getenv(
@@ -173,7 +200,7 @@ class LangFuseLogger:
             )
             self.upstream_langfuse_host = os.getenv("UPSTREAM_LANGFUSE_HOST")
             self.upstream_langfuse_release = os.getenv("UPSTREAM_LANGFUSE_RELEASE")
-            self.upstream_langfuse_debug = os.getenv("UPSTREAM_LANGFUSE_DEBUG")
+            self.upstream_langfuse_debug = upstream_langfuse_debug_env
             self.upstream_langfuse = Langfuse(
                 public_key=self.upstream_langfuse_public_key,
                 secret_key=self.upstream_langfuse_secret_key,

litellm/integrations/langfuse/langfuse_handler.py

@@ -115,8 +115,10 @@ class LangFuseHandler:
 
         langfuse_logger = LangFuseLogger(
             langfuse_public_key=credentials.get("langfuse_public_key"),
-            langfuse_secret=credentials.get("langfuse_secret"),
+            langfuse_secret=credentials.get("langfuse_secret")
+            or credentials.get("langfuse_secret_key"),
             langfuse_host=credentials.get("langfuse_host"),
+            allow_env_credentials=credentials.get("langfuse_host") is None,
         )
         in_memory_dynamic_logger_cache.set_cache(
             credentials=credentials,

litellm/integrations/langfuse/langfuse_prompt_management.py

@@ -20,7 +20,7 @@ from ...litellm_core_utils.specialty_caches.dynamic_logging_cache import (
     DynamicLoggingCache,
 )
 from ..prompt_management_base import PromptManagementBase
-from .langfuse import LangFuseLogger
+from .langfuse import LangFuseLogger, resolve_langfuse_credentials
 from .langfuse_handler import LangFuseHandler
 
 if TYPE_CHECKING:
@@ -46,6 +46,7 @@ def langfuse_client_init(
     langfuse_secret_key=None,
     langfuse_host=None,
     flush_interval=1,
+    allow_env_credentials: bool = True,
 ) -> LangfuseClass:
     """
     Initialize Langfuse client with caching to prevent multiple initializations.
@@ -70,14 +71,12 @@ def langfuse_client_init(
             f"\033[91mLangfuse not installed, try running 'pip install langfuse' to fix this error: {e}\n\033[0m"
         )
 
-    # Instance variables
-
-    secret_key = (
-        langfuse_secret or langfuse_secret_key or os.getenv("LANGFUSE_SECRET_KEY")
-    )
-    public_key = langfuse_public_key or os.getenv("LANGFUSE_PUBLIC_KEY")
-    langfuse_host = langfuse_host or os.getenv(
-        "LANGFUSE_HOST", "https://cloud.langfuse.com"
+    public_key, secret_key, langfuse_host = resolve_langfuse_credentials(
+        langfuse_public_key=langfuse_public_key,
+        langfuse_secret=langfuse_secret,
+        langfuse_secret_key=langfuse_secret_key,
+        langfuse_host=langfuse_host,
+        allow_env_credentials=allow_env_credentials,
     )
 
     if not (
@@ -222,6 +221,7 @@ class LangfusePromptManagement(LangFuseLogger, PromptManagementBase, CustomLogge
             langfuse_secret=dynamic_callback_params.get("langfuse_secret"),
             langfuse_secret_key=dynamic_callback_params.get("langfuse_secret_key"),
             langfuse_host=dynamic_callback_params.get("langfuse_host"),
+            allow_env_credentials=dynamic_callback_params.get("langfuse_host") is None,
         )
         langfuse_prompt_client = self._get_prompt_from_id(
             langfuse_prompt_id=prompt_id,
@@ -246,6 +246,7 @@ class LangfusePromptManagement(LangFuseLogger, PromptManagementBase, CustomLogge
             langfuse_secret=dynamic_callback_params.get("langfuse_secret"),
             langfuse_secret_key=dynamic_callback_params.get("langfuse_secret_key"),
             langfuse_host=dynamic_callback_params.get("langfuse_host"),
+            allow_env_credentials=dynamic_callback_params.get("langfuse_host") is None,
         )
         langfuse_prompt_client = self._get_prompt_from_id(
             langfuse_prompt_id=prompt_id,

litellm/integrations/langsmith.py

@@ -19,6 +19,7 @@ from litellm.integrations.langsmith_mock_client import (
     create_mock_langsmith_client,
     should_use_langsmith_mock,
 )
+from litellm.litellm_core_utils.redact_messages import redact_user_api_key_info
 from litellm.llms.custom_httpx.http_handler import (
     get_async_httpx_client,
     httpxSpecialProvider,
@@ -112,17 +113,28 @@ class LangsmithLogger(CustomBatchLogger):
         langsmith_project: Optional[str] = None,
         langsmith_base_url: Optional[str] = None,
         langsmith_tenant_id: Optional[str] = None,
+        allow_env_credentials: bool = True,
     ) -> LangsmithCredentialsObject:
-        _credentials_api_key = langsmith_api_key or os.getenv("LANGSMITH_API_KEY")
-        _credentials_project = (
-            langsmith_project or os.getenv("LANGSMITH_PROJECT") or "litellm-completion"
-        )
-        _credentials_base_url = (
-            langsmith_base_url
-            or os.getenv("LANGSMITH_BASE_URL")
-            or "https://api.smith.langchain.com"
-        )
-        _credentials_tenant_id = langsmith_tenant_id or os.getenv("LANGSMITH_TENANT_ID")
+        if allow_env_credentials is False and langsmith_base_url is not None:
+            _credentials_api_key = langsmith_api_key
+            _credentials_project = langsmith_project or "litellm-completion"
+            _credentials_base_url = langsmith_base_url
+            _credentials_tenant_id = langsmith_tenant_id
+        else:
+            _credentials_api_key = langsmith_api_key or os.getenv("LANGSMITH_API_KEY")
+            _credentials_project = (
+                langsmith_project
+                or os.getenv("LANGSMITH_PROJECT")
+                or "litellm-completion"
+            )
+            _credentials_base_url = (
+                langsmith_base_url
+                or os.getenv("LANGSMITH_BASE_URL")
+                or "https://api.smith.langchain.com"
+            )
+            _credentials_tenant_id = langsmith_tenant_id or os.getenv(
+                "LANGSMITH_TENANT_ID"
+            )
 
         return LangsmithCredentialsObject(
             LANGSMITH_API_KEY=_credentials_api_key,
@@ -153,6 +165,15 @@ class LangsmithLogger(CustomBatchLogger):
             for key in ("session_id", "thread_id", "conversation_id"):
                 if key in requester_metadata and key not in extra_metadata:
                     extra_metadata[key] = requester_metadata[key]
+
+        # helper is shallow; also scrub nested requester_metadata since
+        # LangSmith forwards the whole dict into `extra`
+        extra_metadata = redact_user_api_key_info(metadata=extra_metadata)
+        nested = extra_metadata.get("requester_metadata")
+        if isinstance(nested, dict):
+            extra_metadata["requester_metadata"] = redact_user_api_key_info(
+                metadata=nested
+            )
         return extra_metadata
 
     def _build_outputs_with_usage(
@@ -540,6 +561,10 @@ class LangsmithLogger(CustomBatchLogger):
                 langsmith_tenant_id=standard_callback_dynamic_params.get(
                     "langsmith_tenant_id", None
                 ),
+                allow_env_credentials=standard_callback_dynamic_params.get(
+                    "langsmith_base_url", None
+                )
+                is None,
             )
         else:
             credentials = self.default_credentials

litellm/integrations/opentelemetry.py

@@ -69,6 +69,8 @@ class OpenTelemetryConfig:
     deployment_environment: Optional[str] = None
     model_id: Optional[str] = None
     ignore_context_propagation: Optional[bool] = None
+    # When True, create a private TracerProvider instead of reusing or setting the global one.
+    skip_set_global: bool = False
 
     def __post_init__(self) -> None:
         # If endpoint is specified but exporter is still the default "console",
@@ -259,16 +261,21 @@ class OpenTelemetry(CustomLogger):
         try:
             existing_provider = get_existing_provider_fn()
 
-            # If a real SDK provider exists (set by another SDK like Langfuse), use it
-            # This uses a positive check for SDK providers instead of a negative check for proxy providers
             if isinstance(existing_provider, sdk_provider_class):
-                verbose_logger.debug(
-                    "OpenTelemetry: Using existing %s: %s",
-                    provider_name,
-                    type(existing_provider).__name__,
-                )
-                provider = existing_provider
-                # Don't call set_provider to preserve existing context
+                if skip_set_global:
+                    verbose_logger.debug(
+                        "OpenTelemetry: existing %s found but skip_set_global=True; creating private %s for isolation",
+                        provider_name,
+                        provider_name,
+                    )
+                    provider = create_new_provider_fn()
+                else:
+                    verbose_logger.debug(
+                        "OpenTelemetry: Using existing %s: %s",
+                        provider_name,
+                        type(existing_provider).__name__,
+                    )
+                    provider = existing_provider
             else:
                 # Default proxy provider or unknown type, create our own
                 verbose_logger.debug("OpenTelemetry: Creating new %s", provider_name)
@@ -293,6 +300,12 @@ class OpenTelemetry(CustomLogger):
 
         return provider
 
+    def _skip_set_global(self) -> bool:
+        # langfuse_otel relies on the Langfuse SDK's providers; don't overwrite them.
+        return self.config.skip_set_global or (
+            hasattr(self, "callback_name") and self.callback_name == "langfuse_otel"
+        )
+
     def _init_tracing(self, tracer_provider):
         from opentelemetry import trace
         from opentelemetry.sdk.trace import TracerProvider
@@ -303,11 +316,6 @@ class OpenTelemetry(CustomLogger):
             provider.add_span_processor(self._get_span_processor())
             return provider
 
-        # CRITICAL FIX: For Langfuse OTEL, skip setting global provider to prevent interference
-        skip_global = (
-            hasattr(self, "callback_name") and self.callback_name == "langfuse_otel"
-        )
-
         tracer_provider = self._get_or_create_provider(
             provider=tracer_provider,
             provider_name="TracerProvider",
@@ -315,16 +323,18 @@ class OpenTelemetry(CustomLogger):
             sdk_provider_class=TracerProvider,
             create_new_provider_fn=create_tracer_provider,
             set_provider_fn=trace.set_tracer_provider,
-            skip_set_global=skip_global,
+            skip_set_global=self._skip_set_global(),
         )
 
         # Grab our tracer from the TracerProvider (not from global context)
         # This ensures we use the provided TracerProvider (e.g., for testing)
         self.tracer = tracer_provider.get_tracer(LITELLM_TRACER_NAME)
+        self._tracer_provider = tracer_provider
         self.span_kind = SpanKind
 
     def _init_metrics(self, meter_provider):
         if not self.config.enable_metrics:
+            self._meter_provider = None
             self._operation_duration_histogram = None
             self._token_usage_histogram = None
             self._cost_histogram = None
@@ -350,7 +360,9 @@ class OpenTelemetry(CustomLogger):
             sdk_provider_class=MeterProvider,
             create_new_provider_fn=create_meter_provider,
             set_provider_fn=metrics.set_meter_provider,
+            skip_set_global=self._skip_set_global(),
         )
+        self._meter_provider = meter_provider
 
         meter = meter_provider.get_meter(__name__)
 
@@ -388,6 +400,7 @@ class OpenTelemetry(CustomLogger):
     def _init_logs(self, logger_provider):
         # nothing to do if events disabled
         if not self.config.enable_events:
+            self._logger_provider = None
             return
 
         from opentelemetry._logs import get_logger_provider, set_logger_provider
@@ -404,13 +417,14 @@ class OpenTelemetry(CustomLogger):
             )
             return provider
 
-        self._get_or_create_provider(
+        self._logger_provider = self._get_or_create_provider(
             provider=logger_provider,
             provider_name="LoggerProvider",
             get_existing_provider_fn=get_logger_provider,
             sdk_provider_class=OTLoggerProvider,
             create_new_provider_fn=create_logger_provider,
             set_provider_fn=set_logger_provider,
+            skip_set_global=self._skip_set_global(),
         )
 
     def log_success_event(self, kwargs, response_obj, start_time, end_time):
@@ -1073,7 +1087,7 @@ class OpenTelemetry(CustomLogger):
         # See: https://github.com/open-telemetry/opentelemetry-python/pull/4676
         # TODO: Refactor to use the proper OTEL Logs API instead of directly creating SDK LogRecords
 
-        from opentelemetry._logs import SeverityNumber, get_logger
+        from opentelemetry._logs import SeverityNumber
 
         try:
             from opentelemetry.sdk._logs import (  # type: ignore[attr-defined]  # OTEL < 1.39.0
@@ -1084,7 +1098,10 @@ class OpenTelemetry(CustomLogger):
                 LogRecord as SdkLogRecord,  # type: ignore[attr-defined]  # OTEL >= 1.39.0
             )
 
-        otel_logger = get_logger(LITELLM_LOGGER_NAME)
+        # Resolve through the handler's own LoggerProvider (which may be a
+        # private one when skip_set_global=True) rather than the module-level
+        # get_logger() which always goes through the global provider.
+        otel_logger = self._logger_provider.get_logger(LITELLM_LOGGER_NAME)
 
         parent_ctx = span.get_span_context()
         provider = (kwargs.get("litellm_params") or {}).get(

litellm/integrations/prometheus.py

@@ -265,6 +265,7 @@ class PrometheusLogger(CustomLogger):
             ########################################
             # LiteLLM Virtual API KEY metrics
             ########################################
+
             # Remaining MODEL RPM limit for API Key
             self.litellm_remaining_api_key_requests_for_model = self._gauge_factory(
                 "litellm_remaining_api_key_requests_for_model",
@@ -1928,7 +1929,7 @@ class PrometheusLogger(CustomLogger):
             or _litellm_params_metadata.get("user_agent"),
         }
 
-    def set_llm_deployment_failure_metrics(self, request_kwargs: dict):
+    def set_llm_deployment_failure_metrics(self, request_kwargs: dict):  # noqa: PLR0915
         """
         Sets Failure metrics when an LLM API call fails
 
@@ -2006,17 +2007,32 @@ class PrometheusLogger(CustomLogger):
                     if code is not None:
                         exception_status = str(code)
 
-            # Create enum_values for the label factory (always create for use in different metrics)
+            # On LiteLLM-side rejects (no deployment picked), route request_kwargs["model"]
+            # into requested_model and leave deployment-scoped labels empty.
+            deployment_selected = bool(model_id)
+            if deployment_selected:
+                label_litellm_model_name = litellm_model_name
+                label_model_id = model_id
+                label_api_base = api_base
+                label_api_provider = llm_provider
+                label_requested_model = model_group or litellm_model_name
+            else:
+                label_litellm_model_name = ""
+                label_model_id = ""
+                label_api_base = ""
+                label_api_provider = ""
+                label_requested_model = litellm_model_name or model_group or ""
+
             enum_values = UserAPIKeyLabelValues(
-                litellm_model_name=litellm_model_name,
-                model_id=model_id,
-                api_base=api_base,
-                api_provider=llm_provider,
+                litellm_model_name=label_litellm_model_name,
+                model_id=label_model_id,
+                api_base=label_api_base,
+                api_provider=label_api_provider,
                 exception_status=exception_status,
                 exception_class=(
                     self._get_exception_class_name(exception) if exception else None
                 ),
-                requested_model=model_group or litellm_model_name,
+                requested_model=label_requested_model,
                 hashed_api_key=hashed_api_key,
                 api_key_alias=api_key_alias,
                 team=team,
@@ -2030,12 +2046,14 @@ class PrometheusLogger(CustomLogger):
             log these labels
             ["litellm_model_name", "model_id", "api_base", "api_provider"]
             """
-            self.set_deployment_partial_outage(
-                litellm_model_name=litellm_model_name or "",
-                model_id=model_id,
-                api_base=api_base,
-                api_provider=llm_provider or "",
-            )
+            # Only mark a deployment outage when one was actually picked.
+            if deployment_selected:
+                self.set_deployment_partial_outage(
+                    litellm_model_name=litellm_model_name or "",
+                    model_id=model_id,
+                    api_base=api_base,
+                    api_provider=llm_provider or "",
+                )
             _deployment_label_ctx = PrometheusLabelFactoryContext(enum_values)
             if exception is not None:
                 PrometheusLogger._inc_labeled_counter(

litellm/integrations/prometheus_helpers/prometheus_api.py

@@ -2,6 +2,7 @@
 Helper functions to query prometheus API
 """
 
+import json
 import time
 from datetime import datetime, timedelta
 from typing import Optional
@@ -81,6 +82,24 @@ def is_prometheus_connected() -> bool:
     return False
 
 
+def _quote_promql_string_literal(value: str) -> str:
+    """Render ``value`` as a PromQL double-quoted string literal.
+
+    PromQL string literals follow Go's escape rules
+    (https://prometheus.io/docs/prometheus/latest/querying/basics/): a
+    backslash begins an escape sequence and a bare ``"`` ends the literal.
+    Without escaping, callers that accept arbitrary user-supplied values
+    (like the ``api_key`` filter on ``/global/spend/logs``) can inject extra
+    label matchers or selectors and read cross-tenant metrics.
+
+    JSON's quoting rules are a strict subset of Go's, so ``json.dumps`` of
+    a Python string produces a literal Prometheus accepts: ``\\``, ``\\"``,
+    and the standard ``\\n`` / ``\\t`` / ``\\uNNNN`` control-character
+    escapes. The returned value already includes the surrounding quotes.
+    """
+    return json.dumps(value, ensure_ascii=False)
+
+
 async def get_daily_spend_from_prometheus(api_key: Optional[str]):
     """
     Expected Response Format:
@@ -109,8 +128,11 @@ async def get_daily_spend_from_prometheus(api_key: Optional[str]):
     if api_key is None:
         query = "sum(delta(litellm_spend_metric_total[1d]))"
     else:
+        quoted_api_key = _quote_promql_string_literal(api_key)
         query = (
-            f'sum(delta(litellm_spend_metric_total{{hashed_api_key="{api_key}"}}[1d]))'
+            "sum(delta(litellm_spend_metric_total{"
+            f"hashed_api_key={quoted_api_key}"
+            "}[1d]))"
         )
 
     params = {

litellm/litellm_core_utils/cli_token_utils.py

@@ -31,15 +31,23 @@ def load_cli_token() -> Optional[dict]:
         return None
 
 
-def get_litellm_gateway_api_key() -> Optional[str]:
+def get_litellm_gateway_api_key(
+    expected_base_url: Optional[str] = None,
+) -> Optional[str]:
     """
     Get the stored CLI API key for use with LiteLLM SDK.
 
     This function reads the token file created by `litellm-proxy login`
     and returns the API key for use in Python scripts.
 
+    Args:
+        expected_base_url: When provided, the key is only returned if it was
+            originally issued for this URL. Pass the target server URL to
+            prevent credential leakage when the client is pointed at a
+            different (possibly malicious) server.
+
     Returns:
-        str: The API key if found, None otherwise
+        str: The API key if found (and origin matches), None otherwise
 
     Example:
         >>> import litellm
@@ -53,6 +61,10 @@ def get_litellm_gateway_api_key() -> Optional[str]:
         >>>     )
     """
     token_data = load_cli_token()
-    if token_data and "key" in token_data:
-        return token_data["key"]
-    return None
+    if not token_data or "key" not in token_data:
+        return None
+    if expected_base_url is not None:
+        stored_url = token_data.get("base_url")
+        if stored_url != expected_base_url.rstrip("/"):
+            return None
+    return token_data["key"]

litellm/litellm_core_utils/cloud_storage_security.py

@@ -0,0 +1,175 @@
+import posixpath
+import re
+from types import MappingProxyType
+from typing import Any, Mapping, Optional, Sequence, Tuple, cast
+from urllib.parse import quote, unquote
+
+from litellm._uuid import uuid
+
+VERTEX_AI_MANAGED_GCS_PREFIX = "litellm-vertex-files/"
+BEDROCK_MANAGED_S3_BATCH_PREFIX = "litellm-bedrock-files-"
+BEDROCK_MANAGED_S3_UPLOAD_PREFIX = "litellm-bedrock-files/"
+BEDROCK_MANAGED_S3_OUTPUT_PREFIX = "litellm-batch-outputs/"
+BEDROCK_MANAGED_S3_PREFIXES = (
+    BEDROCK_MANAGED_S3_BATCH_PREFIX,
+    BEDROCK_MANAGED_S3_UPLOAD_PREFIX,
+    BEDROCK_MANAGED_S3_OUTPUT_PREFIX,
+)
+_MAPPING_PROXY_TYPE: type = type(MappingProxyType({}))
+
+_SAFE_OBJECT_COMPONENT_PATTERN = re.compile(r"[^A-Za-z0-9._-]+")
+
+
+def sanitize_cloud_object_component(
+    value: Optional[str], fallback: str = "file"
+) -> str:
+    if not isinstance(value, str):
+        return fallback
+
+    component = posixpath.basename(value.replace("\\", "/")).strip()
+    if component in {"", ".", ".."}:
+        return fallback
+
+    component = "".join(
+        "_" if ord(char) < 32 or ord(char) == 127 else char for char in component
+    )
+    component = _SAFE_OBJECT_COMPONENT_PATTERN.sub("_", component)
+    component = component.strip("._")
+    if not component:
+        return fallback
+    return component[:255]
+
+
+def sanitize_cloud_object_path(value: Optional[str], fallback: str = "file") -> str:
+    if not isinstance(value, str):
+        return fallback
+
+    segments = []
+    for segment in value.replace("\\", "/").split("/"):
+        sanitized_segment = sanitize_cloud_object_component(segment, fallback="")
+        if sanitized_segment:
+            segments.append(sanitized_segment)
+
+    if not segments:
+        return fallback
+    return "/".join(segments)
+
+
+def build_managed_cloud_object_name(
+    prefix: str, filename: Optional[str], fallback_filename: str = "file"
+) -> str:
+    safe_filename = sanitize_cloud_object_component(
+        filename, fallback=fallback_filename
+    )
+    return f"{prefix}{uuid.uuid4().hex}-{safe_filename}"
+
+
+def _validate_cloud_object_path(object_name: str) -> None:
+    if not object_name:
+        raise ValueError("Cloud storage object name is required")
+    if object_name.startswith("/"):
+        raise ValueError("Cloud storage object name must be relative")
+    if any(ord(char) < 32 or ord(char) == 127 for char in object_name):
+        raise ValueError("Cloud storage object name contains control characters")
+    segments = object_name.split("/")
+    if any(segment in {".", ".."} for segment in segments):
+        raise ValueError("Cloud storage object name contains an invalid path segment")
+    if "" in segments[:-1]:
+        raise ValueError("Cloud storage object name contains an invalid path segment")
+
+
+def split_configured_cloud_bucket_name(bucket_name: str) -> Tuple[str, str]:
+    if not isinstance(bucket_name, str) or not bucket_name.strip():
+        raise ValueError("Cloud storage bucket name is required")
+
+    bucket_name = bucket_name.strip()
+    if "://" in bucket_name or "?" in bucket_name or "#" in bucket_name:
+        raise ValueError(
+            "Cloud storage bucket name must not include a URI scheme or query"
+        )
+    if any(ord(char) < 32 or ord(char) == 127 for char in bucket_name):
+        raise ValueError("Cloud storage bucket name contains control characters")
+
+    bucket, _, prefix = bucket_name.partition("/")
+    if not bucket:
+        raise ValueError("Cloud storage bucket name is required")
+    if "\\" in bucket:
+        raise ValueError("Cloud storage bucket name contains an invalid separator")
+
+    prefix = prefix.strip("/")
+    if prefix:
+        _validate_cloud_object_path(prefix)
+
+    return bucket, prefix
+
+
+def encode_gcs_object_name_for_url(object_name: str) -> str:
+    return quote(unquote(object_name), safe="")
+
+
+def encode_s3_object_key_for_url(object_key: str) -> str:
+    return quote(unquote(object_key), safe="/")
+
+
+def should_allow_legacy_cloud_file_ids(
+    litellm_params: Optional[Mapping[str, Any]] = None,
+) -> bool:
+    value = None
+    if isinstance(litellm_params, Mapping):
+        trusted_model_credentials = litellm_params.get(
+            "_litellm_internal_model_credentials"
+        )
+        if isinstance(trusted_model_credentials, _MAPPING_PROXY_TYPE):
+            value = cast(Mapping[str, Any], trusted_model_credentials).get(
+                "allow_legacy_cloud_file_ids"
+            )
+
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.strip().lower() in {"1", "true", "yes", "on"}
+    return False
+
+
+def validate_managed_cloud_file_id(
+    file_id: str,
+    scheme: str,
+    configured_bucket_name: str,
+    allowed_object_prefixes: Sequence[str],
+    allow_legacy_cloud_file_ids: bool = False,
+) -> Tuple[str, str]:
+    decoded_file_id = unquote(file_id)
+    if not decoded_file_id.startswith(scheme):
+        raise ValueError(f"file_id must be a {scheme} URI")
+
+    full_path = decoded_file_id[len(scheme) :]
+    if "/" not in full_path:
+        raise ValueError("file_id must include a cloud storage object name")
+
+    bucket_name, object_name = full_path.split("/", 1)
+    configured_bucket, configured_prefix = split_configured_cloud_bucket_name(
+        configured_bucket_name
+    )
+    if bucket_name != configured_bucket:
+        raise ValueError("file_id bucket does not match the configured storage bucket")
+
+    _validate_cloud_object_path(object_name)
+    allowed_prefixes = tuple(allowed_object_prefixes)
+    if configured_prefix:
+        allowed_prefixes = tuple(
+            f"{configured_prefix.rstrip('/')}/{prefix}" for prefix in allowed_prefixes
+        )
+
+    if object_name.startswith(allowed_prefixes):
+        return bucket_name, object_name
+
+    if allow_legacy_cloud_file_ids:
+        if configured_prefix and not object_name.startswith(
+            f"{configured_prefix.rstrip('/')}/"
+        ):
+            raise ValueError(
+                "file_id object does not match the configured storage prefix"
+            )
+        return bucket_name, object_name
+
+    raise ValueError("file_id must reference a LiteLLM-managed storage object")

litellm/litellm_core_utils/exception_mapping_utils.py

@@ -6,7 +6,8 @@ from typing import Any, Optional
 import httpx
 
 import litellm
-from litellm._logging import _redact_string, verbose_logger
+from litellm._logging import _ENABLE_SECRET_REDACTION, _redact_string, verbose_logger
+from litellm.litellm_core_utils.secret_redaction import redact_string
 from litellm.types.utils import LlmProviders
 
 from ..exceptions import (
@@ -261,10 +262,18 @@ def exception_type(  # type: ignore  # noqa: PLR0915
         original_exception=original_exception
     )
     try:
-        error_str = str(original_exception)
+        error_str = (
+            redact_string(str(original_exception))
+            if _ENABLE_SECRET_REDACTION
+            else str(original_exception)
+        )
         if model:
             if hasattr(original_exception, "message"):
-                error_str = str(original_exception.message)
+                error_str = (
+                    redact_string(str(original_exception.message))
+                    if _ENABLE_SECRET_REDACTION
+                    else str(original_exception.message)
+                )
             if isinstance(original_exception, BaseException):
                 exception_type = type(original_exception).__name__
             else:
@@ -2431,7 +2440,8 @@ def exception_type(  # type: ignore  # noqa: PLR0915
             else:
                 raise APIConnectionError(
                     message="{}\n{}".format(
-                        str(original_exception), _redact_string(traceback.format_exc())
+                        str(original_exception),
+                        _redact_string(traceback.format_exc()),
                     ),
                     llm_provider=custom_llm_provider,
                     model=model,
@@ -2461,7 +2471,8 @@ def exception_type(  # type: ignore  # noqa: PLR0915
                     raise e  # it's already mapped
             raised_exc = APIConnectionError(
                 message="{}\n{}".format(
-                    original_exception, _redact_string(traceback.format_exc())
+                    original_exception,
+                    _redact_string(traceback.format_exc()),
                 ),
                 llm_provider="",
                 model="",

litellm/litellm_core_utils/initialize_dynamic_callback_params.py

@@ -37,8 +37,6 @@ _supported_callback_params = [
     "langfuse_secret_key",
     "langfuse_host",
     "langfuse_prompt_version",
-    "gcs_bucket_name",
-    "gcs_path_service_account",
     "langsmith_api_key",
     "langsmith_project",
     "langsmith_base_url",
@@ -57,6 +55,11 @@ _supported_callback_params = [
     "lunary_public_key",
 ]
 
+_request_blocked_callback_params = {
+    "gcs_bucket_name",
+    "gcs_path_service_account",
+}
+
 
 def initialize_standard_callback_dynamic_params(
     kwargs: Optional[Dict] = None,
@@ -64,13 +67,15 @@ def initialize_standard_callback_dynamic_params(
     """
     Initialize the standard callback dynamic params from the kwargs
 
-    checks if langfuse_secret_key, gcs_bucket_name in kwargs and sets the corresponding attributes in StandardCallbackDynamicParams
+    checks supported request callback params in kwargs and sets the corresponding attributes in StandardCallbackDynamicParams
     """
 
     standard_callback_dynamic_params = StandardCallbackDynamicParams()
     if kwargs:
         # 1. Check top-level kwargs
         for param in _supported_callback_params:
+            if param in _request_blocked_callback_params:
+                continue
             if param in kwargs:
                 _param_value = kwargs.get(param)
                 validate_no_callback_env_reference(
@@ -86,6 +91,8 @@ def initialize_standard_callback_dynamic_params(
 
         if isinstance(metadata, dict):
             for param in _supported_callback_params:
+                if param in _request_blocked_callback_params:
+                    continue
                 if param not in standard_callback_dynamic_params and param in metadata:
                     _param_value = metadata.get(param)
                     validate_no_callback_env_reference(

litellm/litellm_core_utils/litellm_logging.py

@@ -3242,10 +3242,15 @@ class Logging(LiteLLMLoggingBaseClass):
                     ),
                     langfuse_secret=self.standard_callback_dynamic_params.get(
                         "langfuse_secret"
-                    ),
+                    )
+                    or self.standard_callback_dynamic_params.get("langfuse_secret_key"),
                     langfuse_host=self.standard_callback_dynamic_params.get(
                         "langfuse_host"
                     ),
+                    allow_env_credentials=self.standard_callback_dynamic_params.get(
+                        "langfuse_host"
+                    )
+                    is None,
                 )
             return langFuseLogger
 
@@ -4720,7 +4725,7 @@ class StandardLoggingPayloadSetup:
         ):
             for key, value in litellm_params["metadata"].items():
                 # Skip non-serializable objects like UserAPIKeyAuth
-                if key == "user_api_key_auth":
+                if key in {"user_api_key_auth", "user_api_key_budget_reservation"}:
                     continue
                 merged_metadata[key] = value
 

litellm/litellm_core_utils/llm_request_utils.py

@@ -77,8 +77,8 @@ def get_proxy_server_request_headers(litellm_params: Optional[dict]) -> dict:
     if litellm_params is None:
         return {}
 
-    proxy_request_headers = (
-        litellm_params.get("proxy_server_request", {}).get("headers", {}) or {}
-    )
+    proxy_request_headers = (litellm_params.get("proxy_server_request") or {}).get(
+        "headers"
+    ) or {}
 
     return proxy_request_headers

litellm/litellm_core_utils/prompt_templates/factory.py

@@ -4582,6 +4582,11 @@ class BedrockConverseMessagesProcessor:
                                     message=cast(ChatCompletionFileObject, element)
                                 )
                                 _parts.append(_part)
+                            elif element["type"] == "document":
+                                _part = BedrockConverseMessagesProcessor._process_document_message(
+                                    element
+                                )
+                                _parts.append(_part)
                             _cache_point_block = (
                                 litellm.AmazonConverseConfig()._get_cache_point_block(
                                     message_block=cast(
@@ -4864,6 +4869,44 @@ class BedrockConverseMessagesProcessor:
             image_url=cast(str, file_id or file_data), format=format
         )
 
+    @staticmethod
+    def _process_document_message(element: dict) -> BedrockContentBlock:
+        """Convert a document content block to a Bedrock DocumentBlock.
+
+        Handles the Anthropic-style document format:
+        {"type": "document", "source": {"type": "base64", "media_type": "application/pdf", "data": "..."}}
+        """
+        source = element["source"]
+        source_type = source.get("type")
+        if source_type != "base64":
+            raise ValueError(
+                f"Bedrock Converse only supports base64-encoded document sources, got '{source_type}'. "
+                "Please convert the document to base64 before sending to Bedrock."
+            )
+        media_type: str = source["media_type"]
+        data: str = source["data"]
+        doc_format = BedrockImageProcessor._validate_format(
+            mime_type=media_type, image_format=media_type.split("/")[1]
+        )
+
+        # Deterministic name using the same hashing pattern as _create_bedrock_block
+        HASH_SAMPLE_BYTES = 64 * 1024
+        normalized = "".join(data.split()).encode("utf-8")
+        sample = normalized[:HASH_SAMPLE_BYTES]
+        hasher = hashlib.sha256()
+        hasher.update(sample)
+        hasher.update(str(len(normalized)).encode("utf-8"))
+        content_hash = hasher.hexdigest()[:16]
+        document_name = f"Document_{content_hash}_{doc_format}"
+
+        return BedrockContentBlock(
+            document=BedrockDocumentBlock(
+                source=BedrockSourceBlock(bytes=data),
+                format=doc_format,
+                name=document_name,
+            )
+        )
+
     @staticmethod
     def add_thinking_blocks_to_assistant_content(
         thinking_blocks: List[BedrockContentBlock],
@@ -4961,6 +5004,11 @@ def _bedrock_converse_messages_pt(  # noqa: PLR0915
                                 )
                             )
                             _parts.append(_part)
+                        elif element["type"] == "document":
+                            _part = BedrockConverseMessagesProcessor._process_document_message(
+                                element
+                            )
+                            _parts.append(_part)
                         _cache_point_block = (
                             litellm.AmazonConverseConfig()._get_cache_point_block(
                                 message_block=cast(

litellm/litellm_core_utils/secret_redaction.py

@@ -0,0 +1,81 @@
+"""
+Credential/secret redaction utilities.
+
+This module owns the compiled regex and the public `redact_string` helper so
+that any part of the codebase (logging, exception mapping, etc.) can scrub
+secrets from strings without depending on the logging-configuration module.
+"""
+
+import re
+from typing import List
+
+_REDACTED = "REDACTED"
+
+
+def _build_secret_patterns() -> "re.Pattern[str]":
+    patterns: List[str] = [
+        # PEM private key / certificate blocks
+        r"-----BEGIN[A-Z \-]*PRIVATE KEY-----[\s\S]*?-----END[A-Z \-]*PRIVATE KEY-----",
+        # GCP OAuth2 access tokens (ya29.*)
+        r"\bya29\.[A-Za-z0-9_.~+/-]+",
+        # Credential %s formatting (space separator, no key= prefix)
+        r"(?:client_secret|azure_password|azure_username)\s+[^\s,'\"})\]{}>]+",
+        # AWS access key IDs
+        r"(?:AKIA|ASIA)[0-9A-Z]{16}",
+        # AWS secrets / session tokens / access key IDs (key=value)
+        r"(?:aws_secret_access_key|aws_session_token|aws_access_key_id)"
+        r"\s*[:=]\s*[A-Za-z0-9/+=]{20,}",
+        # Bearer tokens (OAuth, JWT, etc.)
+        r"Bearer\s+[A-Za-z0-9\-._~+/]{10,}=*",
+        # Basic auth headers
+        r"Basic\s+[A-Za-z0-9+/]{10,}={0,2}",
+        # OpenAI / Anthropic sk- prefixed keys
+        r"sk-[A-Za-z0-9\-_]{20,}",
+        # Generic api_key / api-key / apikey (handles 'key': 'value' dict repr)
+        r"(?:api[_-]?key)['\"]?\s*[:=]\s*['\"]?[^\s,'\"})\]{}>]{8,}",
+        # x-api-key / api-key header values (handles 'key': 'value' dict repr)
+        r"(?:x-api-key|api-key)['\"]?\s*[:=]\s*['\"]?[^\s,'\"})\]{}>]+",
+        # Anthropic internal header keys
+        r"x-ak-[A-Za-z0-9\-_]{20,}",
+        # Google API keys (bare key value)
+        r"AIza[0-9A-Za-z\-_]{35}",
+        # URL query-param key=VALUE (e.g. ?key=AIza... or &key=...) — catches the
+        # full "key=<secret>" fragment so the value is redacted regardless of format.
+        r"(?<=[?&])key=[^\s&'\"]{8,}",
+        # Password / secret params (handles key=value and 'key': 'value')
+        # Word boundary prevents O(n^2) backtracking on long word-char runs.
+        r"(?:^|(?<=\W))\w*(?:password|passwd|client_secret|secret_key|_secret)"
+        r"['\"]?\s*[:=]\s*['\"]?[^\s,'\"})\]{}>]+",
+        # Database connection string credentials (scheme://user:pass@host)
+        r"(?<=://)[^\s'\"]*:[^\s'\"@]+(?=@)",
+        # Databricks personal access tokens
+        r"dapi[0-9a-f]{32}",
+        # ── Key-name-based redaction ──
+        # Catches secrets inside dicts/config dumps by matching on the KEY name
+        # regardless of what the value looks like.
+        # e.g. 'master_key': 'any-value-here', "database_url": "postgres://..."
+        # private_key with PEM-aware value capture
+        r"""private_key['\"]?\s*[:=]\s*['\"]?(?:-----BEGIN[A-Z \-]*PRIVATE KEY-----[\s\S]*?-----END[A-Z \-]*PRIVATE KEY-----|[^\s,'\"})\]{}>]+)""",
+        r"(?:master_key|database_url|db_url|connection_string|"
+        r"signing_key|encryption_key|"
+        r"auth_token|access_token|refresh_token|"
+        r"slack_webhook_url|webhook_url|"
+        r"database_connection_string|"
+        r"huggingface_token|jwt_secret)"
+        r"""['\"]?\s*[:=]\s*['\"]?[^\s,'\"})\]{}>]+""",
+        # Raw JWTs (without Bearer prefix)
+        r"\beyJ[A-Za-z0-9_-]{10,}\.[A-Za-z0-9_-]+\.[A-Za-z0-9_-]*",
+        # Azure SAS tokens in URLs
+        r"[?&]sig=[A-Za-z0-9%+/=]+",
+        # Full JSON service-account blobs (single-line and multi-line)
+        r'\{[^{}]*"type"\s*:\s*"service_account"[^{}]*(?:\{[^{}]*\}[^{}]*)*\}',
+    ]
+    return re.compile("|".join(patterns), re.IGNORECASE)
+
+
+_SECRET_RE = _build_secret_patterns()
+
+
+def redact_string(value: str) -> str:
+    """Scrub known secret/credential patterns from *value* and return the result."""
+    return _SECRET_RE.sub(_REDACTED, value)

litellm/litellm_core_utils/streaming_handler.py

@@ -2244,7 +2244,7 @@ class CustomStreamWrapper:
                 asyncio.create_task(
                     self.logging_obj.async_failure_handler(e, traceback_exception)
                 )
-            raise e
+            self._handle_stream_fallback_error(e)
         except Exception as e:
             traceback_exception = traceback.format_exc()
             if self.logging_obj is not None:

litellm/litellm_core_utils/url_utils.py

@@ -21,8 +21,8 @@ Admins can opt out via two ``litellm`` globals (wired from proxy config):
 
 import socket
 from ipaddress import ip_address, ip_network
-from typing import Any, List, Set, Tuple
-from urllib.parse import urlparse, urlunparse
+from typing import Any, List, Optional, Set, Tuple
+from urllib.parse import quote, urlparse, urlunparse
 
 import httpx
 
@@ -46,6 +46,46 @@ class SSRFError(ValueError):
     pass
 
 
+def encode_url_path_segment(value: Any, *, field_name: str = "path parameter") -> str:
+    """Percent-encode one user-controlled URL path segment.
+
+    ``urllib.parse.quote(..., safe="")`` intentionally leaves RFC 3986
+    unreserved characters such as ``.`` unescaped, so reject standalone dot
+    segments before they can be appended to an upstream URL and normalized by
+    the HTTP client.
+    """
+    if value is None:
+        raise ValueError(f"{field_name} is required")
+
+    value_str = str(value)
+    if value_str == "":
+        raise ValueError(f"{field_name} is required")
+    if value_str in {".", ".."}:
+        raise ValueError(f"{field_name} cannot be a dot path segment")
+
+    return quote(value_str, safe="")
+
+
+def encode_url_path_segments(value: Any, *, field_name: str = "path") -> str:
+    """Percent-encode a user-controlled URL path made of multiple segments.
+
+    Empty segments are rejected, so leading, trailing, or consecutive slashes
+    fail closed instead of being normalized by the HTTP client.
+    """
+    if value is None:
+        raise ValueError(f"{field_name} is required")
+
+    value_str = str(value)
+    if value_str == "":
+        raise ValueError(f"{field_name} is required")
+
+    encoded_segments = []
+    for segment in value_str.split("/"):
+        encoded_segments.append(encode_url_path_segment(segment, field_name=field_name))
+
+    return "/".join(encoded_segments)
+
+
 def _is_blocked_ip(addr: str) -> bool:
     """Return True for any IP not safe to reach from a user-supplied URL.
 
@@ -70,6 +110,85 @@ def _normalize_host(host: str) -> str:
     return host.lower().rstrip(".")
 
 
+def _default_port_for_scheme(scheme: str) -> int:
+    return 443 if scheme == "https" else 80
+
+
+def _parse_url_destination_allowlist_entry(
+    entry: str,
+) -> Optional[Tuple[str, Optional[str], Optional[int]]]:
+    """Parse an admin allowlist entry into host, optional scheme, optional port.
+
+    Entries may be bare hosts (``api.example.com``), host+port
+    (``api.example.com:8443``), or origins (``https://api.example.com``).
+    URL paths are intentionally ignored so admins can paste an api_base value.
+    """
+    entry = entry.strip()
+    if not entry:
+        return None
+
+    has_scheme = "://" in entry
+    parsed = urlparse(entry if has_scheme else f"//{entry}")
+    if has_scheme and parsed.scheme not in _ALLOWED_SCHEMES:
+        return None
+    if parsed.username is not None or parsed.password is not None:
+        return None
+    if not parsed.hostname:
+        return None
+
+    try:
+        port = parsed.port
+    except ValueError:
+        return None
+
+    scheme: Optional[str] = parsed.scheme if has_scheme else None
+    if scheme is not None and port is None:
+        port = _default_port_for_scheme(scheme)
+
+    return _normalize_host(parsed.hostname), scheme, port
+
+
+def is_url_destination_allowed_by_host(url: str, allowed_hosts: List[str]) -> bool:
+    """Return True when a credential-bearing provider URL is admin-allowlisted.
+
+    This does not fetch, resolve, or rewrite URLs. It only answers whether the
+    destination origin is explicitly trusted by configuration. Use ``safe_get``
+    for user-controlled content fetches that require SSRF protection.
+    """
+    parsed = urlparse(url)
+    if parsed.scheme not in _ALLOWED_SCHEMES:
+        return False
+    if parsed.username is not None or parsed.password is not None:
+        return False
+    if not parsed.hostname:
+        return False
+
+    try:
+        effective_port = parsed.port or _default_port_for_scheme(parsed.scheme)
+    except ValueError:
+        return False
+
+    normalized_host = _normalize_host(parsed.hostname)
+    configured_entries = (
+        [allowed_hosts] if isinstance(allowed_hosts, str) else allowed_hosts
+    )
+    for entry in configured_entries or []:
+        if not isinstance(entry, str):
+            continue
+        parsed_entry = _parse_url_destination_allowlist_entry(entry)
+        if parsed_entry is None:
+            continue
+        allowed_host, allowed_scheme, allowed_port = parsed_entry
+        if allowed_host != normalized_host:
+            continue
+        if allowed_scheme is not None and allowed_scheme != parsed.scheme:
+            continue
+        if allowed_port is not None and allowed_port != effective_port:
+            continue
+        return True
+    return False
+
+
 def _format_host_header(hostname: str, port: int, default_port: int) -> str:
     """Build an RFC 7230 Host header value, bracketing IPv6 literals."""
     bracketed = f"[{hostname}]" if ":" in hostname else hostname
@@ -145,7 +264,7 @@ def validate_url(url: str) -> Tuple[str, str]:
         raise SSRFError("URL has no hostname")
 
     port = parsed.port
-    default_port = 443 if parsed.scheme == "https" else 80
+    default_port = _default_port_for_scheme(parsed.scheme)
     effective_port = port if port is not None else default_port
     host_header = _format_host_header(hostname, effective_port, default_port)
 
@@ -199,6 +318,47 @@ def validate_url(url: str) -> Tuple[str, str]:
     return rewritten, host_header
 
 
+def assert_same_origin(candidate_url: str, expected_url: str) -> None:
+    """Verify ``candidate_url`` shares scheme, host, and port with ``expected_url``.
+
+    Use when an upstream API returns a URL meant for follow-up requests
+    (e.g. an async-job polling URL that will be hit with the operator's
+    API key in the headers). The upstream is trusted because the operator
+    configured ``api_base``, but the URL it hands back must actually point
+    back at the same origin or we'd be blindly forwarding credentials
+    wherever the upstream told us to.
+
+    Hostnames are compared case-insensitively. Default ports are made
+    explicit (HTTP→80, HTTPS→443) so ``https://api.example.com:443/...``
+    and ``https://api.example.com/...`` are treated as the same origin.
+
+    Error messages identify *which* component mismatched but never echo
+    the operator's ``expected`` host or the candidate's hostname back to
+    the caller — in the SSRF threat model the caller is the attacker,
+    and reflecting host info would be a secondary leak of operator
+    infrastructure details.
+    """
+    candidate = urlparse(candidate_url)
+    expected = urlparse(expected_url)
+
+    if candidate.scheme not in _ALLOWED_SCHEMES:
+        raise SSRFError("URL scheme is not allowed")
+
+    if candidate.scheme != expected.scheme:
+        raise SSRFError("Origin mismatch on scheme")
+
+    candidate_host = _normalize_host(candidate.hostname or "")
+    expected_host = _normalize_host(expected.hostname or "")
+    if not candidate_host or candidate_host != expected_host:
+        raise SSRFError("Origin mismatch on host")
+
+    default_port = 443 if candidate.scheme == "https" else 80
+    candidate_port = candidate.port if candidate.port is not None else default_port
+    expected_port = expected.port if expected.port is not None else default_port
+    if candidate_port != expected_port:
+        raise SSRFError("Origin mismatch on port")
+
+
 _MAX_REDIRECTS = 10
 
 

litellm/llms/anthropic/batches/transformation.py

@@ -5,6 +5,7 @@ from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Union, cas
 import httpx
 from httpx import Headers, Response
 
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.batches.transformation import BaseBatchesConfig
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.types.llms.openai import AllMessageValues, CreateBatchRequest
@@ -122,7 +123,8 @@ class AnthropicBatchesConfig(BaseBatchesConfig):
             Complete URL for Anthropic batch retrieval: {api_base}/v1/messages/batches/{batch_id}
         """
         api_base = api_base or self.anthropic_model_info.get_api_base(api_base)
-        return f"{api_base.rstrip('/')}/v1/messages/batches/{batch_id}"
+        encoded_batch_id = encode_url_path_segment(batch_id, field_name="batch_id")
+        return f"{api_base.rstrip('/')}/v1/messages/batches/{encoded_batch_id}"
 
     def transform_retrieve_batch_request(
         self,

litellm/llms/anthropic/chat/transformation.py

@@ -1,18 +1,31 @@
 import json
 import re
 import time
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union, cast
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Dict,
+    List,
+    NoReturn,
+    Optional,
+    Tuple,
+    Union,
+    cast,
+)
 
 import httpx
 
 import litellm
 from litellm.constants import (
+    ANTHROPIC_MIN_THINKING_BUDGET_TOKENS,
     ANTHROPIC_WEB_SEARCH_TOOL_MAX_USES,
     DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS,
     DEFAULT_REASONING_EFFORT_HIGH_THINKING_BUDGET,
     DEFAULT_REASONING_EFFORT_LOW_THINKING_BUDGET,
+    DEFAULT_REASONING_EFFORT_MAX_THINKING_BUDGET,
     DEFAULT_REASONING_EFFORT_MEDIUM_THINKING_BUDGET,
     DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET,
+    DEFAULT_REASONING_EFFORT_XHIGH_THINKING_BUDGET,
     RESPONSE_FORMAT_TOOL_NAME,
 )
 from litellm.litellm_core_utils.core_helpers import map_finish_reason
@@ -92,6 +105,22 @@ else:
     LoggingClass = Any
 
 
+REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT: Dict[str, str] = {
+    "low": "low",
+    "minimal": "low",
+    "medium": "medium",
+    "high": "high",
+    "xhigh": "xhigh",
+    "max": "max",
+}
+
+DROP_UNSUPPORTED_OUTPUT_CONFIG_WARNING = (
+    "Dropping unsupported `output_config` for model=%s "
+    "(drop_params=True). Effort is only supported on Opus 4.5+, "
+    "Sonnet 4.6+, and Mythos Preview."
+)
+
+
 class AnthropicConfig(AnthropicModelInfo, BaseConfig):
     """
     Reference: https://docs.anthropic.com/claude/reference/messages_post
@@ -202,17 +231,96 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
     def _supports_effort_level(model: str, level: str) -> bool:
         """Check ``supports_{level}_reasoning_effort`` in the model map.
 
-        Mirrors the pattern used in ``openai/chat/gpt_5_transformation.py`` so
-        that adding support for a new effort level is a pure model-map change.
+        Strips bedrock/vertex prefixes so a provider-routed Claude still
+        resolves to the Anthropic model-map entry.
         """
+        key = f"supports_{level}_reasoning_effort"
         try:
-            return _supports_factory(
+            if _supports_factory(
                 model=model,
                 custom_llm_provider="anthropic",
-                key=f"supports_{level}_reasoning_effort",
-            )
+                key=key,
+            ):
+                return True
         except Exception:
-            return False
+            pass
+        candidates = [model]
+        for prefix in (
+            "bedrock/converse/",
+            "bedrock/invoke/",
+            "bedrock/",
+            "vertex_ai/",
+        ):
+            if model.startswith(prefix):
+                candidates.append(model[len(prefix) :])
+        try:
+            from litellm.llms.bedrock.common_utils import BedrockModelInfo
+
+            base = BedrockModelInfo.get_base_model(model)
+            if base:
+                candidates.append(base)
+                candidates.append(f"bedrock/{base}")
+        except Exception:
+            pass
+        try:
+            import litellm
+
+            for cand in candidates:
+                if cand in litellm.model_cost and (
+                    litellm.model_cost[cand].get(key) is True
+                ):
+                    return True
+        except Exception:
+            pass
+        return False
+
+    @staticmethod
+    def _validate_effort_for_model(model: str, effort: Optional[str]) -> Optional[str]:
+        """Return ``None`` if ``effort`` is allowed on ``model``, else an error message."""
+        if effort == "max" and not (
+            AnthropicConfig._is_claude_4_6_model(model)
+            or AnthropicConfig._is_claude_4_7_model(model)
+            or AnthropicConfig._supports_effort_level(model, "max")
+        ):
+            return f"effort='max' is not supported by this model. Got model: {model}"
+        if effort == "xhigh" and not AnthropicConfig._supports_effort_level(
+            model, "xhigh"
+        ):
+            return f"effort='xhigh' is not supported by this model. Got model: {model}"
+        return None
+
+    @staticmethod
+    def _model_supports_effort_param(model: str) -> bool:
+        """Whether the model accepts ``output_config.effort`` at all."""
+        return any(
+            AnthropicConfig._supports_effort_level(model, level)
+            for level in ("low", "minimal", "medium", "high", "xhigh", "max")
+        )
+
+    @staticmethod
+    def _raise_invalid_reasoning_effort(
+        model: str, value: Any, llm_provider: str
+    ) -> NoReturn:
+        """Raise a ``BadRequestError`` for an unrecognised ``reasoning_effort``.
+
+        Args:
+            model: The model id the request was routed to (surfaced in the error).
+            value: The offending ``reasoning_effort`` value supplied by the caller.
+            llm_provider: Provider tag for the raised exception (``"anthropic"``,
+                ``"bedrock_converse"``, ``"databricks"``, ...).
+
+        Raises:
+            litellm.exceptions.BadRequestError: Always.
+        """
+        raise litellm.exceptions.BadRequestError(
+            message=(
+                f"Invalid reasoning_effort: {value!r}. "
+                f"Must be one of: 'minimal', 'low', 'medium', "
+                f"'high', 'xhigh', 'max', 'none'"
+            ),
+            model=model,
+            llm_provider=llm_provider,
+        )
 
     def get_supported_openai_params(self, model: str):
         params = [
@@ -794,12 +902,11 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
     def _map_reasoning_effort(
         reasoning_effort: Optional[Union[REASONING_EFFORT, str]],
         model: str,
+        llm_provider: str = "anthropic",
     ) -> Optional[AnthropicThinkingParam]:
         if reasoning_effort is None or reasoning_effort == "none":
             return None
-        if AnthropicConfig._is_claude_4_6_model(
-            model
-        ) or AnthropicConfig._is_claude_4_7_model(model):
+        if AnthropicConfig._is_adaptive_thinking_model(model):
             return AnthropicThinkingParam(
                 type="adaptive",
             )
@@ -818,13 +925,34 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
                 type="enabled",
                 budget_tokens=DEFAULT_REASONING_EFFORT_HIGH_THINKING_BUDGET,
             )
+        elif reasoning_effort == "xhigh":
+            return AnthropicThinkingParam(
+                type="enabled",
+                budget_tokens=DEFAULT_REASONING_EFFORT_XHIGH_THINKING_BUDGET,
+            )
+        elif reasoning_effort == "max":
+            return AnthropicThinkingParam(
+                type="enabled",
+                budget_tokens=DEFAULT_REASONING_EFFORT_MAX_THINKING_BUDGET,
+            )
         elif reasoning_effort == "minimal":
             return AnthropicThinkingParam(
                 type="enabled",
-                budget_tokens=DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET,
+                budget_tokens=max(
+                    DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET,
+                    ANTHROPIC_MIN_THINKING_BUDGET_TOKENS,
+                ),
             )
         else:
-            raise ValueError(f"Unmapped reasoning effort: {reasoning_effort}")
+            raise litellm.exceptions.BadRequestError(
+                message=(
+                    f"Unmapped reasoning effort: {reasoning_effort!r}. "
+                    f"Must be one of: 'minimal', 'low', 'medium', 'high', "
+                    f"'xhigh', 'max', 'none'."
+                ),
+                model=model,
+                llm_provider=llm_provider,
+            )
 
     def _extract_json_schema_from_response_format(
         self, value: Optional[dict]
@@ -1088,24 +1216,27 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
             elif param == "thinking":
                 optional_params["thinking"] = value
             elif param == "reasoning_effort" and isinstance(value, str):
-                optional_params["thinking"] = AnthropicConfig._map_reasoning_effort(
-                    reasoning_effort=value, model=model
+                mapped_thinking = AnthropicConfig._map_reasoning_effort(
+                    reasoning_effort=value,
+                    model=model,
+                    llm_provider=self.custom_llm_provider or "anthropic",
                 )
-                # For Claude 4.6+ models, effort is controlled via output_config,
-                # not thinking budget_tokens. Map reasoning_effort to output_config.
-                if AnthropicConfig._is_claude_4_6_model(
-                    model
-                ) or AnthropicConfig._is_claude_4_7_model(model):
-                    effort_map = {
-                        "low": "low",
-                        "minimal": "low",
-                        "medium": "medium",
-                        "high": "high",
-                        "xhigh": "xhigh",
-                        "max": "max",
-                    }
-                    mapped_effort = effort_map.get(value, value)
-                    optional_params["output_config"] = {"effort": mapped_effort}
+                if mapped_thinking is None:
+                    optional_params.pop("thinking", None)
+                    optional_params.pop("output_config", None)
+                else:
+                    optional_params["thinking"] = mapped_thinking
+                    if AnthropicConfig._is_adaptive_thinking_model(model):
+                        mapped_effort = REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT.get(
+                            value
+                        )
+                        if mapped_effort is None:
+                            AnthropicConfig._raise_invalid_reasoning_effort(
+                                model=model,
+                                value=value,
+                                llm_provider=self.custom_llm_provider or "anthropic",
+                            )
+                        optional_params["output_config"] = {"effort": mapped_effort}
             elif param == "web_search_options" and isinstance(value, dict):
                 hosted_web_search_tool = self.map_web_search_tool(
                     cast(OpenAIWebSearchOptions, value)
@@ -1527,29 +1658,31 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
         output_config = optional_params.get("output_config")
         if not output_config or not isinstance(output_config, dict):
             return
+        if litellm.drop_params is True and not self._model_supports_effort_param(model):
+            litellm.verbose_logger.warning(
+                DROP_UNSUPPORTED_OUTPUT_CONFIG_WARNING,
+                model,
+            )
+            optional_params.pop("output_config", None)
+            data.pop("output_config", None)
+            return
         effort = output_config.get("effort")
         valid_efforts = ["high", "medium", "low", "xhigh", "max"]
-        if effort and effort not in valid_efforts:
-            raise ValueError(
-                f"Invalid effort value: {effort}. Must be one of: "
-                f"'high', 'medium', 'low', 'xhigh', 'max'"
+        if effort is not None and effort not in valid_efforts:
+            raise litellm.exceptions.BadRequestError(
+                message=(
+                    f"Invalid effort value: {effort!r}. Must be one of: "
+                    f"'high', 'medium', 'low', 'xhigh', 'max'"
+                ),
+                model=model,
+                llm_provider=self.custom_llm_provider or "anthropic",
             )
-        # ``max`` is for Opus 4.6+ output effort (not Sonnet 4.6, not Opus 4.5).
-        # Accept known Opus 4.6/4.7 id patterns and/or ``supports_max_reasoning_effort``
-        # in the model map (same pattern as ``xhigh`` below).
-        if effort == "max" and not (
-            self._is_opus_4_6_model(model)
-            or self._is_opus_4_7_model(model)
-            or self._supports_effort_level(model, "max")
-        ):
-            raise ValueError(
-                f"effort='max' is not supported by this model. Got model: {model}"
-            )
-        # ``xhigh`` is data-driven via ``supports_xhigh_reasoning_effort`` so
-        # enabling it for a new model is a pure model-map change.
-        if effort == "xhigh" and not self._supports_effort_level(model, "xhigh"):
-            raise ValueError(
-                f"effort='xhigh' is not supported by this model. Got model: {model}"
+        gate_error = self._validate_effort_for_model(model, effort)
+        if gate_error is not None:
+            raise litellm.exceptions.BadRequestError(
+                message=gate_error,
+                model=model,
+                llm_provider=self.custom_llm_provider or "anthropic",
             )
         data["output_config"] = output_config
 

litellm/llms/anthropic/common_utils.py

@@ -273,7 +273,18 @@ class AnthropicModelInfo(BaseLLMModelInfo):
 
     @staticmethod
     def _is_adaptive_thinking_model(model: str) -> bool:
-        """Claude 4.6+ models use adaptive thinking with output_config effort."""
+        """Claude 4.6+ models use adaptive thinking with ``output_config.effort``."""
+        from litellm.utils import _supports_factory
+
+        try:
+            if _supports_factory(
+                model=model,
+                custom_llm_provider=None,
+                key="supports_adaptive_thinking",
+            ):
+                return True
+        except Exception:
+            pass
         return AnthropicModelInfo._is_claude_4_6_model(
             model
         ) or AnthropicModelInfo._is_claude_4_7_model(model)

litellm/llms/anthropic/experimental_pass_through/adapters/handler.py

@@ -27,6 +27,16 @@ from litellm.utils import get_model_info
 if TYPE_CHECKING:
     pass
 
+
+# Anthropic-only fields that the translator above already maps into the
+# OpenAI-format completion_kwargs (output_config → reasoning_effort /
+# response_format, etc.). They must be filtered out of the raw
+# extra_kwargs re-merge below or non-Anthropic backends reject the call
+# with 400 "Extra inputs are not permitted". Add new entries here when
+# extending AnthropicMessagesRequestOptionalParams with another Anthropic-
+# specific key.
+ANTHROPIC_ONLY_REQUEST_KEYS: frozenset[str] = frozenset({"output_config"})
+
 ########################################################
 # init adapter
 ANTHROPIC_ADAPTER = AnthropicAdapter()
@@ -202,8 +212,12 @@ class LiteLLMMessagesToCompletionTransformationHandler:
             request_data["output_format"] = output_format
 
         # Extract output_config from extra_kwargs so the translator can use it
-        # (e.g. output_config.effort for adaptive thinking → reasoning_effort)
-        extra_kwargs = extra_kwargs or {}
+        # (e.g. output_config.effort for adaptive thinking → reasoning_effort,
+        # output_config.format → response_format for structured outputs).
+        # Use explicit None check rather than `or {}` so an explicit empty dict
+        # caller-passed argument is preserved (matters for tests that drive
+        # the fallback inference path).
+        extra_kwargs = extra_kwargs if extra_kwargs is not None else {}
         if "output_config" in extra_kwargs:
             request_data["output_config"] = extra_kwargs["output_config"]
 
@@ -225,8 +239,23 @@ class LiteLLMMessagesToCompletionTransformationHandler:
                 "include_usage": True,
             }
 
-        excluded_keys = {"anthropic_messages"}
-        extra_kwargs = extra_kwargs or {}
+        # Keys that must NOT be forwarded as raw extras into the OpenAI-format
+        # ``completion_kwargs`` after translation. The translator above has
+        # already consumed the meaningful parts of these inputs (e.g.
+        # ``output_config.format`` → ``response_format``, ``output_config.effort``
+        # → ``reasoning_effort`` for non-Claude targets). Re-adding the raw
+        # Anthropic-shaped key here causes 400 "Extra inputs are not permitted"
+        # on non-Anthropic backends (Azure OpenAI, Fireworks, Bedrock Nova,
+        # etc.) and is silently lossy on Anthropic-family targets, which would
+        # see the translated key ``response_format`` AND a duplicate, conflicting
+        # ``output_config``.
+        #
+        # Maintainability: when adding a new Anthropic-only request param to
+        # ``AnthropicMessagesRequestOptionalParams``, also extend
+        # ``ANTHROPIC_ONLY_REQUEST_KEYS`` here so it doesn't silently leak.
+        excluded_keys = ANTHROPIC_ONLY_REQUEST_KEYS | {"anthropic_messages"}
+        # NOTE: extra_kwargs was already coerced from None to {} at the top of
+        # this method (line ~220). It is guaranteed to be a dict here.
         for key, value in extra_kwargs.items():
             if (
                 key == "litellm_logging_obj"

litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py

@@ -667,7 +667,7 @@ class LiteLLMAnthropicMessagesAdapter:
 
     @staticmethod
     def translate_anthropic_thinking_to_reasoning_effort(
-        thinking: Dict[str, Any]
+        thinking: Dict[str, Any],
     ) -> Optional[str]:
         """
         Translate Anthropic's thinking parameter to OpenAI's reasoning_effort.
@@ -1084,10 +1084,23 @@ class LiteLLMAnthropicMessagesAdapter:
         anthropic_message_request: AnthropicMessagesRequest,
         new_kwargs: ChatCompletionRequest,
     ) -> None:
-        """Translate output_format to response_format when applicable."""
-        if "output_format" not in anthropic_message_request:
-            return
-        output_format = anthropic_message_request["output_format"]
+        """Translate Anthropic structured-output config to OpenAI ``response_format``.
+
+        Accepts either the legacy top-level ``output_format`` field OR the
+        newer ``output_config.format`` (sub-key on ``output_config``) so that
+        both shapes flow through to non-Anthropic backends as
+        ``response_format``. Without the ``output_config.format`` branch,
+        callers using the new Anthropic Structured Outputs API would have
+        their schema silently dropped on the adapter path — only the legacy
+        top-level ``output_format`` was being mapped.
+
+        ``output_format`` takes precedence when both are provided.
+        """
+        output_format: Any = anthropic_message_request.get("output_format")
+        if not output_format:
+            output_config = anthropic_message_request.get("output_config")
+            if isinstance(output_config, dict):
+                output_format = output_config.get("format")
         if not output_format:
             return
         response_format = self.translate_anthropic_output_format_to_openai(

litellm/llms/anthropic/experimental_pass_through/messages/transformation.py

@@ -47,6 +47,7 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig):
             "inference_geo",
             "speed",
             "output_config",
+            "reasoning_effort",
             # TODO: Add Anthropic `metadata` support
             # "metadata",
         ]
@@ -166,6 +167,62 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig):
 
         return headers, api_base
 
+    @staticmethod
+    def _translate_reasoning_effort_to_anthropic(
+        model: str, optional_params: Dict
+    ) -> None:
+        """Map OpenAI-style ``reasoning_effort`` to native Anthropic params.
+
+        Caller-supplied ``thinking`` / ``output_config`` win over the alias.
+        ``effort='none'`` clears both. Invalid efforts raise a 400.
+        """
+        from litellm.exceptions import BadRequestError as _BadRequestError
+        from litellm.llms.anthropic.chat.transformation import (
+            REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT,
+            AnthropicConfig,
+        )
+
+        reasoning_effort = optional_params.pop("reasoning_effort", None)
+        if not isinstance(reasoning_effort, str):
+            return
+
+        try:
+            mapped_thinking = AnthropicConfig._map_reasoning_effort(
+                reasoning_effort=reasoning_effort, model=model
+            )
+        except _BadRequestError as e:
+            raise AnthropicError(message=str(e.message), status_code=400)
+
+        if mapped_thinking is None:
+            optional_params.pop("thinking", None)
+            optional_params.pop("output_config", None)
+            return
+
+        optional_params.setdefault("thinking", mapped_thinking)
+        if AnthropicModelInfo._is_adaptive_thinking_model(model):
+            mapped_effort = REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT.get(
+                reasoning_effort
+            )
+            if mapped_effort is None:
+                raise AnthropicError(
+                    message=(
+                        f"Invalid reasoning_effort: {reasoning_effort!r}. "
+                        f"Must be one of: 'minimal', 'low', 'medium', 'high', "
+                        f"'xhigh', 'max', 'none'"
+                    ),
+                    status_code=400,
+                )
+            gate_error = AnthropicConfig._validate_effort_for_model(
+                model, mapped_effort
+            )
+            if gate_error is not None:
+                raise AnthropicError(message=gate_error, status_code=400)
+            existing_output_config = optional_params.get("output_config")
+            if not isinstance(existing_output_config, dict):
+                existing_output_config = {}
+            existing_output_config.setdefault("effort", mapped_effort)
+            optional_params["output_config"] = existing_output_config
+
     @staticmethod
     def _translate_legacy_thinking_for_adaptive_model(
         model: str, optional_params: Dict
@@ -217,6 +274,11 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig):
                 status_code=400,
             )
 
+        self._translate_reasoning_effort_to_anthropic(
+            model=model,
+            optional_params=anthropic_messages_optional_request_params,
+        )
+
         self._translate_legacy_thinking_for_adaptive_model(
             model=model,
             optional_params=anthropic_messages_optional_request_params,

litellm/llms/anthropic/files/handler.py

@@ -9,6 +9,7 @@ import litellm
 from litellm._logging import verbose_logger
 from litellm._uuid import uuid
 from litellm.litellm_core_utils.litellm_logging import Logging
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.custom_httpx.http_handler import get_async_httpx_client
 from litellm.types.llms.openai import (
     FileContentRequest,
@@ -89,7 +90,10 @@ class AnthropicFilesHandler:
             raise ValueError("Missing Anthropic API Key")
 
         # Construct the Anthropic batch results URL
-        results_url = f"{api_base.rstrip('/')}/v1/messages/batches/{batch_id}/results"
+        encoded_batch_id = encode_url_path_segment(batch_id, field_name="batch_id")
+        results_url = (
+            f"{api_base.rstrip('/')}/v1/messages/batches/{encoded_batch_id}/results"
+        )
 
         # Prepare headers
         headers = {

litellm/llms/anthropic/files/transformation.py

@@ -19,6 +19,7 @@ from typing import Any, Dict, List, Optional, Union, cast
 import httpx
 from openai.types.file_deleted import FileDeleted
 
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.litellm_core_utils.prompt_templates.common_utils import extract_file_data
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.base_llm.files.transformation import (
@@ -185,7 +186,8 @@ class AnthropicFilesConfig(BaseFilesConfig):
             AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
             or ANTHROPIC_FILES_API_BASE
         )
-        return f"{api_base.rstrip('/')}/v1/files/{file_id}", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base.rstrip('/')}/v1/files/{encoded_file_id}", {}
 
     def transform_retrieve_file_response(
         self,
@@ -206,7 +208,8 @@ class AnthropicFilesConfig(BaseFilesConfig):
             AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
             or ANTHROPIC_FILES_API_BASE
         )
-        return f"{api_base.rstrip('/')}/v1/files/{file_id}", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base.rstrip('/')}/v1/files/{encoded_file_id}", {}
 
     def transform_delete_file_response(
         self,
@@ -268,7 +271,8 @@ class AnthropicFilesConfig(BaseFilesConfig):
             AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
             or ANTHROPIC_FILES_API_BASE
         )
-        return f"{api_base.rstrip('/')}/v1/files/{file_id}/content", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base.rstrip('/')}/v1/files/{encoded_file_id}/content", {}
 
     def transform_file_content_response(
         self,

litellm/llms/anthropic/skills/transformation.py

@@ -7,6 +7,7 @@ from typing import Any, Dict, Optional, Tuple
 import httpx
 
 from litellm._logging import verbose_logger
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.skills.transformation import (
     BaseSkillsAPIConfig,
     LiteLLMLoggingObj,
@@ -81,7 +82,8 @@ class AnthropicSkillsConfig(BaseSkillsAPIConfig):
             api_base = AnthropicModelInfo.get_api_base()
 
         if skill_id:
-            return f"{api_base}/v1/skills/{skill_id}"
+            encoded_skill_id = encode_url_path_segment(skill_id, field_name="skill_id")
+            return f"{api_base}/v1/skills/{encoded_skill_id}"
         return f"{api_base}/v1/{endpoint}"
 
     def transform_create_skill_request(

litellm/llms/azure/azure.py

@@ -16,6 +16,7 @@ import litellm
 from litellm.constants import AZURE_OPERATION_POLLING_TIMEOUT, DEFAULT_MAX_RETRIES
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.litellm_core_utils.logging_utils import track_llm_api_timing
+from litellm.litellm_core_utils.url_utils import SSRFError, assert_same_origin
 from litellm.llms.custom_httpx.http_handler import (
     AsyncHTTPHandler,
     HTTPHandler,
@@ -792,6 +793,7 @@ class AzureChatCompletion(BaseAzureLLM, BaseLLM):
                     client=client,
                     litellm_params=litellm_params,
                     api_base=api_base,
+                    api_version=api_version,
                 )
             azure_client = self.get_azure_openai_client(
                 api_version=api_version,
@@ -898,6 +900,17 @@ class AzureChatCompletion(BaseAzureLLM, BaseLLM):
                 operation_location_url = response.headers["operation-location"]
             else:
                 raise AzureOpenAIError(status_code=500, message=response.text)
+            # Reject polling URLs that don't share an origin with ``api_base``.
+            # Without this an upstream-controlled or attacker-controlled
+            # value would receive the operator's Azure API key in the
+            # request headers below. VERIA-51.
+            try:
+                assert_same_origin(operation_location_url, api_base)
+            except SSRFError as ssrf_err:
+                raise AzureOpenAIError(
+                    status_code=502,
+                    message=f"Rejected polling URL: {ssrf_err}",
+                )
             response = await async_handler.get(
                 url=operation_location_url,
                 headers=headers,
@@ -908,8 +921,13 @@ class AzureChatCompletion(BaseAzureLLM, BaseLLM):
             timeout_secs: int = AZURE_OPERATION_POLLING_TIMEOUT
             start_time = time.time()
             if "status" not in response.json():
-                raise Exception(
-                    "Expected 'status' in response. Got={}".format(response.json())
+                # Don't reflect the raw response body — when the polling
+                # URL points at an internal JSON API (cloud metadata
+                # service etc.) reflecting it here turns Blind SSRF into
+                # Full-Read SSRF. VERIA-51.
+                raise AzureOpenAIError(
+                    status_code=502,
+                    message="Polling response missing 'status' field",
                 )
             while response.json()["status"] not in ["succeeded", "failed"]:
                 if time.time() - start_time > timeout_secs:
@@ -1009,6 +1027,13 @@ class AzureChatCompletion(BaseAzureLLM, BaseLLM):
                 operation_location_url = response.headers["operation-location"]
             else:
                 raise AzureOpenAIError(status_code=500, message=response.text)
+            try:
+                assert_same_origin(operation_location_url, api_base)
+            except SSRFError as ssrf_err:
+                raise AzureOpenAIError(
+                    status_code=502,
+                    message=f"Rejected polling URL: {ssrf_err}",
+                )
             response = sync_handler.get(
                 url=operation_location_url,
                 headers=headers,
@@ -1019,8 +1044,9 @@ class AzureChatCompletion(BaseAzureLLM, BaseLLM):
             timeout_secs: int = AZURE_OPERATION_POLLING_TIMEOUT
             start_time = time.time()
             if "status" not in response.json():
-                raise Exception(
-                    "Expected 'status' in response. Got={}".format(response.json())
+                raise AzureOpenAIError(
+                    status_code=502,
+                    message="Polling response missing 'status' field",
                 )
             while response.json()["status"] not in ["succeeded", "failed"]:
                 if time.time() - start_time > timeout_secs:

litellm/llms/azure/cost_calculation.py

@@ -12,7 +12,10 @@ from litellm.utils import get_model_info
 
 
 def cost_per_token(
-    model: str, usage: Usage, response_time_ms: Optional[float] = 0.0
+    model: str,
+    usage: Usage,
+    response_time_ms: Optional[float] = 0.0,
+    service_tier: Optional[str] = None,
 ) -> Tuple[float, float]:
     """
     Calculates the cost per token for a given model, prompt tokens, and completion tokens.
@@ -47,4 +50,5 @@ def cost_per_token(
         model=model,
         usage=usage,
         custom_llm_provider="azure",
+        service_tier=service_tier,
     )

litellm/llms/azure/responses/transformation.py

@@ -5,6 +5,7 @@ import httpx
 from openai.types.responses import ResponseReasoningItem
 
 from litellm._logging import verbose_logger
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.azure.common_utils import BaseAzureLLM
 from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig
 from litellm.types.llms.openai import *
@@ -201,7 +202,10 @@ class AzureOpenAIResponsesAPIConfig(OpenAIResponsesAPIConfig):
         # Insert the response_id at the end of the path component
         # Remove trailing slash if present to avoid double slashes
         path = parsed_url.path.rstrip("/")
-        new_path = f"{path}/{response_id}"
+        encoded_response_id = encode_url_path_segment(
+            response_id, field_name="response_id"
+        )
+        new_path = f"{path}/{encoded_response_id}"
 
         # Reconstruct the URL with all original components but with the modified path
         constructed_url = urlunparse(
@@ -322,7 +326,10 @@ class AzureOpenAIResponsesAPIConfig(OpenAIResponsesAPIConfig):
         # Insert the response_id and /cancel at the end of the path component
         # Remove trailing slash if present to avoid double slashes
         path = parsed_url.path.rstrip("/")
-        new_path = f"{path}/{response_id}/cancel"
+        encoded_response_id = encode_url_path_segment(
+            response_id, field_name="response_id"
+        )
+        new_path = f"{path}/{encoded_response_id}/cancel"
 
         # Reconstruct the URL with all original components but with the modified path
         cancel_url = urlunparse(

litellm/llms/azure_ai/agents/handler.py

@@ -36,6 +36,7 @@ from typing import (
 import httpx
 
 from litellm._logging import verbose_logger
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.azure_ai.agents.transformation import (
     AzureAIAgentsConfig,
     AzureAIAgentsError,
@@ -75,20 +76,29 @@ class AzureAIAgentsHandler:
     def _build_messages_url(
         self, api_base: str, thread_id: str, api_version: str
     ) -> str:
-        return f"{api_base}/threads/{thread_id}/messages?api-version={api_version}"
+        encoded_thread_id = encode_url_path_segment(thread_id, field_name="thread_id")
+        return (
+            f"{api_base}/threads/{encoded_thread_id}/messages?api-version={api_version}"
+        )
 
     def _build_runs_url(self, api_base: str, thread_id: str, api_version: str) -> str:
-        return f"{api_base}/threads/{thread_id}/runs?api-version={api_version}"
+        encoded_thread_id = encode_url_path_segment(thread_id, field_name="thread_id")
+        return f"{api_base}/threads/{encoded_thread_id}/runs?api-version={api_version}"
 
     def _build_run_status_url(
         self, api_base: str, thread_id: str, run_id: str, api_version: str
     ) -> str:
-        return f"{api_base}/threads/{thread_id}/runs/{run_id}?api-version={api_version}"
+        encoded_thread_id = encode_url_path_segment(thread_id, field_name="thread_id")
+        encoded_run_id = encode_url_path_segment(run_id, field_name="run_id")
+        return f"{api_base}/threads/{encoded_thread_id}/runs/{encoded_run_id}?api-version={api_version}"
 
     def _build_list_messages_url(
         self, api_base: str, thread_id: str, api_version: str
     ) -> str:
-        return f"{api_base}/threads/{thread_id}/messages?api-version={api_version}"
+        encoded_thread_id = encode_url_path_segment(thread_id, field_name="thread_id")
+        return (
+            f"{api_base}/threads/{encoded_thread_id}/messages?api-version={api_version}"
+        )
 
     def _build_create_thread_and_run_url(self, api_base: str, api_version: str) -> str:
         """URL for the create-thread-and-run endpoint (supports streaming)."""

litellm/llms/azure_ai/anthropic/transformation.py

@@ -12,6 +12,23 @@ if TYPE_CHECKING:
     pass
 
 
+def _promote_extra_body_to_optional_params(optional_params: dict) -> None:
+    """Promote anthropic-native passthrough keys out of ``extra_body``.
+
+    ``azure_ai`` is an OpenAI-compatible provider, so non-OpenAI kwargs like
+    ``output_config`` get auto-routed into ``extra_body`` by
+    ``add_provider_specific_params_to_optional_params``. For the Azure→Anthropic
+    route those keys must reach the request body and be validated, so promote
+    them. ``setdefault`` keeps explicit top-level values authoritative.
+    """
+    extra_body = optional_params.get("extra_body")
+    if not isinstance(extra_body, dict) or not extra_body:
+        return
+    for k, v in extra_body.items():
+        optional_params.setdefault(k, v)
+    optional_params.pop("extra_body", None)
+
+
 class AzureAnthropicConfig(AnthropicConfig):
     """
     Azure Anthropic configuration that extends AnthropicConfig.
@@ -39,6 +56,8 @@ class AzureAnthropicConfig(AnthropicConfig):
         1. API key via 'api-key' header
         2. Azure AD token via 'Authorization: Bearer <token>' header
         """
+        _promote_extra_body_to_optional_params(optional_params)
+
         # Convert dict to GenericLiteLLMParams if needed
         if isinstance(litellm_params, dict):
             # Ensure api_key is included if provided
@@ -101,7 +120,8 @@ class AzureAnthropicConfig(AnthropicConfig):
         Transform request using parent AnthropicConfig, then remove unsupported params.
         Azure Anthropic doesn't support extra_body, max_retries, or stream_options parameters.
         """
-        # Call parent transform_request
+        _promote_extra_body_to_optional_params(optional_params)
+
         data = super().transform_request(
             model=model,
             messages=messages,

litellm/llms/azure_ai/cost_calculator.py

@@ -65,6 +65,7 @@ def cost_per_token(
     usage: Usage,
     response_time_ms: Optional[float] = 0.0,
     request_model: Optional[str] = None,
+    service_tier: Optional[str] = None,
 ) -> Tuple[float, float]:
     """
     Calculate the cost per token for Azure AI models.
@@ -102,6 +103,7 @@ def cost_per_token(
             model=model,
             usage=usage,
             custom_llm_provider="azure_ai",
+            service_tier=service_tier,
         )
     except Exception as e:
         # For Model Router, the model name (e.g., "azure-model-router") may not be in the cost map

litellm/llms/azure_ai/ocr/document_intelligence/transformation.py

@@ -17,11 +17,13 @@ from urllib.parse import quote
 import httpx
 
 from litellm._logging import verbose_logger
+from litellm.litellm_core_utils.url_utils import SSRFError, assert_same_origin
 from litellm.constants import (
     AZURE_DOCUMENT_INTELLIGENCE_API_VERSION,
     AZURE_DOCUMENT_INTELLIGENCE_DEFAULT_DPI,
     AZURE_OPERATION_POLLING_TIMEOUT,
 )
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.ocr.transformation import (
     BaseOCRConfig,
     DocumentType,
@@ -217,11 +219,12 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig):
         if "/" in model:
             # Extract the last part after the last slash
             model_id = model.split("/")[-1]
+        encoded_model_id = encode_url_path_segment(model_id, field_name="model_id")
 
         # Azure Document Intelligence analyze endpoint
         # Note: API version 2024-11-30+ uses /documentintelligence/ (not /formrecognizer/)
         url = (
-            f"{api_base}/documentintelligence/documentModels/{model_id}:analyze"
+            f"{api_base}/documentintelligence/documentModels/{encoded_model_id}:analyze"
             f"?api-version={AZURE_DOCUMENT_INTELLIGENCE_API_VERSION}"
         )
 
@@ -599,6 +602,16 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig):
                         "Azure Document Intelligence returned 202 but no Operation-Location header found"
                     )
 
+                # Reject cross-origin polling URLs — the auth headers
+                # below would otherwise leak to whatever URL the upstream
+                # (or an attacker-controlled upstream) returns. VERIA-51.
+                try:
+                    assert_same_origin(operation_url, str(raw_response.request.url))
+                except SSRFError as ssrf_err:
+                    raise ValueError(
+                        f"Azure Document Intelligence: rejected polling URL ({ssrf_err})"
+                    )
+
                 # Get headers for polling (need auth)
                 poll_headers = {
                     "Ocp-Apim-Subscription-Key": raw_response.request.headers.get(
@@ -711,6 +724,14 @@ class AzureDocumentIntelligenceOCRConfig(BaseOCRConfig):
                         "Azure Document Intelligence returned 202 but no Operation-Location header found"
                     )
 
+                # Reject cross-origin polling URLs (see sync path). VERIA-51.
+                try:
+                    assert_same_origin(operation_url, str(raw_response.request.url))
+                except SSRFError as ssrf_err:
+                    raise ValueError(
+                        f"Azure Document Intelligence: rejected polling URL ({ssrf_err})"
+                    )
+
                 # Get headers for polling (need auth)
                 poll_headers = {
                     "Ocp-Apim-Subscription-Key": raw_response.request.headers.get(

litellm/llms/base_llm/chat/transformation.py

@@ -87,9 +87,7 @@ class BaseConfig(ABC):
         return {
             k: v
             for k, v in cls.__dict__.items()
-            if not k.startswith("__")
-            and not k.startswith("_abc")
-            and not k.startswith("_is_base_class")
+            if not k.startswith("_")
             and not isinstance(
                 v,
                 (

litellm/llms/bedrock/chat/converse_transformation.py

@@ -31,7 +31,11 @@ from litellm.litellm_core_utils.prompt_templates.factory import (
     _bedrock_converse_messages_pt,
     _bedrock_tools_pt,
 )
-from litellm.llms.anthropic.chat.transformation import AnthropicConfig
+from litellm.llms.anthropic.chat.transformation import (
+    DROP_UNSUPPORTED_OUTPUT_CONFIG_WARNING,
+    REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT,
+    AnthropicConfig,
+)
 from litellm.llms.base_llm.chat.transformation import BaseConfig, BaseLLMException
 from litellm.types.llms.bedrock import *
 from litellm.types.llms.openai import (
@@ -189,7 +193,7 @@ class AmazonConverseConfig(BaseConfig):
         return {
             k: v
             for k, v in cls.__dict__.items()
-            if not k.startswith("__")
+            if not k.startswith("_")
             and not isinstance(
                 v,
                 (
@@ -410,47 +414,64 @@ class AmazonConverseConfig(BaseConfig):
         """
         Handle the reasoning_effort parameter based on the model type.
 
-        Different model families handle reasoning effort differently:
-        - GPT-OSS models: Keep reasoning_effort as-is (passed to additionalModelRequestFields)
-        - Nova 2 models: Transform to reasoningConfig structure
-        - Other models (Anthropic, etc.): Convert to thinking parameter
-
-        Args:
-            model: The model identifier
-            reasoning_effort: The reasoning effort value
-            optional_params: Dictionary of optional parameters to update in-place
-
-        Examples:
-            >>> config = AmazonConverseConfig()
-            >>> params = {}
-            >>> config._handle_reasoning_effort_parameter("gpt-oss-model", "high", params)
-            >>> params
-            {'reasoning_effort': 'high'}
-
-            >>> params = {}
-            >>> config._handle_reasoning_effort_parameter("amazon.nova-2-lite-v1:0", "high", params)
-            >>> params
-            {'reasoningConfig': {'type': 'enabled', 'maxReasoningEffort': 'high'}}
-
-            >>> params = {}
-            >>> config._handle_reasoning_effort_parameter("anthropic.claude-3", "high", params)
-            >>> params
-            {'thinking': {'type': 'enabled', 'budget_tokens': 10000}}
+        - GPT-OSS models: passed through unchanged via additionalModelRequestFields.
+        - Nova 2 models: transformed to reasoningConfig.
+        - Anthropic models: mapped to ``thinking`` (and ``output_config.effort`` on
+          adaptive Claude 4.6 / 4.7).
         """
         if "gpt-oss" in model:
-            # GPT-OSS models: keep reasoning_effort as-is
-            # It will be passed through to additionalModelRequestFields
             optional_params["reasoning_effort"] = reasoning_effort
         elif self._is_nova_2_model(model):
-            # Nova 2 models: transform to reasoningConfig
             reasoning_config = self._transform_reasoning_effort_to_reasoning_config(
                 reasoning_effort
             )
             optional_params.update(reasoning_config)
         else:
-            # Anthropic and other models: convert to thinking parameter
-            optional_params["thinking"] = AnthropicConfig._map_reasoning_effort(
-                reasoning_effort=reasoning_effort, model=model
+            mapped_thinking = AnthropicConfig._map_reasoning_effort(
+                reasoning_effort=reasoning_effort,
+                model=model,
+                llm_provider="bedrock_converse",
+            )
+            if mapped_thinking is None:
+                optional_params.pop("thinking", None)
+                optional_params.pop("output_config", None)
+            else:
+                optional_params["thinking"] = mapped_thinking
+                if AnthropicConfig._is_adaptive_thinking_model(model):
+                    mapped_effort = REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT.get(
+                        reasoning_effort
+                    )
+                    if mapped_effort is None:
+                        AnthropicConfig._raise_invalid_reasoning_effort(
+                            model=model,
+                            value=reasoning_effort,
+                            llm_provider="bedrock_converse",
+                        )
+                    self._validate_anthropic_adaptive_effort(
+                        model=model, effort=mapped_effort
+                    )
+                    optional_params["output_config"] = {"effort": mapped_effort}
+
+    @staticmethod
+    def _validate_anthropic_adaptive_effort(model: str, effort: str) -> None:
+        """Validate ``output_config.effort`` for adaptive-thinking Claude 4.6/4.7."""
+        valid_efforts = {"high", "medium", "low", "xhigh", "max"}
+        if effort not in valid_efforts:
+            raise litellm.exceptions.BadRequestError(
+                message=(
+                    f"Invalid reasoning_effort/output_config.effort value: "
+                    f"{effort!r}. Must be one of: 'low', 'medium', 'high', "
+                    f"'xhigh', or 'max'."
+                ),
+                model=model,
+                llm_provider="bedrock_converse",
+            )
+        error = AnthropicConfig._validate_effort_for_model(model=model, effort=effort)
+        if error is not None:
+            raise litellm.exceptions.BadRequestError(
+                message=error,
+                model=model,
+                llm_provider="bedrock_converse",
             )
 
     @staticmethod
@@ -1192,9 +1213,11 @@ class AmazonConverseConfig(BaseConfig):
             + supported_config_params
         )
         inference_params.pop("json_mode", None)  # used for handling json_schema
-        # Anthropic-only key. Bedrock expects `outputConfig` (camelCase) and
-        # will reject `output_config` if it leaks through pass-through routes.
-        inference_params.pop("output_config", None)
+
+        # Anthropic-only ``output_config`` (snake_case) — re-attached to
+        # ``additionalModelRequestFields`` for Anthropic models below. The
+        # Bedrock-native ``outputConfig`` (camelCase) is handled separately.
+        anthropic_output_config = inference_params.pop("output_config", None)
 
         # Extract requestMetadata before processing other parameters
         request_metadata = inference_params.pop("requestMetadata", None)
@@ -1204,9 +1227,6 @@ class AmazonConverseConfig(BaseConfig):
         output_config: Optional[OutputConfigBlock] = inference_params.pop(
             "outputConfig", None
         )
-        inference_params.pop(
-            "output_config", None
-        )  # Bedrock Converse doesn't support it
 
         # keep supported params in 'inference_params', and set all model-specific params in 'additional_request_params'
         additional_request_params = {
@@ -1249,6 +1269,27 @@ class AmazonConverseConfig(BaseConfig):
             additional_request_params
         )
 
+        if anthropic_output_config is not None and isinstance(
+            anthropic_output_config, dict
+        ):
+            base_model = BedrockModelInfo.get_base_model(model)
+            if base_model.startswith("anthropic"):
+                if (
+                    litellm.drop_params is True
+                    and not AnthropicConfig._model_supports_effort_param(model)
+                ):
+                    litellm.verbose_logger.warning(
+                        DROP_UNSUPPORTED_OUTPUT_CONFIG_WARNING,
+                        model,
+                    )
+                else:
+                    effort = anthropic_output_config.get("effort")
+                    if effort is not None:
+                        self._validate_anthropic_adaptive_effort(
+                            model=model, effort=effort
+                        )
+                    additional_request_params["output_config"] = anthropic_output_config
+
         return (
             inference_params,
             additional_request_params,
@@ -1372,9 +1413,25 @@ class AmazonConverseConfig(BaseConfig):
         # Append pre-formatted tools (systemTool etc.) after transformation
         bedrock_tools.extend(pre_formatted_tools)
 
+        # Opus 4.5 gates ``output_config.effort`` behind a beta header;
+        # Claude 4.6/4.7 accept it without one.
+        base_model = BedrockModelInfo.get_base_model(model)
+        if base_model.startswith("anthropic"):
+            output_config = additional_request_params.get("output_config")
+            if (
+                isinstance(output_config, dict)
+                and output_config.get("effort") is not None
+                and not AnthropicConfig._is_adaptive_thinking_model(model)
+            ):
+                from litellm.types.llms.anthropic import (
+                    ANTHROPIC_EFFORT_BETA_HEADER,
+                )
+
+                if ANTHROPIC_EFFORT_BETA_HEADER not in anthropic_beta_list:
+                    anthropic_beta_list.append(ANTHROPIC_EFFORT_BETA_HEADER)
+
         # Set anthropic_beta in additional_request_params if we have any beta features
         # ONLY apply to Anthropic/Claude models - other models (e.g., Qwen, Llama) don't support this field
-        base_model = BedrockModelInfo.get_base_model(model)
         if anthropic_beta_list and base_model.startswith("anthropic"):
             additional_request_params["anthropic_beta"] = anthropic_beta_list
 

litellm/llms/bedrock/chat/invoke_agent/transformation.py

@@ -12,6 +12,7 @@ import httpx
 
 from litellm._logging import verbose_logger
 from litellm._uuid import uuid
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.litellm_core_utils.prompt_templates.common_utils import (
     convert_content_list_to_str,
 )
@@ -97,8 +98,15 @@ class AmazonInvokeAgentConfig(BaseConfig, BaseAWSLLM):
 
         agent_id, agent_alias_id = self._get_agent_id_and_alias_id(model)
         session_id = self._get_session_id(optional_params)
+        encoded_agent_id = encode_url_path_segment(agent_id, field_name="agent_id")
+        encoded_agent_alias_id = encode_url_path_segment(
+            agent_alias_id, field_name="agent_alias_id"
+        )
+        encoded_session_id = encode_url_path_segment(
+            session_id, field_name="session_id"
+        )
 
-        endpoint_url = f"{endpoint_url}/agents/{agent_id}/agentAliases/{agent_alias_id}/sessions/{session_id}/text"
+        endpoint_url = f"{endpoint_url}/agents/{encoded_agent_id}/agentAliases/{encoded_agent_alias_id}/sessions/{encoded_session_id}/text"
 
         return endpoint_url
 

litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py

@@ -169,7 +169,6 @@ class AmazonAnthropicClaudeConfig(AmazonInvokeConfig, AnthropicConfig):
         anthropic_request.pop("model", None)
         anthropic_request.pop("stream", None)
         anthropic_request.pop("output_format", None)
-        anthropic_request.pop("output_config", None)
         if "anthropic_version" not in anthropic_request:
             anthropic_request["anthropic_version"] = self.anthropic_version
 

litellm/llms/bedrock/count_tokens/transformation.py

@@ -201,13 +201,14 @@ class BedrockCountTokensConfig(BaseAWSLLM):
         # Remove bedrock/ prefix if present
         if model_id.startswith("bedrock/"):
             model_id = model_id[8:]  # Remove "bedrock/" prefix
+        encoded_model_id = self.encode_model_id(model_id=model_id)
 
         base_url, _ = self.get_runtime_endpoint(
             api_base=api_base,
             aws_bedrock_runtime_endpoint=aws_bedrock_runtime_endpoint,
             aws_region_name=aws_region_name,
         )
-        endpoint = f"{base_url}/model/{model_id}/count-tokens"
+        endpoint = f"{base_url}/model/{encoded_model_id}/count-tokens"
 
         return endpoint
 

litellm/llms/bedrock/files/handler.py

@@ -1,10 +1,17 @@
 import asyncio
 import base64
-from typing import Any, Coroutine, Optional, Tuple, Union
+import os
+from types import MappingProxyType
+from typing import Any, Coroutine, Mapping, Optional, Tuple, Union, cast
 
 import httpx
 
 from litellm import LlmProviders
+from litellm.litellm_core_utils.cloud_storage_security import (
+    BEDROCK_MANAGED_S3_PREFIXES,
+    should_allow_legacy_cloud_file_ids,
+    validate_managed_cloud_file_id,
+)
 from litellm.llms.custom_httpx.http_handler import get_async_httpx_client
 from litellm.types.llms.openai import (
     FileContentRequest,
@@ -35,7 +42,7 @@ class BedrockFilesHandler(BaseAWSLLM):
 
         The file ID can be in two formats:
         1. Base64-encoded unified file ID containing: llm_output_file_id,s3://bucket/path
-        2. Direct S3 URI: s3://bucket/path
+        2. Direct S3 URI: s3://bucket/litellm-managed-prefix/path
 
         Args:
             file_id: Encoded file ID or direct S3 URI
@@ -58,14 +65,19 @@ class BedrockFilesHandler(BaseAWSLLM):
         except Exception:
             pass
 
-        # If not base64 encoded or doesn't contain llm_output_file_id, assume it's already an S3 URI
+        # If not base64 encoded or doesn't contain llm_output_file_id, accept only
+        # explicit S3 URIs. Bucket and key validation happens before any S3 call.
         if file_id.startswith("s3://"):
             return file_id
 
-        # If it doesn't start with s3://, assume it's a direct S3 URI and add the prefix
-        return f"s3://{file_id}"
+        raise ValueError("file_id must be a managed LiteLLM S3 file id")
 
-    def _parse_s3_uri(self, s3_uri: str) -> Tuple[str, str]:
+    def _parse_s3_uri(
+        self,
+        s3_uri: str,
+        configured_bucket_name: str,
+        allow_legacy_cloud_file_ids: bool = False,
+    ) -> Tuple[str, str]:
         """
         Parse S3 URI to extract bucket name and object key.
 
@@ -75,21 +87,34 @@ class BedrockFilesHandler(BaseAWSLLM):
         Returns:
             Tuple of (bucket_name, object_key)
         """
-        if not s3_uri.startswith("s3://"):
-            raise ValueError(
-                f"Invalid S3 URI format: {s3_uri}. Expected format: s3://bucket-name/path/to/file"
+        return validate_managed_cloud_file_id(
+            file_id=s3_uri,
+            scheme="s3://",
+            configured_bucket_name=configured_bucket_name,
+            allowed_object_prefixes=BEDROCK_MANAGED_S3_PREFIXES,
+            allow_legacy_cloud_file_ids=allow_legacy_cloud_file_ids,
+        )
+
+    def _get_configured_s3_bucket_name(self, litellm_params: dict) -> str:
+        trusted_model_credentials = litellm_params.get(
+            "_litellm_internal_model_credentials"
+        )
+        bucket_name = None
+        if isinstance(trusted_model_credentials, type(MappingProxyType({}))):
+            trusted_model_credentials_mapping = cast(
+                Mapping[str, Any], trusted_model_credentials
             )
-
-        # Remove 's3://' prefix
-        path = s3_uri[5:]
-
-        if "/" in path:
-            bucket_name, object_key = path.split("/", 1)
-        else:
-            bucket_name = path
-            object_key = ""
-
-        return bucket_name, object_key
+            candidate_bucket_name = trusted_model_credentials_mapping.get(
+                "s3_bucket_name"
+            )
+            if isinstance(candidate_bucket_name, str):
+                bucket_name = candidate_bucket_name
+        bucket_name = bucket_name or os.getenv("AWS_S3_BUCKET_NAME")
+        if not bucket_name:
+            raise ValueError(
+                "S3 bucket_name is required. Set 's3_bucket_name' in proxy config or AWS_S3_BUCKET_NAME for Bedrock file content retrieval."
+            )
+        return bucket_name
 
     async def afile_content(
         self,
@@ -119,7 +144,14 @@ class BedrockFilesHandler(BaseAWSLLM):
 
         # Extract S3 URI from file ID
         s3_uri = self._extract_s3_uri_from_file_id(file_id)
-        bucket_name, object_key = self._parse_s3_uri(s3_uri)
+        configured_bucket_name = self._get_configured_s3_bucket_name(optional_params)
+        bucket_name, object_key = self._parse_s3_uri(
+            s3_uri=s3_uri,
+            configured_bucket_name=configured_bucket_name,
+            allow_legacy_cloud_file_ids=should_allow_legacy_cloud_file_ids(
+                optional_params
+            ),
+        )
 
         # Get AWS credentials
         aws_region_name = self._get_aws_region_name(

litellm/llms/bedrock/files/transformation.py

@@ -2,6 +2,7 @@ import json
 import os
 import time
 from typing import Any, Dict, List, Optional, Tuple, Union
+from urllib.parse import unquote
 
 import httpx
 from httpx import Headers, Response
@@ -10,6 +11,14 @@ from openai.types.file_deleted import FileDeleted
 from litellm._logging import verbose_logger
 from litellm._uuid import uuid
 from litellm.files.utils import FilesAPIUtils
+from litellm.litellm_core_utils.cloud_storage_security import (
+    BEDROCK_MANAGED_S3_BATCH_PREFIX,
+    BEDROCK_MANAGED_S3_UPLOAD_PREFIX,
+    build_managed_cloud_object_name,
+    encode_s3_object_key_for_url,
+    sanitize_cloud_object_component,
+    split_configured_cloud_bucket_name,
+)
 from litellm.litellm_core_utils.prompt_templates.common_utils import extract_file_data
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.base_llm.files.transformation import (
@@ -116,10 +125,13 @@ class BedrockFilesConfig(BaseAWSLLM, BaseFilesConfig):
         if _model.startswith("bedrock/"):
             _model = _model[8:]
 
-        # Replace colons with hyphens for Bedrock S3 URI compliance
-        _model = _model.replace(":", "-")
+        safe_model = sanitize_cloud_object_component(
+            _model.replace(":", "-"), fallback="model"
+        )
 
-        object_name = f"litellm-bedrock-files-{_model}-{uuid.uuid4()}.jsonl"
+        object_name = (
+            f"{BEDROCK_MANAGED_S3_BATCH_PREFIX}{safe_model}-{uuid.uuid4()}.jsonl"
+        )
         return object_name
 
     def get_object_name(
@@ -146,12 +158,13 @@ class BedrockFilesConfig(BaseAWSLLM, BaseFilesConfig):
             if len(openai_jsonl_content) > 0:
                 return self._get_s3_object_name_from_batch_jsonl(openai_jsonl_content)
 
-        ## 2. If not jsonl, return the filename
+        ## 2. If not jsonl, store under a server-generated managed object name
         filename = extracted_file_data.get("filename")
-        if filename:
-            return filename
-        ## 3. If no file name, return timestamp
-        return str(int(time.time()))
+        return build_managed_cloud_object_name(
+            prefix=BEDROCK_MANAGED_S3_UPLOAD_PREFIX,
+            filename=filename,
+            fallback_filename="file",
+        )
 
     def get_complete_file_url(
         self,
@@ -172,6 +185,7 @@ class BedrockFilesConfig(BaseAWSLLM, BaseFilesConfig):
             raise ValueError(
                 "S3 bucket_name is required. Set 's3_bucket_name' in litellm_params or AWS_S3_BUCKET_NAME env var"
             )
+        bucket_name, object_prefix = split_configured_cloud_bucket_name(bucket_name)
 
         s3_region_name = litellm_params.get("s3_region_name") or optional_params.get(
             "s3_region_name"
@@ -188,14 +202,17 @@ class BedrockFilesConfig(BaseAWSLLM, BaseFilesConfig):
             raise ValueError("purpose is required")
         extracted_file_data = extract_file_data(file_data)
         object_name = self.get_object_name(extracted_file_data, purpose)
+        if object_prefix:
+            object_name = f"{object_prefix}/{object_name}"
+        encoded_object_name = encode_s3_object_key_for_url(object_name)
 
         # S3 endpoint URL format
         s3_endpoint_url = (
             optional_params.get("s3_endpoint_url")
             or f"https://s3.{aws_region_name}.amazonaws.com"
-        )
+        ).rstrip("/")
 
-        return f"{s3_endpoint_url}/{bucket_name}/{object_name}"
+        return f"{s3_endpoint_url}/{bucket_name}/{encoded_object_name}"
 
     def get_supported_openai_params(
         self, model: str
@@ -532,10 +549,12 @@ class BedrockFilesConfig(BaseAWSLLM, BaseFilesConfig):
         if match1:
             # Pattern: https://s3.region.amazonaws.com/bucket/key
             region, bucket, key = match1.groups()
+            key = unquote(key)
             s3_uri = f"s3://{bucket}/{key}"
         elif match2:
             # Pattern: https://bucket.s3.region.amazonaws.com/key
             bucket, region, key = match2.groups()
+            key = unquote(key)
             s3_uri = f"s3://{bucket}/{key}"
         else:
             # Fallback: try to extract bucket and key from URL path
@@ -545,6 +564,7 @@ class BedrockFilesConfig(BaseAWSLLM, BaseFilesConfig):
             path_parts = parsed.path.lstrip("/").split("/", 1)
             if len(path_parts) >= 2:
                 bucket, key = path_parts[0], path_parts[1]
+                key = unquote(key)
                 s3_uri = f"s3://{bucket}/{key}"
             else:
                 raise ValueError(f"Unable to parse S3 URL: {https_url}")
@@ -722,7 +742,12 @@ class BedrockJsonlFilesTransformation:
         # Remove bedrock/ prefix if present
         if _model.startswith("bedrock/"):
             _model = _model[8:]
-        object_name = f"litellm-bedrock-files-{_model}-{uuid.uuid4()}.jsonl"
+        safe_model = sanitize_cloud_object_component(
+            _model.replace(":", "-"), fallback="model"
+        )
+        object_name = (
+            f"{BEDROCK_MANAGED_S3_BATCH_PREFIX}{safe_model}-{uuid.uuid4()}.jsonl"
+        )
         return object_name
 
     def _get_content_from_openai_file(self, openai_file_content: FileTypes) -> str:

litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py

@@ -12,9 +12,14 @@ from typing import (
 
 import httpx
 
+import litellm
 from litellm.anthropic_beta_headers_manager import filter_and_transform_beta_headers
 from litellm.constants import BEDROCK_MIN_THINKING_BUDGET_TOKENS
 from litellm.litellm_core_utils.litellm_logging import verbose_logger
+from litellm.llms.anthropic.chat.transformation import (
+    DROP_UNSUPPORTED_OUTPUT_CONFIG_WARNING,
+    AnthropicConfig,
+)
 from litellm.llms.anthropic.common_utils import AnthropicModelInfo
 from litellm.llms.anthropic.experimental_pass_through.messages.transformation import (
     AnthropicMessagesConfig,
@@ -580,6 +585,17 @@ class AmazonAnthropicClaudeMessagesConfig(
         if filtered_betas:
             anthropic_messages_request["anthropic_beta"] = filtered_betas
 
+        if (
+            litellm.drop_params is True
+            and "output_config" in anthropic_messages_request
+            and not AnthropicConfig._model_supports_effort_param(model)
+        ):
+            verbose_logger.warning(
+                DROP_UNSUPPORTED_OUTPUT_CONFIG_WARNING,
+                model,
+            )
+            anthropic_messages_request.pop("output_config", None)
+
         # 7. Final safety net: filter top-level fields to the Bedrock Invoke allowlist.
         # Catches Anthropic-only extensions (context_management, output_config, speed,
         # mcp_servers, ...) and any future additions Claude Code may start sending.

litellm/llms/bedrock/vector_stores/transformation.py

@@ -5,6 +5,7 @@ from urllib.parse import urlparse
 import httpx
 
 from litellm._logging import verbose_logger
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.vector_store.transformation import BaseVectorStoreConfig
 from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM
 from litellm.types.integrations.rag.bedrock_knowledgebase import (
@@ -209,7 +210,10 @@ class BedrockVectorStoreConfig(BaseVectorStoreConfig, BaseAWSLLM):
         if isinstance(query, list):
             query = " ".join(query)
 
-        url = f"{api_base}/{vector_store_id}/retrieve"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}/retrieve"
 
         request_body: Dict[str, Any] = {
             "retrievalQuery": BedrockKBRetrievalQuery(text=query),

litellm/llms/black_forest_labs/image_edit/handler.py

@@ -15,6 +15,7 @@ import httpx
 import litellm
 from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.litellm_core_utils.url_utils import SSRFError, assert_same_origin
 from litellm.llms.custom_httpx.http_handler import (
     AsyncHTTPHandler,
     HTTPHandler,
@@ -331,6 +332,17 @@ class BlackForestLabsImageEdit:
                 message="No polling_url in BFL response",
             )
 
+        # Reject cross-origin polling URLs — the ``x-key`` auth header
+        # would otherwise leak to whatever URL the upstream returns.
+        # VERIA-51.
+        try:
+            assert_same_origin(polling_url, str(initial_response.request.url))
+        except SSRFError as ssrf_err:
+            raise BlackForestLabsError(
+                status_code=502,
+                message=f"Rejected polling URL: {ssrf_err}",
+            )
+
         # Get just the auth header for polling
         polling_headers = {"x-key": headers.get("x-key", "")}
 
@@ -416,6 +428,17 @@ class BlackForestLabsImageEdit:
                 message="No polling_url in BFL response",
             )
 
+        # Reject cross-origin polling URLs — the ``x-key`` auth header
+        # would otherwise leak to whatever URL the upstream returns.
+        # VERIA-51.
+        try:
+            assert_same_origin(polling_url, str(initial_response.request.url))
+        except SSRFError as ssrf_err:
+            raise BlackForestLabsError(
+                status_code=502,
+                message=f"Rejected polling URL: {ssrf_err}",
+            )
+
         # Get just the auth header for polling
         polling_headers = {"x-key": headers.get("x-key", "")}
 

litellm/llms/black_forest_labs/image_generation/handler.py

@@ -15,6 +15,7 @@ import httpx
 import litellm
 from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.litellm_core_utils.url_utils import SSRFError, assert_same_origin
 from litellm.llms.custom_httpx.http_handler import (
     AsyncHTTPHandler,
     HTTPHandler,
@@ -317,6 +318,17 @@ class BlackForestLabsImageGeneration:
                 message="No polling_url in BFL response",
             )
 
+        # Reject cross-origin polling URLs — the ``x-key`` auth header
+        # would otherwise leak to whatever URL the upstream returns.
+        # VERIA-51.
+        try:
+            assert_same_origin(polling_url, str(initial_response.request.url))
+        except SSRFError as ssrf_err:
+            raise BlackForestLabsError(
+                status_code=502,
+                message=f"Rejected polling URL: {ssrf_err}",
+            )
+
         # Get just the auth header for polling
         polling_headers = {"x-key": headers.get("x-key", "")}
 
@@ -402,6 +414,17 @@ class BlackForestLabsImageGeneration:
                 message="No polling_url in BFL response",
             )
 
+        # Reject cross-origin polling URLs — the ``x-key`` auth header
+        # would otherwise leak to whatever URL the upstream returns.
+        # VERIA-51.
+        try:
+            assert_same_origin(polling_url, str(initial_response.request.url))
+        except SSRFError as ssrf_err:
+            raise BlackForestLabsError(
+                status_code=502,
+                message=f"Rejected polling URL: {ssrf_err}",
+            )
+
         # Get just the auth header for polling
         polling_headers = {"x-key": headers.get("x-key", "")}
 

litellm/llms/bytez/chat/transformation.py

@@ -5,6 +5,7 @@ from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union
 
 import httpx
 
+from litellm.litellm_core_utils.url_utils import encode_url_path_segments
 from litellm.litellm_core_utils.exception_mapping_utils import exception_type
 from litellm.litellm_core_utils.logging_utils import track_llm_api_timing
 from litellm.llms.base_llm.chat.transformation import BaseConfig, BaseLLMException
@@ -149,7 +150,8 @@ class BytezChatConfig(BaseConfig):
         litellm_params: dict,
         stream: Optional[bool] = None,
     ) -> str:
-        return f"{API_BASE}/{model}"
+        encoded_model = encode_url_path_segments(model, field_name="model")
+        return f"{API_BASE}/{encoded_model}"
 
     def transform_request(
         self,

litellm/llms/cloudflare/chat/transformation.py

@@ -5,6 +5,7 @@ from typing import AsyncIterator, Iterator, List, Optional, Union
 import httpx
 
 import litellm
+from litellm.litellm_core_utils.url_utils import encode_url_path_segments
 from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator
 from litellm.llms.base_llm.chat.transformation import (
     BaseConfig,
@@ -89,7 +90,8 @@ class CloudflareChatConfig(BaseConfig):
             api_base = (
                 f"https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/"
             )
-        return api_base + model
+        encoded_model = encode_url_path_segments(model, field_name="model")
+        return api_base + encoded_model
 
     def get_supported_openai_params(self, model: str) -> List[str]:
         return [
@@ -147,9 +149,9 @@ class CloudflareChatConfig(BaseConfig):
     ) -> ModelResponse:
         completion_response = raw_response.json()
 
-        model_response.choices[0].message.content = completion_response["result"][  # type: ignore
-            "response"
-        ]
+        # Support both "response" and "response_text" keys (newer models like Nemotron use "response_text")
+        result = completion_response["result"]
+        model_response.choices[0].message.content = result.get("response") if result.get("response") is not None else result.get("response_text", "")  # type: ignore
 
         prompt_tokens = litellm.utils.get_token_count(messages=messages, model=model)
         completion_tokens = len(
@@ -199,8 +201,10 @@ class CloudflareChatResponseIterator(BaseModelResponseIterator):
 
             index = int(chunk.get("index", 0))
 
-            if "response" in chunk:
+            if "response" in chunk and chunk["response"] is not None:
                 text = chunk["response"]
+            elif "response_text" in chunk and chunk["response_text"] is not None:
+                text = chunk["response_text"]
 
             returned_chunk = GenericStreamingChunk(
                 text=text,

litellm/llms/custom_httpx/container_handler.py

@@ -12,6 +12,7 @@ from typing import TYPE_CHECKING, Any, Coroutine, Dict, Optional, Type, Union
 import httpx
 
 import litellm
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.custom_httpx.http_handler import (
     AsyncHTTPHandler,
     HTTPHandler,
@@ -72,7 +73,8 @@ def _build_url(
 
     # Substitute path parameters
     for param, value in path_params.items():
-        path_template = path_template.replace(f"{{{param}}}", value)
+        encoded_value = encode_url_path_segment(value, field_name=param)
+        path_template = path_template.replace(f"{{{param}}}", encoded_value)
 
     # Parse the api_base to extract existing query params
     parsed_base = httpx.URL(api_base)

litellm/llms/custom_httpx/llm_http_handler.py

@@ -26,6 +26,7 @@ from litellm._logging import _redact_string, verbose_logger
 from litellm.anthropic_beta_headers_manager import update_headers_with_filtered_beta
 from litellm.constants import REALTIME_WEBSOCKET_MAX_MESSAGE_SIZE_BYTES
 from litellm.litellm_core_utils.realtime_streaming import RealTimeStreaming
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.anthropic_messages.transformation import (
     BaseAnthropicMessagesConfig,
 )
@@ -8948,7 +8949,10 @@ class BaseLLMHTTPHandler:
             litellm_params=dict(litellm_params),
         )
 
-        url = f"{api_base}/{vector_store_id}"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}"
 
         logging_obj.pre_call(
             input="",
@@ -9015,7 +9019,10 @@ class BaseLLMHTTPHandler:
             litellm_params=dict(litellm_params),
         )
 
-        url = f"{api_base}/{vector_store_id}"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}"
 
         logging_obj.pre_call(
             input="",
@@ -9214,7 +9221,10 @@ class BaseLLMHTTPHandler:
             litellm_params=dict(litellm_params),
         )
 
-        url = f"{api_base}/{vector_store_id}"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}"
 
         request_body: Dict[str, Any] = dict(vector_store_update_optional_params)
 
@@ -9297,7 +9307,10 @@ class BaseLLMHTTPHandler:
             litellm_params=dict(litellm_params),
         )
 
-        url = f"{api_base}/{vector_store_id}"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}"
 
         request_body: Dict[str, Any] = dict(vector_store_update_optional_params)
 
@@ -9363,7 +9376,10 @@ class BaseLLMHTTPHandler:
             litellm_params=dict(litellm_params),
         )
 
-        url = f"{api_base}/{vector_store_id}"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}"
 
         logging_obj.pre_call(
             input="",
@@ -9428,7 +9444,10 @@ class BaseLLMHTTPHandler:
             litellm_params=dict(litellm_params),
         )
 
-        url = f"{api_base}/{vector_store_id}"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}"
 
         logging_obj.pre_call(
             input="",

litellm/llms/databricks/chat/transformation.py

@@ -56,7 +56,10 @@ from litellm.types.utils import (
     Usage,
 )
 
-from ...anthropic.chat.transformation import AnthropicConfig
+from ...anthropic.chat.transformation import (
+    REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT,
+    AnthropicConfig,
+)
 from ...openai_like.chat.transformation import OpenAILikeChatConfig
 from ..common_utils import DatabricksBase, DatabricksException
 
@@ -330,9 +333,30 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig):
             )  # unsupported for claude models - if json_schema -> convert to tool call
 
         if "reasoning_effort" in non_default_params and "claude" in model:
-            optional_params["thinking"] = AnthropicConfig._map_reasoning_effort(
-                reasoning_effort=non_default_params.get("reasoning_effort"), model=model
+            reasoning_effort_value = non_default_params.get("reasoning_effort")
+            mapped_thinking = AnthropicConfig._map_reasoning_effort(
+                reasoning_effort=reasoning_effort_value,
+                model=model,
+                llm_provider="databricks",
             )
+            if mapped_thinking is None:
+                optional_params.pop("thinking", None)
+                optional_params.pop("output_config", None)
+            else:
+                optional_params["thinking"] = mapped_thinking
+                if AnthropicConfig._is_adaptive_thinking_model(model):
+                    mapped_effort: Optional[str] = None
+                    if isinstance(reasoning_effort_value, str):
+                        mapped_effort = REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT.get(
+                            reasoning_effort_value
+                        )
+                    if mapped_effort is None:
+                        AnthropicConfig._raise_invalid_reasoning_effort(
+                            model=model,
+                            value=reasoning_effort_value,
+                            llm_provider="databricks",
+                        )
+                    optional_params["output_config"] = {"effort": mapped_effort}
             optional_params.pop("reasoning_effort", None)
         ## handle thinking tokens
         self.update_optional_params_with_thinking_tokens(

litellm/llms/elevenlabs/text_to_speech/transformation.py

@@ -11,13 +11,14 @@ import httpx
 from httpx import Headers
 
 import litellm
-from litellm.types.utils import all_litellm_params
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.base_llm.text_to_speech.transformation import (
     BaseTextToSpeechConfig,
     TextToSpeechRequestData,
 )
 from litellm.secret_managers.main import get_secret_str
+from litellm.types.utils import all_litellm_params
 
 from ..common_utils import ElevenLabsException
 
@@ -321,7 +322,8 @@ class ElevenLabsTextToSpeechConfig(BaseTextToSpeechConfig):
                 "ElevenLabs voice_id is required. Pass `voice` when calling `litellm.speech()`."
             )
 
-        url = f"{base_url}{self.TTS_ENDPOINT_PATH}/{voice_id}"
+        encoded_voice_id = encode_url_path_segment(voice_id, field_name="voice_id")
+        url = f"{base_url}{self.TTS_ENDPOINT_PATH}/{encoded_voice_id}"
 
         query_params = litellm_params.get(self.ELEVENLABS_QUERY_PARAMS_KEY, {})
         if query_params:

litellm/llms/gemini/files/transformation.py

@@ -12,6 +12,7 @@ import httpx
 from openai.types.file_deleted import FileDeleted
 
 from litellm._logging import verbose_logger
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.litellm_core_utils.prompt_templates.common_utils import extract_file_data
 from litellm.llms.base_llm.files.transformation import (
     BaseFilesConfig,
@@ -258,10 +259,14 @@ class GoogleAIStudioFilesHandler(GeminiModelInfo, BaseFilesConfig):
             normalized_file_id = file_id
 
         normalized_file_id = normalized_file_id.strip("/")
-        if not normalized_file_id.startswith("files/"):
-            normalized_file_id = f"files/{normalized_file_id}"
+        if normalized_file_id.startswith("files/"):
+            normalized_file_id = normalized_file_id.removeprefix("files/")
 
-        return normalized_file_id
+        encoded_file_id = encode_url_path_segment(
+            normalized_file_id, field_name="file_id"
+        )
+
+        return f"files/{encoded_file_id}"
 
     def transform_retrieve_file_response(
         self,
@@ -337,13 +342,8 @@ class GoogleAIStudioFilesHandler(GeminiModelInfo, BaseFilesConfig):
         if not api_key:
             raise ValueError("api_key is required")
 
-        # Extract file name from URI if full URI is provided
-        # file_id could be "files/abc123" or "https://generativelanguage.googleapis.com/v1beta/files/abc123"
-        if file_id.startswith("http"):
-            # Extract the file path from full URI
-            file_name = file_id.split("/v1beta/")[-1]
-        else:
-            file_name = file_id if file_id.startswith("files/") else f"files/{file_id}"
+        # Normalize and encode the file name before interpolating it into the URL.
+        file_name = self._normalize_gemini_file_id(file_id)
 
         # Construct the delete URL
         url = f"{api_base}/v1beta/{file_name}"

litellm/llms/gemini/interactions/transformation.py

@@ -15,6 +15,7 @@ import httpx
 
 from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.core_helpers import process_response_headers
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.interactions.transformation import BaseInteractionsAPIConfig
 from litellm.llms.gemini.common_utils import GeminiError, GeminiModelInfo
 from litellm.types.interactions import (
@@ -205,8 +206,11 @@ class GoogleAIStudioInteractionsConfig(BaseInteractionsAPIConfig):
         resolved_api_base = GeminiModelInfo.get_api_base(api_base)
         if not GeminiModelInfo.get_api_key(litellm_params.api_key):
             raise ValueError("Google API key is required")
+        encoded_interaction_id = encode_url_path_segment(
+            interaction_id, field_name="interaction_id"
+        )
         return (
-            f"{resolved_api_base}/{self.api_version}/interactions/{interaction_id}",
+            f"{resolved_api_base}/{self.api_version}/interactions/{encoded_interaction_id}",
             {},
         )
 
@@ -238,8 +242,11 @@ class GoogleAIStudioInteractionsConfig(BaseInteractionsAPIConfig):
         resolved_api_base = GeminiModelInfo.get_api_base(api_base)
         if not GeminiModelInfo.get_api_key(litellm_params.api_key):
             raise ValueError("Google API key is required")
+        encoded_interaction_id = encode_url_path_segment(
+            interaction_id, field_name="interaction_id"
+        )
         return (
-            f"{resolved_api_base}/{self.api_version}/interactions/{interaction_id}",
+            f"{resolved_api_base}/{self.api_version}/interactions/{encoded_interaction_id}",
             {},
         )
 
@@ -268,8 +275,11 @@ class GoogleAIStudioInteractionsConfig(BaseInteractionsAPIConfig):
         resolved_api_base = GeminiModelInfo.get_api_base(api_base)
         if not GeminiModelInfo.get_api_key(litellm_params.api_key):
             raise ValueError("Google API key is required")
+        encoded_interaction_id = encode_url_path_segment(
+            interaction_id, field_name="interaction_id"
+        )
         return (
-            f"{resolved_api_base}/{self.api_version}/interactions/{interaction_id}:cancel",
+            f"{resolved_api_base}/{self.api_version}/interactions/{encoded_interaction_id}:cancel",
             {},
         )
 

litellm/llms/hosted_vllm/embedding/README.md

@@ -2,4 +2,15 @@ No transformation is required for hosted_vllm embedding.
 
 VLLM is a superset of OpenAI's `embedding` endpoint.
 
-To pass provider-specific parameters, see [this](https://docs.litellm.ai/docs/completion/provider_specific_params)
+## `encoding_format`
+
+For OpenAI-compatible embedding calls (including `openai/...` with a custom `api_base` pointing at vLLM), LiteLLM resolves `encoding_format` when it is not set on the request:
+
+1. Explicit value on the embedding call (`encoding_format=...`).
+2. Model config (`litellm_params.encoding_format` on the proxy `model_list` entry).
+3. Environment variable `LITELLM_DEFAULT_EMBEDDING_ENCODING_FORMAT` (e.g. in `.env` or container env).
+4. Default **`float`**.
+
+That avoids forwarding `encoding_format=None` to the provider/SDK where some servers behave poorly.
+
+To pass provider-specific parameters, see [provider-specific params](https://docs.litellm.ai/docs/completion/provider_specific_params).

litellm/llms/manus/files/transformation.py

@@ -18,6 +18,7 @@ from openai.types.file_deleted import FileDeleted
 
 import litellm
 from litellm._logging import verbose_logger
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.litellm_core_utils.prompt_templates.common_utils import extract_file_data
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.base_llm.files.transformation import (
@@ -306,7 +307,8 @@ class ManusFilesConfig(BaseFilesConfig):
             optional_params=optional_params,
             litellm_params=litellm_params,
         )
-        return f"{api_base}/{file_id}", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base}/{encoded_file_id}", {}
 
     def transform_retrieve_file_response(
         self,
@@ -336,7 +338,8 @@ class ManusFilesConfig(BaseFilesConfig):
             optional_params=optional_params,
             litellm_params=litellm_params,
         )
-        return f"{api_base}/{file_id}", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base}/{encoded_file_id}", {}
 
     def transform_delete_file_response(
         self,
@@ -422,7 +425,8 @@ class ManusFilesConfig(BaseFilesConfig):
             optional_params=optional_params,
             litellm_params=litellm_params,
         )
-        return f"{api_base}/{file_id}/content", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base}/{encoded_file_id}/content", {}
 
     def transform_file_content_response(
         self,

litellm/llms/manus/responses/transformation.py

@@ -6,6 +6,7 @@ import httpx
 import litellm
 from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.core_helpers import process_response_headers
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.litellm_core_utils.llm_response_utils.convert_dict_to_response import (
     _safe_convert_created_field,
 )
@@ -270,7 +271,10 @@ class ManusResponsesAPIConfig(OpenAIResponsesAPIConfig):
 
         Reference: https://open.manus.im/docs/openai-compatibility
         """
-        url = f"{api_base}/{response_id}"
+        encoded_response_id = encode_url_path_segment(
+            response_id, field_name="response_id"
+        )
+        url = f"{api_base}/{encoded_response_id}"
         data: Dict = {}
         return url, data
 

litellm/llms/openai/chat/gpt_5_transformation.py

@@ -244,9 +244,11 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
                         ),
                         status_code=400,
                     )
-        elif effective_effort == "minimal":
-            # minimal is opt-out: unknown models pass through; only block when
-            # the model map explicitly sets supports_minimal_reasoning_effort=false.
+        elif effective_effort in ("minimal", "low"):
+            # minimal/low are opt-out: unknown models pass through; only block when
+            # the model map explicitly sets supports_{level}_reasoning_effort=false.
+            # Example: gpt-5.5-pro only accepts {medium, high, xhigh}, so it sets
+            # supports_low_reasoning_effort=false (and supports_minimal=false).
             if self._is_reasoning_effort_level_explicitly_disabled(
                 model, effective_effort
             ):

litellm/llms/openai/containers/transformation.py

@@ -6,6 +6,7 @@ import litellm
 from litellm.litellm_core_utils.llm_cost_calc.tool_call_cost_tracking import (
     StandardBuiltInToolCostTracking,
 )
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.secret_managers.main import get_secret_str
 from litellm.types.containers.main import (
     ContainerCreateOptionalRequestParams,
@@ -198,7 +199,10 @@ class OpenAIContainerConfig(BaseContainerConfig):
     ) -> Tuple[str, Dict]:
         """Transform the OpenAI container retrieve request."""
         # For container retrieve, we just need to construct the URL
-        url = join_container_api_base_path(api_base, f"/{container_id}")
+        encoded_container_id = encode_url_path_segment(
+            container_id, field_name="container_id"
+        )
+        url = join_container_api_base_path(api_base, f"/{encoded_container_id}")
 
         # No additional data needed for GET request
         data: Dict[str, Any] = {}
@@ -230,7 +234,10 @@ class OpenAIContainerConfig(BaseContainerConfig):
         - DELETE /v1/containers/{container_id}
         """
         # Construct the URL for container delete
-        url = join_container_api_base_path(api_base, f"/{container_id}")
+        encoded_container_id = encode_url_path_segment(
+            container_id, field_name="container_id"
+        )
+        url = join_container_api_base_path(api_base, f"/{encoded_container_id}")
 
         # No data needed for DELETE request
         data: Dict[str, Any] = {}
@@ -267,7 +274,10 @@ class OpenAIContainerConfig(BaseContainerConfig):
         - GET /v1/containers/{container_id}/files
         """
         # Construct the URL for container files
-        url = join_container_api_base_path(api_base, f"/{container_id}/files")
+        encoded_container_id = encode_url_path_segment(
+            container_id, field_name="container_id"
+        )
+        url = join_container_api_base_path(api_base, f"/{encoded_container_id}/files")
 
         # Prepare query parameters
         params: Dict[str, Any] = {}
@@ -311,8 +321,12 @@ class OpenAIContainerConfig(BaseContainerConfig):
         - GET /v1/containers/{container_id}/files/{file_id}/content
         """
         # Construct the URL for container file content
+        encoded_container_id = encode_url_path_segment(
+            container_id, field_name="container_id"
+        )
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
         url = join_container_api_base_path(
-            api_base, f"/{container_id}/files/{file_id}/content"
+            api_base, f"/{encoded_container_id}/files/{encoded_file_id}/content"
         )
 
         # No query parameters needed

litellm/llms/openai/evals/transformation.py

@@ -7,6 +7,7 @@ from typing import Any, Dict, Optional, Tuple
 import httpx
 
 from litellm._logging import verbose_logger
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.evals.transformation import (
     BaseEvalsAPIConfig,
     LiteLLMLoggingObj,
@@ -76,7 +77,8 @@ class OpenAIEvalsConfig(BaseEvalsAPIConfig):
             api_base = "https://api.openai.com"
 
         if eval_id:
-            return f"{api_base}/v1/evals/{eval_id}"
+            encoded_eval_id = encode_url_path_segment(eval_id, field_name="eval_id")
+            return f"{api_base}/v1/evals/{encoded_eval_id}"
         return f"{api_base}/v1/{endpoint}"
 
     def transform_create_eval_request(
@@ -276,7 +278,8 @@ class OpenAIEvalsConfig(BaseEvalsAPIConfig):
         if litellm_params and litellm_params.api_base:
             api_base = litellm_params.api_base
 
-        url = f"{api_base}/v1/evals/{eval_id}/runs"
+        encoded_eval_id = encode_url_path_segment(eval_id, field_name="eval_id")
+        url = f"{api_base}/v1/evals/{encoded_eval_id}/runs"
 
         # Build request body
         request_body = {k: v for k, v in create_request.items() if v is not None}
@@ -310,7 +313,8 @@ class OpenAIEvalsConfig(BaseEvalsAPIConfig):
         if litellm_params and litellm_params.api_base:
             api_base = litellm_params.api_base
 
-        url = f"{api_base}/v1/evals/{eval_id}/runs"
+        encoded_eval_id = encode_url_path_segment(eval_id, field_name="eval_id")
+        url = f"{api_base}/v1/evals/{encoded_eval_id}/runs"
 
         # Build query parameters
         query_params: Dict[str, Any] = {}
@@ -350,7 +354,9 @@ class OpenAIEvalsConfig(BaseEvalsAPIConfig):
         headers: dict,
     ) -> Tuple[str, Dict]:
         """Transform get run request for OpenAI"""
-        url = f"{api_base}/v1/evals/{eval_id}/runs/{run_id}"
+        encoded_eval_id = encode_url_path_segment(eval_id, field_name="eval_id")
+        encoded_run_id = encode_url_path_segment(run_id, field_name="run_id")
+        url = f"{api_base}/v1/evals/{encoded_eval_id}/runs/{encoded_run_id}"
 
         verbose_logger.debug("Get run request - URL: %s", url)
 
@@ -376,7 +382,9 @@ class OpenAIEvalsConfig(BaseEvalsAPIConfig):
         headers: dict,
     ) -> Tuple[str, Dict, Dict]:
         """Transform cancel run request for OpenAI"""
-        url = f"{api_base}/v1/evals/{eval_id}/runs/{run_id}/cancel"
+        encoded_eval_id = encode_url_path_segment(eval_id, field_name="eval_id")
+        encoded_run_id = encode_url_path_segment(run_id, field_name="run_id")
+        url = f"{api_base}/v1/evals/{encoded_eval_id}/runs/{encoded_run_id}/cancel"
 
         # Empty body for cancel request
         request_body: Dict[str, Any] = {}
@@ -405,7 +413,9 @@ class OpenAIEvalsConfig(BaseEvalsAPIConfig):
         headers: dict,
     ) -> Tuple[str, Dict, Dict]:
         """Transform delete run request for OpenAI"""
-        url = f"{api_base}/v1/evals/{eval_id}/runs/{run_id}"
+        encoded_eval_id = encode_url_path_segment(eval_id, field_name="eval_id")
+        encoded_run_id = encode_url_path_segment(run_id, field_name="run_id")
+        url = f"{api_base}/v1/evals/{encoded_eval_id}/runs/{encoded_run_id}"
 
         # Empty body for delete request
         request_body: Dict[str, Any] = {}

litellm/llms/openai/responses/transformation.py

@@ -7,6 +7,7 @@ from pydantic import BaseModel, ValidationError
 import litellm
 from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.core_helpers import process_response_headers
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.litellm_core_utils.llm_response_utils.convert_dict_to_response import (
     _safe_convert_created_field,
 )
@@ -421,7 +422,10 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig):
         OpenAI API expects the following request
         - DELETE /v1/responses/{response_id}
         """
-        url = f"{api_base}/{response_id}"
+        encoded_response_id = encode_url_path_segment(
+            response_id, field_name="response_id"
+        )
+        url = f"{api_base}/{encoded_response_id}"
         data: Dict = {}
         return url, data
 
@@ -457,7 +461,10 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig):
         OpenAI API expects the following request
         - GET /v1/responses/{response_id}
         """
-        url = f"{api_base}/{response_id}"
+        encoded_response_id = encode_url_path_segment(
+            response_id, field_name="response_id"
+        )
+        url = f"{api_base}/{encoded_response_id}"
         data: Dict = {}
         return url, data
 
@@ -498,7 +505,10 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig):
         limit: int = 20,
         order: Literal["asc", "desc"] = "desc",
     ) -> Tuple[str, Dict]:
-        url = f"{api_base}/{response_id}/input_items"
+        encoded_response_id = encode_url_path_segment(
+            response_id, field_name="response_id"
+        )
+        url = f"{api_base}/{encoded_response_id}/input_items"
         params: Dict[str, Any] = {}
         if after is not None:
             params["after"] = after
@@ -540,7 +550,10 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig):
         OpenAI API expects the following request
         - POST /v1/responses/{response_id}/cancel
         """
-        url = f"{api_base}/{response_id}/cancel"
+        encoded_response_id = encode_url_path_segment(
+            response_id, field_name="response_id"
+        )
+        url = f"{api_base}/{encoded_response_id}/cancel"
         data: Dict = {}
         return url, data
 

litellm/llms/openai/vector_store_files/transformation.py

@@ -3,6 +3,7 @@ from typing import Any, Dict, Optional, Tuple, cast
 import httpx
 
 import litellm
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.vector_store_files.transformation import (
     BaseVectorStoreFilesConfig,
 )
@@ -98,7 +99,10 @@ class OpenAIVectorStoreFilesConfig(BaseVectorStoreFilesConfig):
             or "https://api.openai.com/v1"
         )
         base_url = base_url.rstrip("/")
-        return f"{base_url}/vector_stores/{vector_store_id}/files"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        return f"{base_url}/vector_stores/{encoded_vector_store_id}/files"
 
     def transform_create_vector_store_file_request(
         self,
@@ -163,7 +167,8 @@ class OpenAIVectorStoreFilesConfig(BaseVectorStoreFilesConfig):
         file_id: str,
         api_base: str,
     ) -> Tuple[str, Dict[str, Any]]:
-        return f"{api_base}/{file_id}", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base}/{encoded_file_id}", {}
 
     def transform_retrieve_vector_store_file_response(
         self,
@@ -186,7 +191,8 @@ class OpenAIVectorStoreFilesConfig(BaseVectorStoreFilesConfig):
         file_id: str,
         api_base: str,
     ) -> Tuple[str, Dict[str, Any]]:
-        return f"{api_base}/{file_id}/content", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base}/{encoded_file_id}/content", {}
 
     def transform_retrieve_vector_store_file_content_response(
         self,
@@ -218,7 +224,8 @@ class OpenAIVectorStoreFilesConfig(BaseVectorStoreFilesConfig):
                 payload["attributes"] = filtered_attributes
             else:
                 payload.pop("attributes", None)
-        return f"{api_base}/{file_id}", payload
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base}/{encoded_file_id}", payload
 
     def transform_update_vector_store_file_response(
         self,
@@ -241,7 +248,8 @@ class OpenAIVectorStoreFilesConfig(BaseVectorStoreFilesConfig):
         file_id: str,
         api_base: str,
     ) -> Tuple[str, Dict[str, Any]]:
-        return f"{api_base}/{file_id}", {}
+        encoded_file_id = encode_url_path_segment(file_id, field_name="file_id")
+        return f"{api_base}/{encoded_file_id}", {}
 
     def transform_delete_vector_store_file_response(
         self,

litellm/llms/openai/vector_stores/transformation.py

@@ -3,6 +3,7 @@ from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union, cast
 import httpx
 
 import litellm
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.vector_store.transformation import BaseVectorStoreConfig
 from litellm.secret_managers.main import get_secret_str
 from litellm.types.router import GenericLiteLLMParams
@@ -108,7 +109,10 @@ class OpenAIVectorStoreConfig(BaseVectorStoreConfig):
         litellm_params: dict,
         extra_body: Optional[Dict[str, Any]] = None,
     ) -> Tuple[str, Dict]:
-        url = f"{api_base}/{vector_store_id}/search"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}/search"
         typed_request_body = VectorStoreSearchRequest(
             query=query,
             filters=vector_store_search_optional_params.get("filters", None),

litellm/llms/openai/videos/transformation.py

@@ -1,11 +1,13 @@
 import mimetypes
 from io import BufferedReader, BytesIO
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union, cast
+from urllib.parse import quote
 
 import httpx
 from httpx._types import RequestFiles
 
 import litellm
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.videos.transformation import BaseVideoConfig
 from litellm.llms.openai.image_edit.transformation import ImageEditRequestUtils
 from litellm.secret_managers.main import get_secret_str
@@ -220,11 +222,18 @@ class OpenAIVideoConfig(BaseVideoConfig):
         - GET /v1/videos/{video_id}/content?variant=thumbnail
         """
         original_video_id = extract_original_video_id(video_id)
+        encoded_video_id = encode_url_path_segment(
+            original_video_id, field_name="video_id"
+        )
 
         # Construct the URL for video content download
-        url = f"{api_base.rstrip('/')}/{original_video_id}/content"
+        url = f"{api_base.rstrip('/')}/{encoded_video_id}/content"
         if variant is not None:
-            url = f"{url}?variant={variant}"
+            # Encode the user-controlled ``variant`` so a value like
+            # ``thumbnail&extra=1`` cannot inject additional query params
+            # into the upstream request — same hardening rationale as the
+            # path-segment encoding above.
+            url = f"{url}?variant={quote(variant, safe='')}"
 
         # No additional data needed for GET content request
         data: Dict[str, Any] = {}
@@ -247,9 +256,12 @@ class OpenAIVideoConfig(BaseVideoConfig):
         - POST /v1/videos/{video_id}/remix
         """
         original_video_id = extract_original_video_id(video_id)
+        encoded_video_id = encode_url_path_segment(
+            original_video_id, field_name="video_id"
+        )
 
         # Construct the URL for video remix
-        url = f"{api_base.rstrip('/')}/{original_video_id}/remix"
+        url = f"{api_base.rstrip('/')}/{encoded_video_id}/remix"
 
         # Prepare the request data
         data = {"prompt": prompt}
@@ -391,9 +403,12 @@ class OpenAIVideoConfig(BaseVideoConfig):
         - DELETE /v1/videos/{video_id}
         """
         original_video_id = extract_original_video_id(video_id)
+        encoded_video_id = encode_url_path_segment(
+            original_video_id, field_name="video_id"
+        )
 
         # Construct the URL for video delete
-        url = f"{api_base.rstrip('/')}/{original_video_id}"
+        url = f"{api_base.rstrip('/')}/{encoded_video_id}"
 
         # No data needed for DELETE request
         data: Dict[str, Any] = {}
@@ -427,9 +442,12 @@ class OpenAIVideoConfig(BaseVideoConfig):
         """
         # Extract the original video_id (remove provider encoding if present)
         original_video_id = extract_original_video_id(video_id)
+        encoded_video_id = encode_url_path_segment(
+            original_video_id, field_name="video_id"
+        )
 
         # For video retrieve, we just need to construct the URL
-        url = f"{api_base.rstrip('/')}/{original_video_id}"
+        url = f"{api_base.rstrip('/')}/{encoded_video_id}"
 
         # No additional data needed for GET request
         data: Dict[str, Any] = {}
@@ -494,7 +512,11 @@ class OpenAIVideoConfig(BaseVideoConfig):
         litellm_params: GenericLiteLLMParams,
         headers: dict,
     ) -> Tuple[str, Dict]:
-        url = f"{api_base.rstrip('/')}/characters/{character_id}"
+        original_character_id = extract_original_character_id(character_id)
+        encoded_character_id = encode_url_path_segment(
+            original_character_id, field_name="character_id"
+        )
+        url = f"{api_base.rstrip('/')}/characters/{encoded_character_id}"
         return url, {}
 
     def transform_video_get_character_response(

litellm/llms/openai_like/providers.json

@@ -106,5 +106,13 @@
     "base_url": "https://aihubmix.com/v1",
     "api_key_env": "AIHUBMIX_API_KEY",
     "api_base_env": "AIHUBMIX_API_BASE"
+  },
+  "crusoe": {
+    "base_url": "https://managed-inference-api-proxy.crusoecloud.com/v1",
+    "api_key_env": "CRUSOE_API_KEY",
+    "api_base_env": "CRUSOE_API_BASE",
+    "param_mappings": {
+      "max_completion_tokens": "max_tokens"
+    }
   }
 }

litellm/llms/pg_vector/vector_stores/transformation.py

@@ -1,5 +1,6 @@
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
 
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.openai.vector_stores.transformation import OpenAIVectorStoreConfig
 from litellm.secret_managers.main import get_secret_str
 from litellm.types.router import GenericLiteLLMParams
@@ -82,7 +83,10 @@ class PGVectorStoreConfig(OpenAIVectorStoreConfig):
         litellm_params: dict,
         extra_body: Optional[Dict[str, Any]] = None,
     ) -> Tuple[str, Dict]:
-        url = f"{api_base}/{vector_store_id}/search"
+        encoded_vector_store_id = encode_url_path_segment(
+            vector_store_id, field_name="vector_store_id"
+        )
+        url = f"{api_base}/{encoded_vector_store_id}/search"
         _, request_body = super().transform_search_vector_store_request(
             vector_store_id=vector_store_id,
             query=query,

litellm/llms/ragflow/chat/transformation.py

@@ -13,6 +13,7 @@ Model name format:
 from typing import List, Optional, Tuple
 
 import litellm
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.openai.openai import OpenAIConfig
 from litellm.secret_managers.main import get_secret, get_secret_str
 from litellm.types.llms.openai import AllMessageValues
@@ -126,10 +127,11 @@ class RAGFlowConfig(OpenAIConfig):
             api_base = api_base[:-3]  # Remove /v1
 
         # Construct the RAGFlow-specific path
+        encoded_entity_id = encode_url_path_segment(entity_id, field_name="entity_id")
         if endpoint_type == "chat":
-            path = f"/api/v1/chats_openai/{entity_id}/chat/completions"
+            path = f"/api/v1/chats_openai/{encoded_entity_id}/chat/completions"
         else:  # agent
-            path = f"/api/v1/agents_openai/{entity_id}/chat/completions"
+            path = f"/api/v1/agents_openai/{encoded_entity_id}/chat/completions"
 
         # Ensure path starts with /
         if not path.startswith("/"):

litellm/llms/runwayml/videos/transformation.py

@@ -6,6 +6,7 @@ from httpx._types import RequestFiles
 
 import litellm
 from litellm.constants import RUNWAYML_DEFAULT_API_VERSION
+from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.base_llm.videos.transformation import BaseVideoConfig
 from litellm.llms.custom_httpx.http_handler import (
@@ -334,9 +335,12 @@ class RunwayMLVideoConfig(BaseVideoConfig):
         We'll retrieve the task and extract the video URL.
         """
         original_video_id = extract_original_video_id(video_id)
+        encoded_video_id = encode_url_path_segment(
+            original_video_id, field_name="video_id"
+        )
 
         # Get task status to retrieve video URL
-        url = f"{api_base}/tasks/{original_video_id}"
+        url = f"{api_base}/tasks/{encoded_video_id}"
 
         params: Dict[str, Any] = {}
 
@@ -495,9 +499,12 @@ class RunwayMLVideoConfig(BaseVideoConfig):
         RunwayML uses task cancellation.
         """
         original_video_id = extract_original_video_id(video_id)
+        encoded_video_id = encode_url_path_segment(
+            original_video_id, field_name="video_id"
+        )
 
         # Construct the URL for task cancellation
-        url = f"{api_base}/tasks/{original_video_id}/cancel"
+        url = f"{api_base}/tasks/{encoded_video_id}/cancel"
 
         data: Dict[str, Any] = {}
 
@@ -533,9 +540,12 @@ class RunwayMLVideoConfig(BaseVideoConfig):
         RunwayML uses GET /v1/tasks/{task_id} to retrieve task status.
         """
         original_video_id = extract_original_video_id(video_id)
+        encoded_video_id = encode_url_path_segment(
+            original_video_id, field_name="video_id"
+        )
 
         # Construct the full URL for task status retrieval
-        url = f"{api_base}/tasks/{original_video_id}"
+        url = f"{api_base}/tasks/{encoded_video_id}"
 
         # Empty dict for GET request (no body)
         data: Dict[str, Any] = {}

litellm/llms/vertex_ai/batches/handler.py

@@ -4,7 +4,11 @@ from typing import Any, Coroutine, Dict, Optional, Union
 import httpx
 
 import litellm
-from litellm.litellm_core_utils.url_utils import async_safe_get, safe_get
+from litellm.litellm_core_utils.url_utils import (
+    async_safe_get,
+    encode_url_path_segment,
+    safe_get,
+)
 from litellm.llms.custom_httpx.http_handler import (
     _get_httpx_client,
     get_async_httpx_client,
@@ -170,7 +174,8 @@ class VertexAIBatchPrediction(VertexLLM):
         )
 
         # Append batch_id to the URL
-        default_api_base = f"{default_api_base}/{batch_id}"
+        encoded_batch_id = encode_url_path_segment(batch_id, field_name="batch_id")
+        default_api_base = f"{default_api_base}/{encoded_batch_id}"
 
         if len(default_api_base.split(":")) > 1:
             endpoint = default_api_base.split(":")[-1]
@@ -413,7 +418,8 @@ class VertexAIBatchPrediction(VertexLLM):
             vertex_project=vertex_project or project_id,
         )
 
-        retrieve_api_base_default = f"{default_api_base}/{batch_id}"
+        encoded_batch_id = encode_url_path_segment(batch_id, field_name="batch_id")
+        retrieve_api_base_default = f"{default_api_base}/{encoded_batch_id}"
         cancel_api_base_default = f"{retrieve_api_base_default}:cancel"
 
         _, api_base = self._check_custom_proxy(