ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into fix_vertex_expired_tokens

Browse Source
This commit is contained in:
Oz Ben-Ami 2025-08-08 02:19:17 -04:00
commit 58bbecffb7
85 changed files with 2473 additions and 973 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
docker/Dockerfile.non_root
View File

@ -11,7 +11,7 @@ WORKDIR /app
# Install build dependencies
USER root
RUN apk add --no-cache build-base bash \
&& pip install --no-cache-dir --upgrade pip build
&& pip install --no-cache-dir --upgrade pip build
# Copy project files
COPY . .
@ -21,8 +21,8 @@ RUN chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
# Build package and wheel dependencies
RUN rm -rf dist/* && python -m build && \
pip install dist/*.whl && \
pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
pip install dist/*.whl && \
pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
# -----------------
# Runtime Stage
@ -33,9 +33,10 @@ WORKDIR /app
# Install runtime dependencies
USER root
RUN apk upgrade --no-cache && \
apk add --no-cache bash libstdc++ ca-certificates openssl
apk add --no-cache bash libstdc++ ca-certificates openssl
# Copy only necessary artifacts from builder stage for runtime
COPY . .
COPY --from=builder /app/docker/entrypoint.sh /app/docker/prod_entrypoint.sh /app/docker/
COPY --from=builder /app/schema.prisma /app/schema.prisma
COPY --from=builder /app/dist/*.whl .
@ -43,16 +44,16 @@ COPY --from=builder /wheels/ /wheels/
# Install package from wheel and dependencies
RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ \
&& rm -f *.whl \
&& rm -rf /wheels
&& rm -f *.whl \
&& rm -rf /wheels
# Install semantic_router without dependencies
RUN pip install semantic_router --no-deps
# Ensure correct JWT library is used (pyjwt not jwt)
RUN pip uninstall jwt -y && \
pip uninstall PyJWT -y && \
pip install PyJWT==2.9.0 --no-cache-dir
pip uninstall PyJWT -y && \
pip install PyJWT==2.9.0 --no-cache-dir
# --- Prisma Handling for Non-Root User ---
# Set Prisma cache directories
@ -61,29 +62,29 @@ ENV NPM_CONFIG_CACHE=/.npm
# Install prisma and make entrypoints executable
RUN pip install --no-cache-dir prisma && \
chmod +x docker/entrypoint.sh && \
chmod +x docker/prod_entrypoint.sh
chmod +x docker/entrypoint.sh && \
chmod +x docker/prod_entrypoint.sh
# Create directories and set permissions for non-root user
RUN mkdir -p /nonexistent /.npm && \
chown -R nobody:nogroup /app && \
chown -R nobody:nogroup /nonexistent /.npm && \
PRISMA_PATH=$(python -c "import os, prisma; print(os.path.dirname(prisma.__file__))") && \
chown -R nobody:nogroup $PRISMA_PATH
chown -R nobody:nogroup /app && \
chown -R nobody:nogroup /nonexistent /.npm && \
PRISMA_PATH=$(python -c "import os, prisma; print(os.path.dirname(prisma.__file__))") && \
chown -R nobody:nogroup $PRISMA_PATH
# --- OpenShift Compatibility: Apply Red Hat recommended pattern ---
# Get paths for directories that need write access at runtime
RUN PRISMA_PATH=$(python -c "import os, prisma; print(os.path.dirname(prisma.__file__))") && \
LITELLM_PROXY_EXTRAS_PATH=$(python -c "import os, litellm_proxy_extras; print(os.path.dirname(litellm_proxy_extras.__file__))" 2>/dev/null || echo "") && \
# Set group ownership to 0 (root group) for OpenShift compatibility && \
chgrp -R 0 $PRISMA_PATH && \
[ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chgrp -R 0 $LITELLM_PROXY_EXTRAS_PATH || true && \
# Mirror owner permissions to group (g=u) as recommended by Red Hat && \
chmod -R g=u $PRISMA_PATH && \
[ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chmod -R g=u $LITELLM_PROXY_EXTRAS_PATH || true && \
# Ensure directories are writable by group && \
chmod -R g+w $PRISMA_PATH && \
[ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chmod -R g+w $LITELLM_PROXY_EXTRAS_PATH || true
LITELLM_PROXY_EXTRAS_PATH=$(python -c "import os, litellm_proxy_extras; print(os.path.dirname(litellm_proxy_extras.__file__))" 2>/dev/null || echo "") && \
# Set group ownership to 0 (root group) for OpenShift compatibility && \
chgrp -R 0 $PRISMA_PATH && \
[ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chgrp -R 0 $LITELLM_PROXY_EXTRAS_PATH || true && \
# Mirror owner permissions to group (g=u) as recommended by Red Hat && \
chmod -R g=u $PRISMA_PATH && \
[ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chmod -R g=u $LITELLM_PROXY_EXTRAS_PATH || true && \
# Ensure directories are writable by group && \
chmod -R g+w $PRISMA_PATH && \
[ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chmod -R g+w $LITELLM_PROXY_EXTRAS_PATH || true
# Switch to non-root user
USER nobody
@ -100,4 +101,4 @@ ENTRYPOINT ["/app/docker/prod_entrypoint.sh"]
# Append "--detailed_debug" to the end of CMD to view detailed debug logs
# CMD ["--port", "4000", "--detailed_debug"]
CMD ["--port", "4000"]
CMD ["--port", "4000"]

8
docs/my-website/docs/providers/openai.md
View File

@ -163,6 +163,14 @@ os.environ["OPENAI_BASE_URL"] = "https://your_host/v1" # OPTIONAL
| Model Name | Function Call |
|-----------------------|-----------------------------------------------------------------|
| gpt-5 | `response = completion(model="gpt-5", messages=messages)` |
| gpt-5-mini | `response = completion(model="gpt-5-mini", messages=messages)` |
| gpt-5-nano | `response = completion(model="gpt-5-nano", messages=messages)` |
| gpt-5-chat | `response = completion(model="gpt-5-chat", messages=messages)` |
| gpt-5-chat-latest | `response = completion(model="gpt-5-chat-latest", messages=messages)` |
| gpt-5-2025-08-07 | `response = completion(model="gpt-5-2025-08-07", messages=messages)` |
| gpt-5-mini-2025-08-07 | `response = completion(model="gpt-5-mini-2025-08-07", messages=messages)` |
| gpt-5-nano-2025-08-07 | `response = completion(model="gpt-5-nano-2025-08-07", messages=messages)` |
| gpt-4.1 | `response = completion(model="gpt-4.1", messages=messages)` |
| gpt-4.1-mini | `response = completion(model="gpt-4.1-mini", messages=messages)` |
| gpt-4.1-nano | `response = completion(model="gpt-4.1-nano", messages=messages)` |

52
docs/my-website/docs/proxy/guardrails/pii_masking_v2.md
View File

@ -12,7 +12,7 @@ import TabItem from '@theme/TabItem';
| Provider | [Microsoft Presidio](https://github.com/microsoft/presidio/) |
| Supported Entity Types | All Presidio Entity Types |
| Supported Actions | `MASK`, `BLOCK` |
| Supported Modes | `pre_call`, `during_call`, `post_call`, `logging_only` |
| Supported Modes | `pre_call`, `during_call`, `post_call`, `logging_only`, `pre_mcp_call` |
| Language Support | Configurable via `presidio_language` parameter (supports multiple languages including English, Spanish, German, etc.) |
## Deployment options
@ -239,7 +239,7 @@ guardrails:
- guardrail_name: "presidio-mask-guard"
litellm_params:
guardrail: presidio
mode: "pre_call"
mode: "pre_mcp_call" # Use this mode for MCP requests
pii_entities_config:
CREDIT_CARD: "MASK" # Will mask credit card numbers
EMAIL_ADDRESS: "MASK" # Will mask email addresses
@ -247,7 +247,7 @@ guardrails:
- guardrail_name: "presidio-block-guard"
litellm_params:
guardrail: presidio
mode: "pre_call"
mode: "pre_call" # Use this mode for regular LLM requests
pii_entities_config:
CREDIT_CARD: "BLOCK" # Will block requests containing credit card numbers
```
@ -338,6 +338,52 @@ The exception includes the entity type that was blocked (`CREDIT_CARD` in this c
## Advanced
### Supported Modes
The Presidio guardrail supports the following modes:
- `pre_call`: Run **before** LLM call, on **input**
- `post_call`: Run **after** LLM call, on **input & output**
- `logging_only`: Run **after** LLM call, only apply PII Masking before logging to Langfuse, etc. Not on the actual llm api request / response
- `pre_mcp_call`: Run **before** MCP call, on **input**. Use this mode when you want to apply PII masking/blocking for MCP requests
### MCP Usage Example
Here's how to use Presidio guardrails with MCP:
```yaml title="MCP Configuration Example" showLineNumbers
guardrails:
- guardrail_name: "presidio-mcp-guard"
litellm_params:
guardrail: presidio
mode: "pre_mcp_call"
pii_entities_config:
CREDIT_CARD: "MASK" # Will mask credit card numbers
EMAIL_ADDRESS: "BLOCK" # Will block email addresses
PHONE_NUMBER: "MASK" # Will mask phone numbers
MEDICAL_LICENSE: "BLOCK" # Will block medical license numbers
default_on: true
```
Test the MCP guardrail with a request:
```shell title="Test MCP Guardrail" showLineNumbers
curl http://localhost:4000/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-3.5-turbo",
"messages": [
{"role": "user", "content": "My credit card is 4111-1111-1111-1111 and my medical license is ABC123"}
],
"guardrails": ["presidio-mcp-guard"]
}'
```
The request will be processed as follows:
1. Credit card number will be masked (e.g., replaced with `<CREDIT_CARD>`)
2. If a medical license is detected, the request will be blocked with a `BlockedPiiEntityError`
### Set `language` per request
The Presidio API [supports passing the `language` param](https://microsoft.github.io/presidio/api-docs/api-docs.html#tag/Analyzer/paths/~1analyze/post). Here is how to set the `language` per request

BIN
litellm-proxy-extras/dist/litellm_proxy_extras-0.2.16-py3-none-any.whl vendored Normal file
View File

Binary file not shown.

BIN
litellm-proxy-extras/dist/litellm_proxy_extras-0.2.16.tar.gz vendored Normal file
View File

Binary file not shown.

4
litellm-proxy-extras/pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry]
name = "litellm-proxy-extras"
version = "0.2.15"
version = "0.2.16"
description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
authors = ["BerriAI"]
readme = "README.md"
@ -22,7 +22,7 @@ requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"
[tool.commitizen]
version = "0.2.15"
version = "0.2.16"
version_files = [
"pyproject.toml:version",
"../requirements.txt:litellm-proxy-extras==",

11
litellm/__init__.py
View File

@ -357,7 +357,7 @@ disable_copilot_system_to_assistant: bool = (
)
public_model_groups: Optional[List[str]] = None
public_model_groups_links: Dict[str, str] = {}
#### REQUEST PRIORITIZATION #####
#### REQUEST PRIORITIZATION ######
priority_reservation: Optional[Dict[str, float]] = None
@ -533,6 +533,7 @@ morph_models: List = []
lambda_ai_models: List = []
hyperbolic_models: List = []
recraft_models: List = []
oci_models: List = []
def is_bedrock_pricing_only_model(key: str) -> bool:
@ -722,6 +723,8 @@ def add_known_models():
hyperbolic_models.append(key)
elif value.get("litellm_provider") == "recraft":
recraft_models.append(key)
elif value.get("litellm_provider") == "oci":
oci_models.append(key)
add_known_models()
@ -810,6 +813,7 @@ model_list = (
+ morph_models
+ lambda_ai_models
+ recraft_models
+ oci_models
)
model_list_set = set(model_list)
@ -883,6 +887,7 @@ models_by_provider: dict = {
"lambda_ai": lambda_ai_models,
"hyperbolic": hyperbolic_models,
"recraft": recraft_models,
"oci": oci_models,
}
# mapping for those models which have larger equivalents
@ -1140,6 +1145,9 @@ openaiOSeriesConfig = OpenAIOSeriesConfig()
from .llms.openai.chat.gpt_transformation import (
OpenAIGPTConfig,
)
from .llms.openai.chat.gpt_5_transformation import (
OpenAIGPT5Config,
)
from .llms.openai.transcriptions.whisper_transformation import (
OpenAIWhisperAudioTranscriptionConfig,
)
@ -1153,6 +1161,7 @@ from .llms.openai.chat.gpt_audio_transformation import (
)
openAIGPTAudioConfig = OpenAIGPTAudioConfig()
openAIGPT5Config = OpenAIGPT5Config()
from .llms.nvidia_nim.chat.transformation import NvidiaNimConfig
from .llms.nvidia_nim.embed import NvidiaNimEmbeddingConfig

42
litellm/llms/mistral/chat/transformation.py
View File

@ -9,6 +9,7 @@ Docs - https://docs.mistral.ai/api/
from typing import Any, Coroutine, List, Literal, Optional, Tuple, Union, cast, overload
import httpx
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.litellm_core_utils.prompt_templates.common_utils import (
handle_messages_with_content_list_to_str_conversion,
@ -147,7 +148,8 @@ class MistralConfig(OpenAIGPTConfig):
if param == "max_completion_tokens": # max_completion_tokens should take priority
optional_params["max_tokens"] = value
if param == "tools":
optional_params["tools"] = value
# Clean tools to remove problematic schema fields for Mistral API
optional_params["tools"] = self._clean_tool_schema_for_mistral(value)
if param == "stream" and value is True:
optional_params["stream"] = value
if param == "temperature":
@ -195,7 +197,8 @@ class MistralConfig(OpenAIGPTConfig):
@overload
def _transform_messages(
self, messages: List[AllMessageValues], model: str, is_async: Literal[True]
) -> Coroutine[Any, Any, List[AllMessageValues]]: ...
) -> Coroutine[Any, Any, List[AllMessageValues]]:
...
@overload
def _transform_messages(
@ -203,7 +206,8 @@ class MistralConfig(OpenAIGPTConfig):
messages: List[AllMessageValues],
model: str,
is_async: Literal[False] = False,
) -> List[AllMessageValues]: ...
) -> List[AllMessageValues]:
...
def _transform_messages(
self, messages: List[AllMessageValues], model: str, is_async: bool = False
@ -286,6 +290,38 @@ class MistralConfig(OpenAIGPTConfig):
optional_params.pop("_add_reasoning_prompt", None)
return messages
@classmethod
def _clean_tool_schema_for_mistral(cls, tools: list) -> list:
"""
Clean tool schemas to remove fields that cause issues with Mistral API.
Removes:
- $id and $schema fields (cause grammar validation errors)
- additionalProperties=False (causes OpenAI API schema errors)
- strict field (not supported by Mistral)
Args:
tools: List of tool definitions
max_depth: Maximum recursion depth for schema cleaning (default: 10)
Returns:
Cleaned tools list
"""
if not tools:
return tools
import copy
from litellm.constants import DEFAULT_MAX_RECURSE_DEPTH
from litellm.utils import _remove_json_schema_refs
cleaned_tools = copy.deepcopy(tools)
# Apply all cleaning functions with max_depth protection
cleaned_tools = _remove_json_schema_refs(cleaned_tools, max_depth=DEFAULT_MAX_RECURSE_DEPTH)
return cleaned_tools
@classmethod
def _handle_name_in_message(cls, message: AllMessageValues) -> AllMessageValues:
"""

58
litellm/llms/openai/chat/gpt_5_transformation.py Normal file
View File

@ -0,0 +1,58 @@
"""Support for OpenAI gpt-5 model family."""
from typing import Optional
import litellm
from .gpt_transformation import OpenAIGPTConfig
class OpenAIGPT5Config(OpenAIGPTConfig):
"""Configuration for gpt-5 models.
Handles OpenAI API quirks for the gpt-5 series like:
- Mapping ``max_tokens`` -> ``max_completion_tokens``.
- Dropping unsupported ``temperature`` values when requested.
"""
@classmethod
def is_model_gpt_5_model(cls, model: str) -> bool:
return "gpt-5" in model
def map_openai_params(
self,
non_default_params: dict,
optional_params: dict,
model: str,
drop_params: bool,
) -> dict:
################################################################
# max_tokens is not supported for gpt-5 models on OpenAI API
# Relevant issue: https://github.com/BerriAI/litellm/issues/13381
################################################################
if "max_tokens" in non_default_params:
optional_params["max_completion_tokens"] = non_default_params.pop(
"max_tokens"
)
if "temperature" in non_default_params:
temperature_value: Optional[float] = non_default_params.pop("temperature")
if temperature_value is not None:
if temperature_value == 1:
optional_params["temperature"] = temperature_value
elif litellm.drop_params or drop_params:
pass
else:
raise litellm.utils.UnsupportedParamsError(
message=(
"gpt-5 models don't support temperature={}. Only temperature=1 is supported. To drop unsupported params set `litellm.drop_params = True`"
).format(temperature_value),
status_code=400,
)
return super()._map_openai_params(
non_default_params=non_default_params,
optional_params=optional_params,
model=model,
drop_params=drop_params,
)

11
litellm/llms/openai/openai.py
View File

@ -47,6 +47,7 @@ from litellm.utils import (
from ...types.llms.openai import *
from ..base import BaseLLM
from .chat.gpt_5_transformation import OpenAIGPT5Config
from .chat.o_series_transformation import OpenAIOSeriesConfig
from .common_utils import (
BaseOpenAILLM,
@ -55,6 +56,7 @@ from .common_utils import (
)
openaiOSeriesConfig = OpenAIOSeriesConfig()
openAIGPT5Config = OpenAIGPT5Config()
class MistralEmbeddingConfig:
@ -183,6 +185,8 @@ class OpenAIConfig(BaseConfig):
"""
if openaiOSeriesConfig.is_model_o_series_model(model=model):
return openaiOSeriesConfig.get_supported_openai_params(model=model)
elif openAIGPT5Config.is_model_gpt_5_model(model=model):
return openAIGPT5Config.get_supported_openai_params(model=model)
elif litellm.openAIGPTAudioConfig.is_model_gpt_audio_model(model=model):
return litellm.openAIGPTAudioConfig.get_supported_openai_params(model=model)
else:
@ -217,6 +221,13 @@ class OpenAIConfig(BaseConfig):
model=model,
drop_params=drop_params,
)
elif openAIGPT5Config.is_model_gpt_5_model(model=model):
return openAIGPT5Config.map_openai_params(
non_default_params=non_default_params,
optional_params=optional_params,
model=model,
drop_params=drop_params,
)
elif litellm.openAIGPTAudioConfig.is_model_gpt_audio_model(model=model):
return litellm.openAIGPTAudioConfig.map_openai_params(
non_default_params=non_default_params,

661
litellm/model_prices_and_context_window_backup.json
View File

@ -612,6 +612,263 @@
"search_context_size_high": 0.03
}
},
"gpt-5": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-mini": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-nano": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-chat": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2e-05,
"input_cost_per_token_batches": 2.5e-06,
"output_cost_per_token_batches": 1e-05,
"cache_read_input_token_cost": 1.25e-06,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true
},
"gpt-5-chat-latest": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"codex-mini-latest": {
"max_tokens": 100000,
"max_input_tokens": 200000,
@ -2007,6 +2264,263 @@
"/v1/audio/speech"
]
},
"azure/gpt-5": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-mini": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-nano": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-chat": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2e-05,
"input_cost_per_token_batches": 2.5e-06,
"output_cost_per_token_batches": 1e-05,
"cache_read_input_token_cost": 1.25e-06,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true
},
"azure/gpt-5-chat-latest": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-4o-mini-tts": {
"mode": "audio_speech",
"input_cost_per_token": 2.5e-06,
@ -5771,6 +6285,32 @@
"supports_reasoning": true,
"supports_computer_use": true
},
"claude-opus-4-1": {
"max_tokens": 32000,
"max_input_tokens": 200000,
"max_output_tokens": 32000,
"input_cost_per_token": 1.5e-05,
"output_cost_per_token": 7.5e-05,
"search_context_cost_per_query": {
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01,
"search_context_size_high": 0.01
},
"cache_creation_input_token_cost": 1.875e-05,
"cache_read_input_token_cost": 1.5e-06,
"litellm_provider": "anthropic",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 159,
"supports_assistant_prefill": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_computer_use": true
},
"claude-opus-4-1-20250805": {
"max_tokens": 32000,
"max_input_tokens": 200000,
@ -17693,5 +18233,126 @@
"supports_vision": false,
"supports_system_messages": true,
"supports_tool_choice": false
},
"oci/meta.llama-4-maverick-17b-128e-instruct-fp8": {
"max_tokens": 512000,
"max_input_tokens": 512000,
"max_output_tokens": 4000,
"input_cost_per_token": 7.2e-07,
"output_cost_per_token": 7.2e-07,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/meta.llama-4-scout-17b-16e-instruct": {
"max_tokens": 192000,
"max_input_tokens": 192000,
"max_output_tokens": 4000,
"input_cost_per_token": 7.2e-07,
"output_cost_per_token": 7.2e-07,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/meta.llama-3.3-70b-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4000,
"input_cost_per_token": 7.2e-07,
"output_cost_per_token": 7.2e-07,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/meta.llama-3.2-90b-vision-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4000,
"input_cost_per_token": 2.0e-06,
"output_cost_per_token": 2.0e-06,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/meta.llama-3.1-405b-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4000,
"input_cost_per_token": 1.068e-05,
"output_cost_per_token": 1.068e-05,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-4": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 3.0e-06,
"output_cost_per_token": 1.5e-07,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-3": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 3.0e-06,
"output_cost_per_token": 1.5e-07,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-3-mini": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 3.0e-07,
"output_cost_per_token": 5.0e-07,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-3-fast": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 5.0e-06,
"output_cost_per_token": 2.5e-05,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-3-mini-fast": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 6.0e-07,
"output_cost_per_token": 4.0e-06,
"litellm_provider": "oci",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
}
}

1
litellm/proxy/_experimental/out/_next/static/chunks/154-66d79df6143c694f.js Normal file
View File

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/154-78c3416dcb61977f.js
View File

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/162-8529572226f208c5.js
View File

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/162-9e6f5133e328d61f.js Normal file
View File

File diff suppressed because one or more lines are too long

0
litellm/proxy/_experimental/out/_next/static/chunks/172-08ae62d50ce1f0e7.js → litellm/proxy/_experimental/out/_next/static/chunks/172-1c7afccd96ceca39.js
View File

12
litellm/proxy/_experimental/out/_next/static/chunks/498-ee02f9b58491d7a9.js
View File

File diff suppressed because one or more lines are too long

12
litellm/proxy/_experimental/out/_next/static/chunks/683-07087d813e7eeb43.js Normal file
View File

File diff suppressed because one or more lines are too long

2
ui/litellm-dashboard/out/_next/static/chunks/866-9e1803a09e9ae8da.js → litellm/proxy/_experimental/out/_next/static/chunks/866-3523e0e07cf314f6.js
View File

File diff suppressed because one or more lines are too long

0
litellm/proxy/_experimental/out/_next/static/chunks/app/onboarding/page-883c32e6b072b842.js → litellm/proxy/_experimental/out/_next/static/chunks/app/onboarding/page-7e4cd2bb92dbf9ce.js
View File

1
litellm/proxy/_experimental/out/_next/static/chunks/app/page-0a9a9f137522a76c.js
View File

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/app/page-1d51309983956823.js Normal file
View File

File diff suppressed because one or more lines are too long

3
litellm/proxy/_experimental/out/_next/static/css/0dbff0867726409d.css Normal file
View File

File diff suppressed because one or more lines are too long

3
litellm/proxy/_experimental/out/_next/static/css/fe37e928fd602d9e.css
View File

File diff suppressed because one or more lines are too long

0
litellm/proxy/_experimental/out/_next/static/rkJYRcYqQ8OBbL83KQCc4/_buildManifest.js → litellm/proxy/_experimental/out/_next/static/poVnZDt3J0aYERGVwpJKO/_buildManifest.js
View File

0
litellm/proxy/_experimental/out/_next/static/rkJYRcYqQ8OBbL83KQCc4/_ssgManifest.js → litellm/proxy/_experimental/out/_next/static/poVnZDt3J0aYERGVwpJKO/_ssgManifest.js
View File

2
litellm/proxy/_experimental/out/index.html
View File

File diff suppressed because one or more lines are too long

4
litellm/proxy/_experimental/out/index.txt
View File

@ -1,7 +1,7 @@
2:I[19107,[],"ClientPageRoot"]
3:I[19813,["665","static/chunks/3014691f-b7b79b78e27792f3.js","990","static/chunks/13b76428-ebdf3012af0e4489.js","416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","866","static/chunks/866-9e1803a09e9ae8da.js","498","static/chunks/498-ee02f9b58491d7a9.js","154","static/chunks/154-78c3416dcb61977f.js","162","static/chunks/162-8529572226f208c5.js","172","static/chunks/172-08ae62d50ce1f0e7.js","931","static/chunks/app/page-0a9a9f137522a76c.js"],"default",1]
3:I[6691,["665","static/chunks/3014691f-b7b79b78e27792f3.js","990","static/chunks/13b76428-ebdf3012af0e4489.js","416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","866","static/chunks/866-3523e0e07cf314f6.js","683","static/chunks/683-07087d813e7eeb43.js","154","static/chunks/154-66d79df6143c694f.js","162","static/chunks/162-9e6f5133e328d61f.js","172","static/chunks/172-1c7afccd96ceca39.js","931","static/chunks/app/page-1d51309983956823.js"],"default",1]
4:I[4707,[],""]
5:I[36423,[],""]
0:["rkJYRcYqQ8OBbL83KQCc4",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/fe37e928fd602d9e.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
0:["poVnZDt3J0aYERGVwpJKO",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/0dbff0867726409d.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
1:null

4
litellm/proxy/_experimental/out/model_hub.txt
View File

@ -1,7 +1,7 @@
2:I[19107,[],"ClientPageRoot"]
3:I[52829,["416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","154","static/chunks/154-78c3416dcb61977f.js","162","static/chunks/162-8529572226f208c5.js","418","static/chunks/app/model_hub/page-b26e0d313b582dbf.js"],"default",1]
3:I[52829,["416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","154","static/chunks/154-66d79df6143c694f.js","162","static/chunks/162-9e6f5133e328d61f.js","418","static/chunks/app/model_hub/page-b26e0d313b582dbf.js"],"default",1]
4:I[4707,[],""]
5:I[36423,[],""]
0:["rkJYRcYqQ8OBbL83KQCc4",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/fe37e928fd602d9e.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
0:["poVnZDt3J0aYERGVwpJKO",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/0dbff0867726409d.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
1:null

4
litellm/proxy/_experimental/out/model_hub_table.txt
View File

@ -1,7 +1,7 @@
2:I[19107,[],"ClientPageRoot"]
3:I[22775,["416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","866","static/chunks/866-9e1803a09e9ae8da.js","154","static/chunks/154-78c3416dcb61977f.js","162","static/chunks/162-8529572226f208c5.js","172","static/chunks/172-08ae62d50ce1f0e7.js","25","static/chunks/app/model_hub_table/page-d080c5775ebaf3a1.js"],"default",1]
3:I[22775,["416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","866","static/chunks/866-3523e0e07cf314f6.js","154","static/chunks/154-66d79df6143c694f.js","162","static/chunks/162-9e6f5133e328d61f.js","172","static/chunks/172-1c7afccd96ceca39.js","25","static/chunks/app/model_hub_table/page-d080c5775ebaf3a1.js"],"default",1]
4:I[4707,[],""]
5:I[36423,[],""]
0:["rkJYRcYqQ8OBbL83KQCc4",[[["",{"children":["model_hub_table",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub_table",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub_table","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/fe37e928fd602d9e.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
0:["poVnZDt3J0aYERGVwpJKO",[[["",{"children":["model_hub_table",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub_table",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub_table","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/0dbff0867726409d.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
1:null

1
litellm/proxy/_experimental/out/model_hub_table/index.html
View File

File diff suppressed because one or more lines are too long

4
litellm/proxy/_experimental/out/onboarding.txt
View File

@ -1,7 +1,7 @@
2:I[19107,[],"ClientPageRoot"]
3:I[12011,["665","static/chunks/3014691f-b7b79b78e27792f3.js","416","static/chunks/416-ad6bd55a20a586bd.js","154","static/chunks/154-78c3416dcb61977f.js","461","static/chunks/app/onboarding/page-883c32e6b072b842.js"],"default",1]
3:I[12011,["665","static/chunks/3014691f-b7b79b78e27792f3.js","416","static/chunks/416-ad6bd55a20a586bd.js","154","static/chunks/154-66d79df6143c694f.js","461","static/chunks/app/onboarding/page-7e4cd2bb92dbf9ce.js"],"default",1]
4:I[4707,[],""]
5:I[36423,[],""]
0:["rkJYRcYqQ8OBbL83KQCc4",[[["",{"children":["onboarding",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["onboarding",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","onboarding","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/fe37e928fd602d9e.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
0:["poVnZDt3J0aYERGVwpJKO",[[["",{"children":["onboarding",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["onboarding",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","onboarding","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/0dbff0867726409d.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
1:null

306
litellm/proxy/management_endpoints/common_daily_activity.py
View File

@ -267,6 +267,106 @@ async def get_api_key_metadata(
}
def _build_where_conditions(
*,
entity_id_field: str,
entity_id: Optional[Union[str, List[str]]],
start_date: str,
end_date: str,
model: Optional[str],
api_key: Optional[str],
exclude_entity_ids: Optional[List[str]] = None,
) -> Dict[str, Any]:
"""Build prisma where clause for daily activity queries."""
where_conditions: Dict[str, Any] = {
"date": {
"gte": start_date,
"lte": end_date,
}
}
if model:
where_conditions["model"] = model
if api_key:
where_conditions["api_key"] = api_key
if entity_id is not None:
if isinstance(entity_id, list):
where_conditions[entity_id_field] = {"in": entity_id}
else:
where_conditions[entity_id_field] = {"equals": entity_id}
if exclude_entity_ids:
current = where_conditions.get(entity_id_field, {})
if isinstance(current, str):
current = {"equals": current}
current["not"] = {"in": exclude_entity_ids}
where_conditions[entity_id_field] = current
return where_conditions
async def _aggregate_spend_records(
*,
prisma_client: PrismaClient,
records: List[Any],
entity_id_field: Optional[str],
entity_metadata_field: Optional[Dict[str, dict]],
) -> Dict[str, Any]:
"""Aggregate rows into DailySpendData list and total metrics."""
api_keys: Set[str] = set()
for record in records:
if record.api_key:
api_keys.add(record.api_key)
api_key_metadata: Dict[str, Dict[str, Any]] = {}
model_metadata: Dict[str, Dict[str, Any]] = {}
provider_metadata: Dict[str, Dict[str, Any]] = {}
if api_keys:
api_key_metadata = await get_api_key_metadata(prisma_client, api_keys)
results: List[DailySpendData] = []
total_metrics = SpendMetrics()
grouped_data: Dict[str, Dict[str, Any]] = {}
for record in records:
date_str = record.date
if date_str not in grouped_data:
grouped_data[date_str] = {
"metrics": SpendMetrics(),
"breakdown": BreakdownMetrics(),
}
grouped_data[date_str]["metrics"] = update_metrics(
grouped_data[date_str]["metrics"], record
)
grouped_data[date_str]["breakdown"] = update_breakdown_metrics(
grouped_data[date_str]["breakdown"],
record,
model_metadata,
provider_metadata,
api_key_metadata,
entity_id_field=entity_id_field,
entity_metadata_field=entity_metadata_field,
)
total_metrics = update_metrics(total_metrics, record)
for date_str, data in grouped_data.items():
results.append(
DailySpendData(
date=datetime.strptime(date_str, "%Y-%m-%d").date(),
metrics=data["metrics"],
breakdown=data["breakdown"],
)
)
results.sort(key=lambda x: x.date, reverse=True)
return {"results": results, "totals": total_metrics}
async def get_daily_activity(
prisma_client: Optional[PrismaClient],
table_name: str,
@ -296,27 +396,15 @@ async def get_daily_activity(
)
try:
# Build filter conditions
where_conditions: Dict[str, Any] = {
"date": {
"gte": start_date,
"lte": end_date,
}
}
if model:
where_conditions["model"] = model
if api_key:
where_conditions["api_key"] = api_key
if entity_id is not None:
if isinstance(entity_id, list):
where_conditions[entity_id_field] = {"in": entity_id}
else:
where_conditions[entity_id_field] = entity_id
if exclude_entity_ids:
where_conditions.setdefault(entity_id_field, {})["not"] = {
"in": exclude_entity_ids
}
where_conditions = _build_where_conditions(
entity_id_field=entity_id_field,
entity_id=entity_id,
start_date=start_date,
end_date=end_date,
model=model,
api_key=api_key,
exclude_entity_ids=exclude_entity_ids,
)
# Get total count for pagination
total_count = await getattr(prisma_client.db, table_name).count(
@ -333,87 +421,25 @@ async def get_daily_activity(
take=page_size,
)
# Get all unique API keys from the spend data
api_keys = set()
for record in daily_spend_data:
if record.api_key:
api_keys.add(record.api_key)
# Fetch key aliases in bulk
api_key_metadata: Dict[str, Dict[str, Any]] = {}
model_metadata: Dict[str, Dict[str, Any]] = {}
provider_metadata: Dict[str, Dict[str, Any]] = {}
if api_keys:
api_key_metadata = await get_api_key_metadata(prisma_client, api_keys)
# Process results
results = []
total_metrics = SpendMetrics()
grouped_data: Dict[str, Dict[str, Any]] = {}
for record in daily_spend_data:
date_str = record.date
if date_str not in grouped_data:
grouped_data[date_str] = {
"metrics": SpendMetrics(),
"breakdown": BreakdownMetrics(),
}
# Update metrics
grouped_data[date_str]["metrics"] = update_metrics(
grouped_data[date_str]["metrics"], record
)
# Update breakdowns
grouped_data[date_str]["breakdown"] = update_breakdown_metrics(
grouped_data[date_str]["breakdown"],
record,
model_metadata,
provider_metadata,
api_key_metadata,
entity_id_field=entity_id_field,
entity_metadata_field=entity_metadata_field,
)
# Update total metrics
total_metrics.spend += record.spend
total_metrics.prompt_tokens += record.prompt_tokens
total_metrics.completion_tokens += record.completion_tokens
total_metrics.total_tokens += (
record.prompt_tokens + record.completion_tokens
)
total_metrics.cache_read_input_tokens += record.cache_read_input_tokens
total_metrics.cache_creation_input_tokens += (
record.cache_creation_input_tokens
)
total_metrics.api_requests += record.api_requests
total_metrics.successful_requests += record.successful_requests
total_metrics.failed_requests += record.failed_requests
# Convert grouped data to response format
for date_str, data in grouped_data.items():
results.append(
DailySpendData(
date=datetime.strptime(date_str, "%Y-%m-%d").date(),
metrics=data["metrics"],
breakdown=data["breakdown"],
)
)
# Sort results by date
results.sort(key=lambda x: x.date, reverse=True)
aggregated = await _aggregate_spend_records(
prisma_client=prisma_client,
records=daily_spend_data,
entity_id_field=entity_id_field,
entity_metadata_field=entity_metadata_field,
)
return SpendAnalyticsPaginatedResponse(
results=results,
results=aggregated["results"],
metadata=DailySpendMetadata(
total_spend=total_metrics.spend,
total_prompt_tokens=total_metrics.prompt_tokens,
total_completion_tokens=total_metrics.completion_tokens,
total_tokens=total_metrics.total_tokens,
total_api_requests=total_metrics.api_requests,
total_successful_requests=total_metrics.successful_requests,
total_failed_requests=total_metrics.failed_requests,
total_cache_read_input_tokens=total_metrics.cache_read_input_tokens,
total_cache_creation_input_tokens=total_metrics.cache_creation_input_tokens,
total_spend=aggregated["totals"].spend,
total_prompt_tokens=aggregated["totals"].prompt_tokens,
total_completion_tokens=aggregated["totals"].completion_tokens,
total_tokens=aggregated["totals"].total_tokens,
total_api_requests=aggregated["totals"].api_requests,
total_successful_requests=aggregated["totals"].successful_requests,
total_failed_requests=aggregated["totals"].failed_requests,
total_cache_read_input_tokens=aggregated["totals"].cache_read_input_tokens,
total_cache_creation_input_tokens=aggregated["totals"].cache_creation_input_tokens,
page=page,
total_pages=-(-total_count // page_size), # Ceiling division
has_more=(page * page_size) < total_count,
@ -426,3 +452,85 @@ async def get_daily_activity(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail={"error": f"Failed to fetch analytics: {str(e)}"},
)
async def get_daily_activity_aggregated(
prisma_client: Optional[PrismaClient],
table_name: str,
entity_id_field: str,
entity_id: Optional[Union[str, List[str]]],
entity_metadata_field: Optional[Dict[str, dict]],
start_date: Optional[str],
end_date: Optional[str],
model: Optional[str],
api_key: Optional[str],
exclude_entity_ids: Optional[List[str]] = None,
) -> SpendAnalyticsPaginatedResponse:
"""Aggregated variant that returns the full result set (no pagination).
Matches the response model of the paginated endpoint so the UI does not need to transform.
"""
if prisma_client is None:
raise HTTPException(
status_code=500,
detail={"error": CommonProxyErrors.db_not_connected_error.value},
)
if start_date is None or end_date is None:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail={"error": "Please provide start_date and end_date"},
)
try:
where_conditions = _build_where_conditions(
entity_id_field=entity_id_field,
entity_id=entity_id,
start_date=start_date,
end_date=end_date,
model=model,
api_key=api_key,
exclude_entity_ids=exclude_entity_ids,
)
# Fetch all matching results (no pagination)
daily_spend_data = await getattr(prisma_client.db, table_name).find_many(
where=where_conditions,
order=[
{"date": "desc"},
],
)
aggregated = await _aggregate_spend_records(
prisma_client=prisma_client,
records=daily_spend_data,
entity_id_field=entity_id_field,
entity_metadata_field=entity_metadata_field,
)
return SpendAnalyticsPaginatedResponse(
results=aggregated["results"],
metadata=DailySpendMetadata(
total_spend=aggregated["totals"].spend,
total_prompt_tokens=aggregated["totals"].prompt_tokens,
total_completion_tokens=aggregated["totals"].completion_tokens,
total_tokens=aggregated["totals"].total_tokens,
total_api_requests=aggregated["totals"].api_requests,
total_successful_requests=aggregated["totals"].successful_requests,
total_failed_requests=aggregated["totals"].failed_requests,
total_cache_read_input_tokens=aggregated["totals"].cache_read_input_tokens,
total_cache_creation_input_tokens=aggregated["totals"].cache_creation_input_tokens,
page=1,
total_pages=1,
has_more=False,
),
)
except Exception as e:
verbose_proxy_logger.exception(
f"Error fetching aggregated daily activity: {str(e)}"
)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail={"error": f"Failed to fetch analytics: {str(e)}"},
)

149
litellm/proxy/management_endpoints/internal_user_endpoints.py
View File

@ -26,7 +26,10 @@ from litellm._logging import verbose_proxy_logger
from litellm.proxy._types import *
from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
from litellm.proxy.hooks.user_management_event_hooks import UserManagementEventHooks
from litellm.proxy.management_endpoints.common_daily_activity import get_daily_activity
from litellm.proxy.management_endpoints.common_daily_activity import (
get_daily_activity,
get_daily_activity_aggregated,
)
from litellm.proxy.management_endpoints.common_utils import _user_has_admin_view
from litellm.proxy.management_endpoints.key_management_endpoints import (
generate_key_helper_fn,
@ -35,13 +38,7 @@ from litellm.proxy.management_endpoints.key_management_endpoints import (
from litellm.proxy.management_helpers.utils import management_endpoint_wrapper
from litellm.proxy.utils import handle_exception_on_proxy
from litellm.types.proxy.management_endpoints.common_daily_activity import (
BreakdownMetrics,
KeyMetadata,
KeyMetricWithMetadata,
LiteLLM_DailyUserSpend,
MetricWithMetadata,
SpendAnalyticsPaginatedResponse,
SpendMetrics,
)
from litellm.types.proxy.management_endpoints.internal_user_endpoints import (
BulkUpdateUserRequest,
@ -1784,71 +1781,7 @@ async def ui_view_users(
raise HTTPException(status_code=500, detail=f"Error searching users: {str(e)}")
def update_metrics(
group_metrics: SpendMetrics, record: LiteLLM_DailyUserSpend
) -> SpendMetrics:
group_metrics.spend += record.spend
group_metrics.prompt_tokens += record.prompt_tokens
group_metrics.completion_tokens += record.completion_tokens
group_metrics.cache_read_input_tokens += record.cache_read_input_tokens
group_metrics.cache_creation_input_tokens += record.cache_creation_input_tokens
group_metrics.total_tokens += record.prompt_tokens + record.completion_tokens
group_metrics.api_requests += record.api_requests
group_metrics.successful_requests += record.successful_requests
group_metrics.failed_requests += record.failed_requests
return group_metrics
def update_breakdown_metrics(
breakdown: BreakdownMetrics,
record: LiteLLM_DailyUserSpend,
model_metadata: Dict[str, Dict[str, Any]],
provider_metadata: Dict[str, Dict[str, Any]],
api_key_metadata: Dict[str, Dict[str, Any]],
) -> BreakdownMetrics:
"""Updates breakdown metrics for a single record using the existing update_metrics function"""
# Update model breakdown
if record.model:
if record.model not in breakdown.models:
breakdown.models[record.model] = MetricWithMetadata(
metrics=SpendMetrics(),
metadata=model_metadata.get(
record.model, {}
), # Add any model-specific metadata here
)
breakdown.models[record.model].metrics = update_metrics(
breakdown.models[record.model].metrics, record
)
# Update provider breakdown
provider = record.custom_llm_provider or "unknown"
if provider not in breakdown.providers:
breakdown.providers[provider] = MetricWithMetadata(
metrics=SpendMetrics(),
metadata=provider_metadata.get(
provider, {}
), # Add any provider-specific metadata here
)
breakdown.providers[provider].metrics = update_metrics(
breakdown.providers[provider].metrics, record
)
# Update api key breakdown
if record.api_key not in breakdown.api_keys:
breakdown.api_keys[record.api_key] = KeyMetricWithMetadata(
metrics=SpendMetrics(),
metadata=KeyMetadata(
key_alias=api_key_metadata.get(record.api_key, {}).get(
"key_alias", None
)
), # Add any api_key-specific metadata here
)
breakdown.api_keys[record.api_key].metrics = update_metrics(
breakdown.api_keys[record.api_key].metrics, record
)
return breakdown
# Using shared metric helper implementations from common_daily_activity
@router.get(
@ -1857,6 +1790,7 @@ def update_breakdown_metrics(
dependencies=[Depends(user_api_key_auth)],
response_model=SpendAnalyticsPaginatedResponse,
)
@management_endpoint_wrapper
async def get_user_daily_activity(
start_date: Optional[str] = fastapi.Query(
default=None,
@ -1939,3 +1873,74 @@ async def get_user_daily_activity(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail={"error": f"Failed to fetch analytics: {str(e)}"},
)
@router.get(
"/user/daily/activity/aggregated",
tags=["Budget & Spend Tracking", "Internal User management"],
dependencies=[Depends(user_api_key_auth)],
response_model=SpendAnalyticsPaginatedResponse,
)
@management_endpoint_wrapper
async def get_user_daily_activity_aggregated(
start_date: Optional[str] = fastapi.Query(
default=None,
description="Start date in YYYY-MM-DD format",
),
end_date: Optional[str] = fastapi.Query(
default=None,
description="End date in YYYY-MM-DD format",
),
model: Optional[str] = fastapi.Query(
default=None,
description="Filter by specific model",
),
api_key: Optional[str] = fastapi.Query(
default=None,
description="Filter by specific API key",
),
user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
) -> SpendAnalyticsPaginatedResponse:
"""
Aggregated analytics for a user's daily activity without pagination.
Returns the same response shape as the paginated endpoint with page metadata set to single-page.
"""
from litellm.proxy.proxy_server import prisma_client
if prisma_client is None:
raise HTTPException(
status_code=500,
detail={"error": CommonProxyErrors.db_not_connected_error.value},
)
if start_date is None or end_date is None:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail={"error": "Please provide start_date and end_date"},
)
try:
entity_id: Optional[str] = None
if not _user_has_admin_view(user_api_key_dict):
entity_id = user_api_key_dict.user_id
return await get_daily_activity_aggregated(
prisma_client=prisma_client,
table_name="litellm_dailyuserspend",
entity_id_field="user_id",
entity_id=entity_id,
entity_metadata_field=None,
start_date=start_date,
end_date=end_date,
model=model,
api_key=api_key,
)
except Exception as e:
verbose_proxy_logger.exception(
"/user/daily/activity/aggregated: Exception occured - {}".format(str(e))
)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail={"error": f"Failed to fetch analytics: {str(e)}"},
)

472
litellm/proxy/management_endpoints/ui_sso.py
View File

@ -51,6 +51,7 @@ from litellm.proxy.common_utils.admin_ui_utils import (
from litellm.proxy.common_utils.html_forms.jwt_display_template import (
jwt_display_template,
)
from litellm.proxy.common_utils.html_forms.ui_login import html_form
from litellm.proxy.management_endpoints.internal_user_endpoints import new_user
from litellm.proxy.management_endpoints.sso_helper_utils import (
check_is_admin_only_access,
@ -76,20 +77,16 @@ router = APIRouter()
@router.get("/sso/key/generate", tags=["experimental"], include_in_schema=False)
async def serve_login_page(
request: Request,
source: Optional[str] = None,
key: Optional[str] = None,
error: Optional[str] = None,
):
async def google_login(request: Request, source: Optional[str] = None, key: Optional[str] = None): # noqa: PLR0915
"""
Create Proxy API Keys using Google Workspace SSO. Requires setting PROXY_BASE_URL in .env
PROXY_BASE_URL should be the your deployed proxy endpoint, e.g. PROXY_BASE_URL="https://litellm-production-7002.up.railway.app/"
Example:
Serves a unified login page with options for both normal
username/password login and SSO.
"""
from litellm.proxy.proxy_server import premium_user
from litellm.proxy.proxy_server import (
premium_user,
user_custom_ui_sso_sign_in_handler,
)
microsoft_client_id = os.getenv("MICROSOFT_CLIENT_ID", None)
google_client_id = os.getenv("GOOGLE_CLIENT_ID", None)
@ -102,334 +99,6 @@ async def serve_login_page(
if is_disabled:
return admin_ui_disabled()
####### Check if user is a Enterprise / Premium User for SSO #######
sso_available = False
if (
microsoft_client_id is not None
or google_client_id is not None
or generic_client_id is not None
):
if premium_user is True:
sso_available = True
####### Detect DB + MASTER KEY in .env #######
missing_env_vars = show_missing_vars_in_env()
if missing_env_vars is not None:
return missing_env_vars
#########################################################
# Construct Redirect URL
base_url_to_redirect_to: Optional[str] = None
base_url_to_redirect_to = os.getenv("PROXY_BASE_URL", "")
server_root_path = os.getenv("SERVER_ROOT_PATH", "")
if server_root_path != "":
base_url_to_redirect_to += server_root_path
#########################################################
# Build the unified login page HTML
error_message = ""
if error == "1":
error_message = """
<div style="
background-color: #fef2f2;
border-left: 4px solid #dc2626;
border-radius: 6px;
padding: 16px;
margin-bottom: 20px;
color: #dc2626;
font-size: 14px;
font-weight: 500;
">
⚠️ Invalid username or password. Please try again.
</div>
"""
sso_button = ""
if sso_available:
sso_login_url = base_url_to_redirect_to
if sso_login_url.endswith("/"):
sso_login_url += "sso/login"
else:
sso_login_url += "/sso/login"
sso_button = f"""
<div style="
margin-top: 20px;
padding-top: 20px;
border-top: 1px solid #e2e8f0;
text-align: center;
">
<p style="
color: #64748b;
font-size: 14px;
margin-bottom: 16px;
">or</p>
<a href="{sso_login_url}" style="
display: inline-block;
background-color: #f8fafc;
border: 1px solid #e2e8f0;
color: #374151;
padding: 10px 20px;
border-radius: 6px;
text-decoration: none;
font-weight: 500;
transition: all 0.2s;
font-size: 14px;
" onmouseover="this.style.backgroundColor='#f1f5f9'; this.style.borderColor='#cbd5e1';"
onmouseout="this.style.backgroundColor='#f8fafc'; this.style.borderColor='#e2e8f0';">
🔐 Login with SSO
</a>
</div>
"""
if base_url_to_redirect_to.endswith("/"):
url_to_redirect_to = base_url_to_redirect_to + "login"
else:
url_to_redirect_to = base_url_to_redirect_to + "/login"
unified_login_html = f"""
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>LiteLLM Login</title>
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<style>
body {{
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, sans-serif;
background-color: #f8fafc;
margin: 0;
padding: 20px;
display: flex;
justify-content: center;
align-items: center;
min-height: 100vh;
color: #333;
}}
form {{
background-color: #fff;
padding: 40px;
border-radius: 8px;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.1);
width: 450px;
max-width: 100%;
}}
.logo-container {{
text-align: center;
margin-bottom: 30px;
}}
.logo {{
font-size: 24px;
font-weight: 600;
color: #1e293b;
}}
h2 {{
margin: 0 0 10px;
color: #1e293b;
font-size: 28px;
font-weight: 600;
text-align: center;
}}
.subtitle {{
color: #64748b;
margin: 0 0 20px;
font-size: 16px;
text-align: center;
}}
.info-box {{
background-color: #f1f5f9;
border-radius: 6px;
padding: 20px;
margin-bottom: 30px;
border-left: 4px solid #2563eb;
}}
.info-header {{
display: flex;
align-items: center;
margin-bottom: 12px;
color: #1e40af;
font-weight: 600;
font-size: 16px;
}}
.info-header svg {{
margin-right: 8px;
}}
.info-box p {{
color: #475569;
margin: 8px 0;
line-height: 1.5;
font-size: 14px;
}}
label {{
display: block;
margin-bottom: 8px;
font-weight: 500;
color: #334155;
font-size: 14px;
}}
.required {{
color: #dc2626;
margin-left: 2px;
}}
input[type="text"],
input[type="password"] {{
width: 100%;
padding: 10px 14px;
margin-bottom: 20px;
box-sizing: border-box;
border: 1px solid #e2e8f0;
border-radius: 6px;
font-size: 15px;
color: #1e293b;
background-color: #fff;
transition: border-color 0.2s, box-shadow 0.2s;
}}
input[type="text"]:focus,
input[type="password"]:focus {{
outline: none;
border-color: #3b82f6;
box-shadow: 0 0 0 2px rgba(59, 130, 246, 0.2);
}}
.toggle-password {{
display: flex;
align-items: center;
margin-top: -15px;
margin-bottom: 20px;
}}
.toggle-password input[type="checkbox"] {{
margin-right: 8px;
vertical-align: middle;
width: 16px;
height: 16px;
}}
.toggle-password label {{
margin-bottom: 0;
font-size: 14px;
cursor: pointer;
line-height: 1;
}}
input[type="submit"] {{
background-color: #6466E9;
color: #fff;
cursor: pointer;
font-weight: 500;
border: none;
padding: 10px 16px;
transition: background-color 0.2s;
border-radius: 6px;
margin-top: 10px;
font-size: 14px;
width: 100%;
}}
input[type="submit"]:hover {{
background-color: #4138C2;
}}
a {{
color: #3b82f6;
text-decoration: none;
}}
a:hover {{
text-decoration: underline;
}}
code {{
background-color: #f1f5f9;
padding: 2px 4px;
border-radius: 4px;
font-family: monospace;
font-size: 13px;
color: #334155;
}}
</style>
</head>
<body>
<form action="{url_to_redirect_to}" method="post">
<div class="logo-container">
<div class="logo">
🚅 LiteLLM
</div>
</div>
<h2>Login</h2>
<p class="subtitle">Access your LiteLLM Admin UI.</p>
{error_message}
<div class="info-box">
<div class="info-header">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<circle cx="12" cy="12" r="10"></circle>
<line x1="12" y1="16" x2="12" y2="12"></line>
<line x1="12" y1="8" x2="12.01" y2="8"></line>
</svg>
Default Credentials
</div>
<p>By default, Username is <code>admin</code> and Password is your set LiteLLM Proxy <code>MASTER_KEY</code>.</p>
<p>Need to set UI credentials or SSO? <a href="https://docs.litellm.ai/docs/proxy/ui" target="_blank">Check the documentation</a>.</p>
</div>
<label for="username">Username<span class="required">*</span></label>
<input type="text" id="username" name="username" required placeholder="Enter your username" autocomplete="username">
<label for="password">Password<span class="required">*</span></label>
<input type="password" id="password" name="password" required placeholder="Enter your password" autocomplete="current-password">
<div class="toggle-password">
<input type="checkbox" id="show-password" onclick="togglePasswordVisibility()">
<label for="show-password">Show password</label>
</div>
<input type="submit" value="Login">
{sso_button}
</form>
<script>
function togglePasswordVisibility() {{
var passwordField = document.getElementById("password");
passwordField.type = passwordField.type === "password" ? "text" : "password";
}}
</script>
</body>
</html>
"""
from fastapi.responses import HTMLResponse
return HTMLResponse(content=unified_login_html, status_code=200)
@router.get("/sso/login", tags=["experimental"], include_in_schema=False)
async def sso_login_redirect(
request: Request, source: Optional[str] = None, key: Optional[str] = None
):
"""
Handles SSO login redirect - this is what the "Login with SSO" button points to
"""
from litellm.proxy.proxy_server import (
premium_user,
user_custom_ui_sso_sign_in_handler,
)
microsoft_client_id = os.getenv("MICROSOFT_CLIENT_ID", None)
google_client_id = os.getenv("GOOGLE_CLIENT_ID", None)
generic_client_id = os.getenv("GENERIC_CLIENT_ID", None)
####### Check if user is a Enterprise / Premium User #######
if (
microsoft_client_id is not None
@ -444,12 +113,18 @@ async def sso_login_redirect(
code=status.HTTP_403_FORBIDDEN,
)
####### Detect DB + MASTER KEY in .env #######
missing_env_vars = show_missing_vars_in_env()
if missing_env_vars is not None:
return missing_env_vars
ui_username = os.getenv("UI_USERNAME")
# get url from request - always use regular callback, but set state for CLI
redirect_url = SSOAuthenticationHandler.get_redirect_url_for_sso(
request=request,
sso_callback_route="sso/callback",
)
# Store CLI key in state for OAuth flow
cli_state: Optional[str] = SSOAuthenticationHandler._get_cli_state(
source=source,
@ -462,14 +137,11 @@ async def sso_login_redirect(
from litellm_enterprise.proxy.auth.custom_sso_handler import (
EnterpriseCustomSSOHandler,
)
return await EnterpriseCustomSSOHandler.handle_custom_ui_sso_sign_in(
request=request,
)
except ImportError:
raise ValueError(
"Enterprise features are not available. Custom UI SSO sign-in requires LiteLLM Enterprise."
)
raise ValueError("Enterprise features are not available. Custom UI SSO sign-in requires LiteLLM Enterprise.")
# Check if we should use SSO handler
if (
@ -488,9 +160,16 @@ async def sso_login_redirect(
generic_client_id=generic_client_id,
state=cli_state,
)
elif ui_username is not None:
# No Google, Microsoft SSO
# Use UI Credentials set in .env
from fastapi.responses import HTMLResponse
return HTMLResponse(content=html_form, status_code=200)
else:
# No SSO configured, redirect back to login page
return RedirectResponse(url="/sso/key/generate", status_code=303)
from fastapi.responses import HTMLResponse
return HTMLResponse(content=html_form, status_code=200)
def generic_response_convertor(
@ -846,16 +525,15 @@ async def check_and_update_if_proxy_admin_id(
async def auth_callback(request: Request, state: Optional[str] = None): # noqa: PLR0915
"""Verify login"""
verbose_proxy_logger.info(f"Starting SSO callback with state: {state}")
# Check if this is a CLI login (state starts with our CLI prefix)
from litellm.constants import LITELLM_CLI_SESSION_TOKEN_PREFIX
if state and state.startswith(f"{LITELLM_CLI_SESSION_TOKEN_PREFIX}:"):
# Extract the key ID from the state
key_id = state.split(":", 1)[1]
verbose_proxy_logger.info(f"CLI SSO callback detected for key: {key_id}")
return await cli_sso_callback(request, key=key_id)
from litellm.proxy._types import LiteLLM_JWTAuth
from litellm.proxy.auth.handle_jwt import JWTHandler
from litellm.proxy.proxy_server import (
@ -930,7 +608,7 @@ async def auth_callback(request: Request, state: Optional[str] = None): # noqa:
status_code=401,
detail="Result not returned by SSO provider.",
)
return await SSOAuthenticationHandler.get_redirect_response_from_openid(
result=result,
request=request,
@ -940,26 +618,28 @@ async def auth_callback(request: Request, state: Optional[str] = None): # noqa:
)
async def cli_sso_callback(request: Request, key: Optional[str] = None):
"""CLI SSO callback - generates the key with pre-specified ID"""
verbose_proxy_logger.info(f"CLI SSO callback for key: {key}")
from litellm.proxy.management_endpoints.key_management_endpoints import (
generate_key_helper_fn,
)
from litellm.proxy.proxy_server import prisma_client
if not key or not key.startswith("sk-"):
if not key or not key.startswith('sk-'):
raise HTTPException(
status_code=400,
detail="Invalid key parameter. Must be a valid key ID starting with 'sk-'",
detail="Invalid key parameter. Must be a valid key ID starting with 'sk-'"
)
if prisma_client is None:
raise HTTPException(
status_code=500, detail=CommonProxyErrors.db_not_connected_error.value
)
# Generate a simple key for CLI usage with the pre-specified key ID
try:
await generate_key_helper_fn(
@ -973,57 +653,63 @@ async def cli_sso_callback(request: Request, key: Optional[str] = None):
table_name="key",
token=key, # Use the pre-specified key ID
)
verbose_proxy_logger.info(f"Generated CLI key: {key}")
# Return success page
from fastapi.responses import HTMLResponse
from litellm.proxy.common_utils.html_forms.cli_sso_success import (
render_cli_sso_success_page,
)
html_content = render_cli_sso_success_page()
return HTMLResponse(content=html_content, status_code=200)
except Exception as e:
verbose_proxy_logger.error(f"Error generating CLI key: {e}")
raise HTTPException(status_code=500, detail=f"Failed to generate key: {str(e)}")
raise HTTPException(
status_code=500,
detail=f"Failed to generate key: {str(e)}"
)
@router.get("/sso/cli/poll/{key_id}", tags=["experimental"], include_in_schema=False)
async def cli_poll_key(key_id: str):
"""CLI polling endpoint - checks if key exists in DB"""
from litellm.proxy.proxy_server import prisma_client
if not key_id.startswith("sk-"):
raise HTTPException(status_code=400, detail="Invalid key ID format")
if not key_id.startswith('sk-'):
raise HTTPException(
status_code=400,
detail="Invalid key ID format"
)
if prisma_client is None:
raise HTTPException(
status_code=500, detail=CommonProxyErrors.db_not_connected_error.value
)
try:
# Check if key exists in database
from litellm.proxy.utils import hash_token
hashed_token = hash_token(key_id)
key_obj = await prisma_client.db.litellm_verificationtoken.find_unique(
where={"token": hashed_token}
)
if key_obj:
verbose_proxy_logger.info(f"CLI key found: {key_id}")
return {"status": "ready", "key": key_id}
else:
return {"status": "pending"}
except Exception as e:
verbose_proxy_logger.error(f"Error polling for CLI key: {e}")
raise HTTPException(
status_code=500, detail=f"Error checking key status: {str(e)}"
status_code=500,
detail=f"Error checking key status: {str(e)}"
)
@ -1125,7 +811,6 @@ class SSOAuthenticationHandler:
"""
Handler for SSO Authentication across all SSO providers
"""
@staticmethod
async def get_sso_login_redirect(
redirect_url: str,
@ -1478,6 +1163,7 @@ class SSOAuthenticationHandler:
_new_team_request.update(_default_team_params)
team_request = NewTeamRequest(**_new_team_request)
return team_request
@staticmethod
def _get_cli_state(source: Optional[str], key: Optional[str]) -> Optional[str]:
@ -1490,15 +1176,13 @@ class SSOAuthenticationHandler:
LITELLM_CLI_SESSION_TOKEN_PREFIX,
LITELLM_CLI_SOURCE_IDENTIFIER,
)
return f"{LITELLM_CLI_SESSION_TOKEN_PREFIX}:{key}" if source == LITELLM_CLI_SOURCE_IDENTIFIER and key else None
return (
f"{LITELLM_CLI_SESSION_TOKEN_PREFIX}:{key}"
if source == LITELLM_CLI_SOURCE_IDENTIFIER and key
else None
)
@staticmethod
async def get_redirect_response_from_openid( # noqa: PLR0915
async def get_redirect_response_from_openid( # noqa: PLR0915
result: Union[OpenID, dict, CustomOpenID],
request: Request,
received_response: Optional[dict] = None,
@ -1518,18 +1202,14 @@ class SSOAuthenticationHandler:
)
from litellm.proxy.utils import get_prisma_client_or_throw
from litellm.types.proxy.ui_sso import ReturnedUITokenObject
prisma_client = get_prisma_client_or_throw("Prisma client is None, connect a database to your proxy")
prisma_client = get_prisma_client_or_throw(
"Prisma client is None, connect a database to your proxy"
)
# User is Authe'd in - generate key for the UI to access Proxy
verbose_proxy_logger.info(f"SSO callback result: {result}")
user_email: Optional[str] = getattr(result, "email", None)
user_id: Optional[str] = (
getattr(result, "id", None) if result is not None else None
)
user_id: Optional[str] = getattr(result, "id", None) if result is not None else None
if user_email is not None and os.getenv("ALLOWED_EMAIL_DOMAINS") is not None:
email_domain = user_email.split("@")[1]
@ -1714,8 +1394,7 @@ class SSOAuthenticationHandler:
redirect_response = RedirectResponse(url=litellm_dashboard_ui, status_code=303)
redirect_response.set_cookie(key="token", value=jwt_token)
return redirect_response
class MicrosoftSSOHandler:
"""
Handles Microsoft SSO callback response and returns a CustomOpenID object
@ -2215,28 +1894,3 @@ async def debug_sso_callback(request: Request):
)
return HTMLResponse(content=html_content)
@router.post("/sso/key/generate", tags=["experimental"], include_in_schema=False)
async def process_login(request: Request):
"""
Process username/password login from the unified login page
"""
try:
# Get form data
form_data = await request.form()
username = form_data.get("username")
password = form_data.get("password")
if not username or not password:
return RedirectResponse(url="/sso/key/generate?error=1", status_code=303)
# Import the actual login function from proxy_server
from litellm.proxy.proxy_server import login
# Call the real login function that handles all the authentication properly
return await login(request)
except Exception as e:
verbose_proxy_logger.error(f"Error processing login: {e}")
return RedirectResponse(url="/sso/key/generate?error=1", status_code=303)

14
litellm/proxy/proxy_config.yaml
View File

@ -1,15 +1,5 @@
model_list:
- model_name: bedrock/*
- model_name: gemini/*
litellm_params:
model: bedrock/*
model: gemini/*
litellm_settings:
callbacks: ["s3_v2"]
s3_callback_params:
s3_bucket_name: litellm-logs # AWS Bucket Name for S3
s3_region_name: us-west-2
general_settings:
cold_storage_custom_logger: s3_v2
store_prompts_in_cold_storage: true

4
litellm/responses/litellm_completion_transformation/handler.py
View File

@ -84,6 +84,8 @@ class LiteLLMCompletionTransformationHandler:
litellm_custom_stream_wrapper=litellm_completion_response,
request_input=input,
responses_api_request=responses_api_request,
custom_llm_provider=custom_llm_provider,
litellm_metadata=kwargs.get("litellm_metadata", {}),
)
async def async_response_api_handler(
@ -129,4 +131,6 @@ class LiteLLMCompletionTransformationHandler:
litellm_custom_stream_wrapper=litellm_completion_response,
request_input=request_input,
responses_api_request=responses_api_request,
custom_llm_provider=litellm_completion_request.get("custom_llm_provider"),
litellm_metadata=kwargs.get("litellm_metadata", {}),
)

24
litellm/responses/litellm_completion_transformation/streaming_iterator.py
View File

@ -6,6 +6,7 @@ from litellm.responses.litellm_completion_transformation.transformation import (
LiteLLMCompletionResponsesConfig,
)
from litellm.responses.streaming_iterator import ResponsesAPIStreamingIterator
from litellm.responses.utils import ResponsesAPIRequestUtils
from litellm.types.llms.openai import (
OutputTextDeltaEvent,
ReasoningSummaryTextDeltaEvent,
@ -34,6 +35,8 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
litellm_custom_stream_wrapper: litellm.CustomStreamWrapper,
request_input: Union[str, ResponseInputParam],
responses_api_request: ResponsesAPIOptionalRequestParams,
custom_llm_provider: Optional[str] = None,
litellm_metadata: Optional[dict] = None,
):
self.litellm_custom_stream_wrapper: litellm.CustomStreamWrapper = (
litellm_custom_stream_wrapper
@ -42,6 +45,8 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
self.responses_api_request: ResponsesAPIOptionalRequestParams = (
responses_api_request
)
self.custom_llm_provider: Optional[str] = custom_llm_provider
self.litellm_metadata: Optional[dict] = litellm_metadata or {}
self.collected_chat_completion_chunks: List[ModelResponseStream] = []
self.finished: bool = False
@ -164,14 +169,23 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
Union[ModelResponse, TextCompletionResponse]
] = stream_chunk_builder(chunks=self.collected_chat_completion_chunks)
if litellm_model_response and isinstance(litellm_model_response, ModelResponse):
# Transform the response
responses_api_response = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
request_input=self.request_input,
chat_completion_response=litellm_model_response,
responses_api_request=self.responses_api_request,
)
# Encode the response ID to match non-streaming behavior
encoded_response = ResponsesAPIRequestUtils._update_responses_api_response_id_with_model_id(
responses_api_response=responses_api_response,
custom_llm_provider=self.custom_llm_provider,
litellm_metadata=self.litellm_metadata,
)
return ResponseCompletedEvent(
type=ResponsesAPIStreamEvents.RESPONSE_COMPLETED,
response=LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
request_input=self.request_input,
chat_completion_response=litellm_model_response,
responses_api_request=self.responses_api_request,
),
response=encoded_response,
)
else:
return None

33
litellm/utils.py
View File

@ -2912,6 +2912,39 @@ def _remove_strict_from_schema(schema):
return schema
def _remove_json_schema_refs(schema, max_depth=10):
"""
Remove JSON schema reference fields like '$id' and '$schema' that can cause issues with some providers.
These fields are used for schema validation but can cause problems when the schema references
are not accessible to the provider's validation system.
Args:
schema: The schema object to clean (dict, list, or other)
max_depth: Maximum recursion depth to prevent infinite loops (default: 10)
Relevant Issues: Mistral API grammar validation fails when schema contains $id and $schema references
"""
if max_depth <= 0:
return schema
if isinstance(schema, dict):
# Remove JSON schema reference fields
schema.pop("$id", None)
schema.pop("$schema", None)
# Recursively process all dictionary values
for key, value in schema.items():
_remove_json_schema_refs(value, max_depth - 1)
elif isinstance(schema, list):
# Recursively process all items in the list
for item in schema:
_remove_json_schema_refs(item, max_depth - 1)
return schema
def _remove_unsupported_params(
non_default_params: dict, supported_openai_params: Optional[List[str]]
) -> dict:

604
model_prices_and_context_window.json
View File

@ -296,60 +296,6 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"watsonx/ibm/granite-3-8b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -666,6 +612,263 @@
"search_context_size_high": 0.03
}
},
"gpt-5": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-mini": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-nano": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-chat": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2e-05,
"input_cost_per_token_batches": 2.5e-06,
"output_cost_per_token_batches": 1e-05,
"cache_read_input_token_cost": 1.25e-06,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true
},
"gpt-5-chat-latest": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"codex-mini-latest": {
"max_tokens": 100000,
"max_input_tokens": 200000,
@ -2061,6 +2264,263 @@
"/v1/audio/speech"
]
},
"azure/gpt-5": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-mini": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-nano": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-5-chat": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2e-05,
"input_cost_per_token_batches": 2.5e-06,
"output_cost_per_token_batches": 1e-05,
"cache_read_input_token_cost": 1.25e-06,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true
},
"azure/gpt-5-chat-latest": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"azure/gpt-4o-mini-tts": {
"mode": "audio_speech",
"input_cost_per_token": 2.5e-06,
@ -5825,6 +6285,32 @@
"supports_reasoning": true,
"supports_computer_use": true
},
"claude-opus-4-1": {
"max_tokens": 32000,
"max_input_tokens": 200000,
"max_output_tokens": 32000,
"input_cost_per_token": 1.5e-05,
"output_cost_per_token": 7.5e-05,
"search_context_cost_per_query": {
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01,
"search_context_size_high": 0.01
},
"cache_creation_input_token_cost": 1.875e-05,
"cache_read_input_token_cost": 1.5e-06,
"litellm_provider": "anthropic",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 159,
"supports_assistant_prefill": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_computer_use": true
},
"claude-opus-4-1-20250805": {
"max_tokens": 32000,
"max_input_tokens": 200000,
@ -17758,7 +18244,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/meta.llama-4-scout-17b-16e-instruct": {
@ -17771,7 +18256,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/meta.llama-3.3-70b-instruct": {
@ -17784,7 +18268,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/meta.llama-3.2-90b-vision-instruct": {
@ -17797,7 +18280,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/meta.llama-3.1-405b-instruct": {
@ -17810,7 +18292,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
@ -17824,7 +18305,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-3": {
@ -17837,7 +18317,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-3-mini": {
@ -17850,7 +18329,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-3-fast": {
@ -17863,7 +18341,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
},
"oci/xai.grok-3-mini-fast": {
@ -17876,7 +18353,6 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_tool_choice": false,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing"
}
}

7
poetry.lock generated
View File

@ -2538,15 +2538,14 @@ files = [
[[package]]
name = "litellm-proxy-extras"
version = "0.2.15"
version = "0.2.16"
description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
optional = true
python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
groups = ["main"]
markers = "extra == \"proxy\""
files = [
{file = "litellm_proxy_extras-0.2.15-py3-none-any.whl", hash = "sha256:25e7d7cabe3f10233e2802d4521576bef438eea8b0800b1dbf38ba83ba751bb8"},
{file = "litellm_proxy_extras-0.2.15.tar.gz", hash = "sha256:62a9fdcb77d25aa7bfdfa04ac878e452f185dfb0b9538d4d8988a1b512360649"},
{file = "litellm_proxy_extras-0.2.16.tar.gz", hash = "sha256:81a1e8a172feb7da86985f529e891ca7be66ba293ae3e716bf69b266fa776a04"},
]
[[package]]
@ -6524,4 +6523,4 @@ utils = ["numpydoc"]
[metadata]
lock-version = "2.1"
python-versions = ">=3.8.1,<4.0, !=3.9.7"
content-hash = "8caa7dd3ee7d56562ccb799b97de7f2d206010d8300139bdc3614853c9ea1d31"
content-hash = "91f8d8cba2aa02a3eb205e91118891612c510790e828b56d19057fc509e6d25d"

8
proxy_server_config.yaml
View File

@ -137,6 +137,14 @@ model_list:
model: openai/my-fake-model
api_key: my-fake-key
api_base: https://exampleopenaiendpoint-production.up.railway.appxxxx/
- model_name: gemini-1.5-flash
litellm_params:
model: gemini/gemini-1.5-flash
api_key: os.environ/GOOGLE_API_KEY
- model_name: gpt-4o
litellm_params:
model: gpt-4o
api_key: os.environ/OPENAI_API_KEY
litellm_settings:

6
pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry]
name = "litellm"
version = "1.75.2"
version = "1.75.3"
description = "Library to easily interface with LLM API providers"
authors = ["BerriAI"]
license = "MIT"
@ -58,7 +58,7 @@ websockets = {version = "^13.1.0", optional = true}
boto3 = {version = "1.34.34", optional = true}
redisvl = {version = "^0.4.1", optional = true, markers = "python_version >= '3.9' and python_version < '3.14'"}
mcp = {version = "^1.10.0", optional = true, python = ">=3.10"}
litellm-proxy-extras = {version = "0.2.15", optional = true}
litellm-proxy-extras = {version = "0.2.16", optional = true}
rich = {version = "13.7.1", optional = true}
litellm-enterprise = {version = "0.1.19", optional = true}
diskcache = {version = "^5.6.1", optional = true}
@ -154,7 +154,7 @@ requires = ["poetry-core", "wheel"]
build-backend = "poetry.core.masonry.api"
[tool.commitizen]
version = "1.75.2"
version = "1.75.3"
version_files = [
"pyproject.toml:^version"
]

2
requirements.txt
View File

@ -41,7 +41,7 @@ sentry_sdk==2.21.0 # for sentry error handling
detect-secrets==1.5.0 # Enterprise - secret detection / masking in LLM requests
cryptography==43.0.1
tzdata==2025.1 # IANA time zone database
litellm-proxy-extras==0.2.15 # for proxy extras - e.g. prisma migrations
litellm-proxy-extras==0.2.16 # for proxy extras - e.g. prisma migrations
### LITELLM PACKAGE DEPENDENCIES
python-dotenv==1.0.1 # for env
tiktoken==0.8.0 # for calculating usage

1
tests/code_coverage_tests/recursive_detector.py
View File

@ -25,6 +25,7 @@ IGNORE_FUNCTIONS = [
"filter_value_from_dict", # max depth set.
"normalize_json_schema_types", # max depth set.
"_extract_fields_recursive", # max depth set.
"_remove_json_schema_refs", # max depth set.
]

239
tests/llm_responses_api_testing/test_base_responses_api_streaming_iterator.py Normal file
View File

@ -0,0 +1,239 @@
"""
Unit tests for BaseResponsesAPIStreamingIterator
Tests core functionality including:
1. Processing chunks and handling ResponseCompletedEvent
2. Ensuring _update_responses_api_response_id_with_model_id is called for final chunk
3. Verifying ID update is NOT called for non-final chunks (delta events)
4. Edge case handling for invalid JSON, empty chunks, and [DONE] markers
These tests ensure the streaming iterator correctly processes response chunks
and applies model ID updates only to completed responses, as required for proper
response tracking and logging.
"""
import json
import os
import sys
from datetime import datetime
from typing import Any, Dict, Optional
from unittest.mock import Mock, patch
import pytest
sys.path.insert(0, os.path.abspath("../.."))
from litellm.constants import STREAM_SSE_DONE_STRING
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.llms.base_llm.responses.transformation import BaseResponsesAPIConfig
from litellm.responses.streaming_iterator import BaseResponsesAPIStreamingIterator
from litellm.responses.utils import ResponsesAPIRequestUtils
from litellm.types.llms.openai import (
ResponseCompletedEvent,
ResponsesAPIResponse,
ResponsesAPIStreamEvents,
OutputTextDeltaEvent
)
class TestBaseResponsesAPIStreamingIterator:
"""Test cases for BaseResponsesAPIStreamingIterator"""
def test_process_chunk_with_response_completed_event(self):
"""
Test that _process_chunk correctly processes a ResponseCompletedEvent
and calls _update_responses_api_response_id_with_model_id for the final chunk.
"""
# Mock dependencies
mock_response = Mock()
mock_logging_obj = Mock(spec=LiteLLMLoggingObj)
mock_config = Mock(spec=BaseResponsesAPIConfig)
# Create a mock ResponsesAPIResponse for the completed event
mock_responses_api_response = Mock(spec=ResponsesAPIResponse)
mock_responses_api_response.id = "original_response_id"
# Create a mock ResponseCompletedEvent
mock_completed_event = Mock(spec=ResponseCompletedEvent)
mock_completed_event.type = ResponsesAPIStreamEvents.RESPONSE_COMPLETED
mock_completed_event.response = mock_responses_api_response
# Set up the mock transform method to return our completed event
mock_config.transform_streaming_response.return_value = mock_completed_event
# Mock the _update_responses_api_response_id_with_model_id method
updated_response = Mock(spec=ResponsesAPIResponse)
updated_response.id = "updated_response_id"
# Create the iterator instance
iterator = BaseResponsesAPIStreamingIterator(
response=mock_response,
model="gpt-4",
responses_api_provider_config=mock_config,
logging_obj=mock_logging_obj,
litellm_metadata={"model_info": {"id": "model_123"}},
custom_llm_provider="openai"
)
# Prepare test chunk data
test_chunk_data = {
"type": "response.completed",
"response": {
"id": "original_response_id",
"output": [{"type": "message", "content": [{"text": "Hello World"}]}]
}
}
with patch.object(
ResponsesAPIRequestUtils,
'_update_responses_api_response_id_with_model_id',
return_value=updated_response
) as mock_update_id:
# Process the chunk
result = iterator._process_chunk(json.dumps(test_chunk_data))
# Assertions
assert result is not None
assert result.type == ResponsesAPIStreamEvents.RESPONSE_COMPLETED
# Verify that _update_responses_api_response_id_with_model_id was called
mock_update_id.assert_called_once_with(
responses_api_response=mock_responses_api_response,
litellm_metadata={"model_info": {"id": "model_123"}},
custom_llm_provider="openai"
)
# Verify the completed response was stored
assert iterator.completed_response == result
# Verify the response was updated on the event
assert result.response == updated_response
def test_process_chunk_with_delta_event_no_id_update(self):
"""
Test that _process_chunk correctly processes a delta event
and does NOT call _update_responses_api_response_id_with_model_id.
"""
# Mock dependencies
mock_response = Mock()
mock_logging_obj = Mock(spec=LiteLLMLoggingObj)
mock_config = Mock(spec=BaseResponsesAPIConfig)
# Create a mock OutputTextDeltaEvent (not a completed event)
mock_delta_event = Mock(spec=OutputTextDeltaEvent)
mock_delta_event.type = ResponsesAPIStreamEvents.OUTPUT_TEXT_DELTA
mock_delta_event.delta = "Hello"
# Delta events don't have a response attribute
delattr(mock_delta_event, 'response') if hasattr(mock_delta_event, 'response') else None
# Set up the mock transform method to return our delta event
mock_config.transform_streaming_response.return_value = mock_delta_event
# Create the iterator instance
iterator = BaseResponsesAPIStreamingIterator(
response=mock_response,
model="gpt-4",
responses_api_provider_config=mock_config,
logging_obj=mock_logging_obj,
litellm_metadata={"model_info": {"id": "model_123"}},
custom_llm_provider="openai"
)
# Prepare test chunk data for a delta event
test_chunk_data = {
"type": "response.output_text.delta",
"delta": "Hello",
"item_id": "item_123",
"output_index": 0,
"content_index": 0
}
with patch.object(
ResponsesAPIRequestUtils,
'_update_responses_api_response_id_with_model_id'
) as mock_update_id:
# Process the chunk
result = iterator._process_chunk(json.dumps(test_chunk_data))
# Assertions
assert result is not None
assert result.type == ResponsesAPIStreamEvents.OUTPUT_TEXT_DELTA
# Verify that _update_responses_api_response_id_with_model_id was NOT called
mock_update_id.assert_not_called()
# Verify no completed response was stored (since this is not a completed event)
assert iterator.completed_response is None
def test_process_chunk_handles_invalid_json(self):
"""
Test that _process_chunk gracefully handles invalid JSON.
"""
# Mock dependencies
mock_response = Mock()
mock_logging_obj = Mock(spec=LiteLLMLoggingObj)
mock_config = Mock(spec=BaseResponsesAPIConfig)
# Create the iterator instance
iterator = BaseResponsesAPIStreamingIterator(
response=mock_response,
model="gpt-4",
responses_api_provider_config=mock_config,
logging_obj=mock_logging_obj
)
# Test with invalid JSON
result = iterator._process_chunk("invalid json {")
# Should return None for invalid JSON
assert result is None
assert iterator.completed_response is None
def test_process_chunk_handles_done_marker(self):
"""
Test that _process_chunk correctly handles the [DONE] marker.
"""
# Mock dependencies
mock_response = Mock()
mock_logging_obj = Mock(spec=LiteLLMLoggingObj)
mock_config = Mock(spec=BaseResponsesAPIConfig)
# Create the iterator instance
iterator = BaseResponsesAPIStreamingIterator(
response=mock_response,
model="gpt-4",
responses_api_provider_config=mock_config,
logging_obj=mock_logging_obj
)
# Test with [DONE] marker
result = iterator._process_chunk(STREAM_SSE_DONE_STRING)
# Should return None and set finished flag
assert result is None
assert iterator.finished is True
def test_process_chunk_handles_empty_chunk(self):
"""
Test that _process_chunk correctly handles empty or None chunks.
"""
# Mock dependencies
mock_response = Mock()
mock_logging_obj = Mock(spec=LiteLLMLoggingObj)
mock_config = Mock(spec=BaseResponsesAPIConfig)
# Create the iterator instance
iterator = BaseResponsesAPIStreamingIterator(
response=mock_response,
model="gpt-4",
responses_api_provider_config=mock_config,
logging_obj=mock_logging_obj
)
# Test with empty chunk
result = iterator._process_chunk("")
assert result is None
# Test with None chunk
result = iterator._process_chunk(None)
assert result is None

2
tests/llm_translation/test_gemini.py
View File

@ -430,7 +430,7 @@ def test_gemini_with_empty_function_call_arguments():
async def test_claude_tool_use_with_gemini():
response = await litellm.anthropic.messages.acreate(
messages=[
{"role": "user", "content": "Hello, can you tell me the weather in Boston?"}
{"role": "user", "content": "Hello, can you tell me the weather in Boston. Please respond with a tool call?"}
],
model="gemini/gemini-2.5-flash",
stream=True,

69
tests/local_testing/test_amazing_vertex_completion.py
View File

@ -504,75 +504,6 @@ async def test_async_vertexai_streaming_response():
pytest.fail(f"An exception occurred: {e}")
# asyncio.run(test_async_vertexai_streaming_response())
@pytest.mark.parametrize("provider", ["vertex_ai"]) # "vertex_ai_beta"
@pytest.mark.parametrize("sync_mode", [True, False])
@pytest.mark.flaky(retries=3, delay=1)
@pytest.mark.asyncio
async def test_gemini_pro_vision(provider, sync_mode):
try:
load_vertex_ai_credentials()
litellm.set_verbose = True
litellm.num_retries = 3
if sync_mode:
resp = litellm.completion(
model="{}/gemini-2.5-flash-lite".format(provider),
messages=[
{"role": "system", "content": "Be a good bot"},
{
"role": "user",
"content": [
{"type": "text", "text": "Whats in this image?"},
{
"type": "image_url",
"image_url": {
"url": "gs://cloud-samples-data/generative-ai/image/boats.jpeg"
},
},
],
},
],
)
else:
resp = await litellm.acompletion(
model="{}/gemini-2.5-flash-lite".format(provider),
messages=[
{"role": "system", "content": "Be a good bot"},
{
"role": "user",
"content": [
{"type": "text", "text": "Whats in this image?"},
{
"type": "image_url",
"image_url": {
"url": "gs://cloud-samples-data/generative-ai/image/boats.jpeg"
},
},
],
},
],
)
print(resp)
prompt_tokens = resp.usage.prompt_tokens
# DO Not DELETE this ASSERT
# Google counts the prompt tokens for us, we should ensure we use the tokens from the orignal response
assert prompt_tokens == 267 # the gemini api returns 267 to us
except litellm.RateLimitError as e:
pass
except Exception as e:
if "500 Internal error encountered.'" in str(e):
pass
else:
pytest.fail(f"An exception occurred - {str(e)}")
# test_gemini_pro_vision()
@pytest.mark.parametrize("load_pdf", [False]) # True,
@pytest.mark.flaky(retries=3, delay=1)

50
tests/local_testing/test_stream_chunk_builder.py
View File

@ -168,56 +168,6 @@ def test_stream_chunk_builder_litellm_tool_call_regular_message():
# test_stream_chunk_builder_litellm_tool_call_regular_message()
def test_stream_chunk_builder_litellm_usage_chunks():
"""
Checks if stream_chunk_builder is able to correctly rebuild with given metadata from streaming chunks
"""
from litellm.types.utils import Usage
messages = [
{"role": "user", "content": "Tell me the funniest joke you know."},
{
"role": "assistant",
"content": "Why did the chicken cross the road?\nYou will not guess this one I bet\n",
},
{"role": "user", "content": "I do not know, why?"},
{"role": "assistant", "content": "uhhhh\n\n\nhmmmm.....\nthinking....\n"},
{"role": "user", "content": "\nI am waiting...\n\n...\n"},
]
usage: litellm.Usage = Usage(
completion_tokens=27,
prompt_tokens=50,
total_tokens=82,
completion_tokens_details=None,
prompt_tokens_details=None,
)
gemini_pt = usage.prompt_tokens
# make a streaming gemini call
try:
response = completion(
model="gemini/gemini-2.5-flash-lite",
messages=messages,
stream=True,
complete_response=True,
stream_options={"include_usage": True},
)
except litellm.InternalServerError as e:
pytest.skip(f"Skipping test due to internal server error - {str(e)}")
usage: litellm.Usage = response.usage
stream_rebuilt_pt = usage.prompt_tokens
# assert prompt tokens are the same
assert (
gemini_pt == stream_rebuilt_pt
), f"Stream builder is not able to rebuild usage correctly. Got={stream_rebuilt_pt}, expected={gemini_pt}"
def test_stream_chunk_builder_litellm_mixed_calls():
response = stream_chunk_builder(stream_chunk_testdata.chunks)
assert (

4
tests/local_testing/test_streaming.py
View File

@ -701,7 +701,7 @@ async def test_completion_gemini_stream(sync_mode):
},
}
]
messages = [{"role": "user", "content": "What is the weather like in Boston?"}]
messages = [{"role": "user", "content": "What is the weather like in Boston, MA?. You must provide me with a tool call in your response."}]
print("testing gemini streaming")
complete_response = ""
# Add any assertions here to check the response
@ -817,7 +817,7 @@ async def test_completion_gemini_stream_accumulated_json(sync_mode):
},
}
]
messages = [{"role": "user", "content": "What is the weather like in Boston?"}]
messages = [{"role": "user", "content": "What is the weather like in Boston, MA?. You must provide me with a tool call in your response."}]
print("testing gemini streaming")
complete_response = ""
# Add any assertions here to check the response

82
tests/test_litellm/litellm_core_utils/test_streaming_chunk_builder_utils.py
View File

@ -243,3 +243,85 @@ def test_cache_read_input_tokens_retained():
assert usage.cache_creation_input_tokens == 4
assert usage.cache_read_input_tokens == 11775
assert usage.prompt_tokens_details.cached_tokens == 11775
def test_stream_chunk_builder_litellm_usage_chunks():
"""
Validate ChunkProcessor.calculate_usage uses provided usage fields from streaming chunks
and reconstructs prompt and completion tokens without making any upstream API calls.
"""
# Prepare two mocked streaming chunks with usage split across them
chunk1 = ModelResponseStream(
id="chatcmpl-mocked-usage-1",
created=1745513206,
model="gemini/gemini-2.5-flash-lite",
object="chat.completion.chunk",
system_fingerprint=None,
choices=[
StreamingChoices(
finish_reason=None,
index=0,
delta=Delta(
provider_specific_fields=None,
content="",
role=None,
function_call=None,
tool_calls=None,
audio=None,
),
logprobs=None,
)
],
provider_specific_fields=None,
stream_options={"include_usage": True},
usage=Usage(
completion_tokens=0,
prompt_tokens=50,
total_tokens=50,
completion_tokens_details=None,
prompt_tokens_details=None,
),
)
chunk2 = ModelResponseStream(
id="chatcmpl-mocked-usage-1",
created=1745513207,
model="gemini/gemini-2.5-flash-lite",
object="chat.completion.chunk",
system_fingerprint=None,
choices=[
StreamingChoices(
finish_reason="stop",
index=0,
delta=Delta(
provider_specific_fields=None,
content=None,
role=None,
function_call=None,
tool_calls=None,
audio=None,
),
logprobs=None,
)
],
provider_specific_fields=None,
stream_options={"include_usage": True},
usage=Usage(
completion_tokens=27,
prompt_tokens=0,
total_tokens=27,
completion_tokens_details=None,
prompt_tokens_details=None,
),
)
chunks = [chunk1, chunk2]
processor = ChunkProcessor(chunks=chunks)
usage = processor.calculate_usage(
chunks=chunks, model="gemini/gemini-2.5-flash-lite", completion_output=""
)
assert usage.prompt_tokens == 50
assert usage.completion_tokens == 27
assert usage.total_tokens == 77

40
tests/test_litellm/llms/openai/test_gpt5_transformation.py Normal file
View File

@ -0,0 +1,40 @@
import pytest
import litellm
from litellm.llms.openai.openai import OpenAIConfig
@pytest.fixture()
def config() -> OpenAIConfig:
return OpenAIConfig()
def test_gpt5_maps_max_tokens(config: OpenAIConfig):
params = config.map_openai_params(
non_default_params={"max_tokens": 10},
optional_params={},
model="gpt-5",
drop_params=False,
)
assert params["max_completion_tokens"] == 10
assert "max_tokens" not in params
def test_gpt5_temperature_drop(config: OpenAIConfig):
params = config.map_openai_params(
non_default_params={"temperature": 0.2},
optional_params={},
model="gpt-5",
drop_params=True,
)
assert "temperature" not in params
def test_gpt5_temperature_error(config: OpenAIConfig):
with pytest.raises(litellm.utils.UnsupportedParamsError):
config.map_openai_params(
non_default_params={"temperature": 0.2},
optional_params={},
model="gpt-5",
drop_params=False,
)

53
tests/test_litellm/proxy/management_endpoints/test_ui_sso.py
View File

@ -938,10 +938,10 @@ class TestUISSO_FunctionsExistence:
from litellm.proxy.management_endpoints.ui_sso import auth_callback
assert callable(auth_callback)
def test_sso_login_redirect_exists(self):
"""Test that sso_login_redirect function exists"""
from litellm.proxy.management_endpoints.ui_sso import sso_login_redirect
assert callable(sso_login_redirect)
def test_google_login_exists(self):
"""Test that google_login function exists"""
from litellm.proxy.management_endpoints.ui_sso import google_login
assert callable(google_login)
def test_sso_authentication_handler_exists(self):
"""Test that SSOAuthenticationHandler class exists with new methods"""
@ -1054,7 +1054,7 @@ class TestCustomUISSO:
"""Test that proper error is raised when enterprise module is not available"""
from unittest.mock import MagicMock, patch
from litellm.proxy.management_endpoints.ui_sso import sso_login_redirect
from litellm.proxy.management_endpoints.ui_sso import google_login
# Mock request
mock_request = MagicMock()
@ -1246,46 +1246,3 @@ class TestCustomUISSO:
assert result == mock_redirect_response
assert result.status_code == 303
@pytest.mark.asyncio
async def test_serve_login_page_server_root_path():
"""
Test that serve_login_page includes SERVER_ROOT_PATH in the SSO login URL
when SERVER_ROOT_PATH is set.
"""
# Arrange
mock_request = MagicMock(spec=Request)
captured_html = ""
# Mock environment variables
env_vars = {
"PROXY_BASE_URL": "https://example.com",
"SERVER_ROOT_PATH": "/api/v1",
"GOOGLE_CLIENT_ID": "mock_google_client_id", # Enable SSO
"DATABASE_URL": "mock_db_url", # Satisfy show_missing_vars_in_env
"LITELLM_MASTER_KEY": "mock_master_key", # Satisfy show_missing_vars_in_env
}
# Patch HTMLResponse to capture the content
def mock_html_response(content, status_code=200):
nonlocal captured_html
captured_html = content
return MagicMock()
with patch.dict(os.environ, env_vars):
with patch("litellm.proxy.proxy_server.premium_user", True):
with patch("litellm.proxy.proxy_server.prisma_client", MagicMock()):
with patch("litellm.proxy.proxy_server.master_key", "mock_master_key"):
with patch("fastapi.responses.HTMLResponse", side_effect=mock_html_response):
# Import the function to test
from litellm.proxy.management_endpoints.ui_sso import (
serve_login_page,
)
# Act
result = await serve_login_page(request=mock_request)
# Assert
assert result is not None
expected_url = "https://example.com/api/v1/sso/login"
assert expected_url in captured_html, f"Expected URL '{expected_url}' not found in HTML content"

31
tests/test_litellm/responses/litellm_completion_transformation/test_reasoning_content_transformation.py
View File

@ -253,3 +253,34 @@ class TestReasoningContentFinalResponse:
]
assert len(reasoning_items) == 1, "Should have exactly one reasoning item"
assert reasoning_items[0].content[0].text == "Reasoning for first answer"
def test_streaming_chunk_id_raw():
"""Test that streaming chunk IDs are raw (not encoded) to match OpenAI format"""
chunk = ModelResponseStream(
id="chunk-123",
created=1234567890,
model="test-model",
object="chat.completion.chunk",
choices=[
StreamingChoices(
finish_reason=None,
index=0,
delta=Delta(content="Hello", role="assistant"),
)
],
)
iterator = LiteLLMCompletionStreamingIterator(
litellm_custom_stream_wrapper=AsyncMock(),
request_input="Test input",
responses_api_request={},
custom_llm_provider="openai",
litellm_metadata={"model_info": {"id": "gpt-4"}},
)
result = iterator._transform_chat_completion_chunk_to_response_api_chunk(chunk)
# Streaming chunk IDs should be raw (like OpenAI's msg_xxx format)
assert result.item_id == "chunk-123" # Should be raw, not encoded
assert not result.item_id.startswith("resp_") # Should NOT have resp_ prefix

6
tests/test_litellm/test_utils.py
View File

@ -844,6 +844,7 @@ async def test_supports_tool_choice():
or "o1" in model_name
or "o3" in model_name
or "mistral" in model_name
or "oci" in model_name
):
continue
@ -2317,8 +2318,9 @@ def test_block_key_hashing_logic():
Test that block_key() function only hashes keys that start with "sk-"
"""
import hashlib
from litellm.proxy.utils import hash_token
# Test cases: (input_key, should_be_hashed, expected_output)
test_cases = [
("sk-1234567890abcdef", True, hash_token("sk-1234567890abcdef")),
@ -2394,7 +2396,7 @@ def test_generate_gcp_iam_access_token_import_error():
"""
# Import the function first, before mocking
from litellm._redis import _generate_gcp_iam_access_token
# Mock the import to fail when the function tries to import google.cloud.iam_credentials_v1
original_import = __builtins__['__import__']

2
ui/litellm-dashboard/out/404.html
View File

File diff suppressed because one or more lines are too long

1
ui/litellm-dashboard/out/_next/static/chunks/154-66d79df6143c694f.js Normal file
View File

File diff suppressed because one or more lines are too long

1
ui/litellm-dashboard/out/_next/static/chunks/154-78c3416dcb61977f.js
View File

File diff suppressed because one or more lines are too long

1
ui/litellm-dashboard/out/_next/static/chunks/162-8529572226f208c5.js
View File

File diff suppressed because one or more lines are too long

1
ui/litellm-dashboard/out/_next/static/chunks/162-9e6f5133e328d61f.js Normal file
View File

File diff suppressed because one or more lines are too long

0
ui/litellm-dashboard/out/_next/static/chunks/172-08ae62d50ce1f0e7.js → ui/litellm-dashboard/out/_next/static/chunks/172-1c7afccd96ceca39.js
View File

12
ui/litellm-dashboard/out/_next/static/chunks/498-ee02f9b58491d7a9.js
View File

File diff suppressed because one or more lines are too long

12
ui/litellm-dashboard/out/_next/static/chunks/683-07087d813e7eeb43.js Normal file
View File

File diff suppressed because one or more lines are too long

2
litellm/proxy/_experimental/out/_next/static/chunks/866-9e1803a09e9ae8da.js → ui/litellm-dashboard/out/_next/static/chunks/866-3523e0e07cf314f6.js
View File

File diff suppressed because one or more lines are too long

0
ui/litellm-dashboard/out/_next/static/chunks/app/onboarding/page-883c32e6b072b842.js → ui/litellm-dashboard/out/_next/static/chunks/app/onboarding/page-7e4cd2bb92dbf9ce.js
View File

1
ui/litellm-dashboard/out/_next/static/chunks/app/page-0a9a9f137522a76c.js
View File

File diff suppressed because one or more lines are too long

1
ui/litellm-dashboard/out/_next/static/chunks/app/page-1d51309983956823.js Normal file
View File

File diff suppressed because one or more lines are too long

3
ui/litellm-dashboard/out/_next/static/css/0dbff0867726409d.css Normal file
View File

File diff suppressed because one or more lines are too long

3
ui/litellm-dashboard/out/_next/static/css/fe37e928fd602d9e.css
View File

File diff suppressed because one or more lines are too long

0
ui/litellm-dashboard/out/_next/static/rkJYRcYqQ8OBbL83KQCc4/_buildManifest.js → ui/litellm-dashboard/out/_next/static/poVnZDt3J0aYERGVwpJKO/_buildManifest.js
View File

0
ui/litellm-dashboard/out/_next/static/rkJYRcYqQ8OBbL83KQCc4/_ssgManifest.js → ui/litellm-dashboard/out/_next/static/poVnZDt3J0aYERGVwpJKO/_ssgManifest.js
View File

2
ui/litellm-dashboard/out/index.html
View File

File diff suppressed because one or more lines are too long

4
ui/litellm-dashboard/out/index.txt
View File

@ -1,7 +1,7 @@
2:I[19107,[],"ClientPageRoot"]
3:I[19813,["665","static/chunks/3014691f-b7b79b78e27792f3.js","990","static/chunks/13b76428-ebdf3012af0e4489.js","416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","866","static/chunks/866-9e1803a09e9ae8da.js","498","static/chunks/498-ee02f9b58491d7a9.js","154","static/chunks/154-78c3416dcb61977f.js","162","static/chunks/162-8529572226f208c5.js","172","static/chunks/172-08ae62d50ce1f0e7.js","931","static/chunks/app/page-0a9a9f137522a76c.js"],"default",1]
3:I[6691,["665","static/chunks/3014691f-b7b79b78e27792f3.js","990","static/chunks/13b76428-ebdf3012af0e4489.js","416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","866","static/chunks/866-3523e0e07cf314f6.js","683","static/chunks/683-07087d813e7eeb43.js","154","static/chunks/154-66d79df6143c694f.js","162","static/chunks/162-9e6f5133e328d61f.js","172","static/chunks/172-1c7afccd96ceca39.js","931","static/chunks/app/page-1d51309983956823.js"],"default",1]
4:I[4707,[],""]
5:I[36423,[],""]
0:["rkJYRcYqQ8OBbL83KQCc4",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/fe37e928fd602d9e.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
0:["poVnZDt3J0aYERGVwpJKO",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/0dbff0867726409d.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
1:null

2
ui/litellm-dashboard/out/model_hub.html
View File

File diff suppressed because one or more lines are too long

4
ui/litellm-dashboard/out/model_hub.txt
View File

@ -1,7 +1,7 @@
2:I[19107,[],"ClientPageRoot"]
3:I[52829,["416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","154","static/chunks/154-78c3416dcb61977f.js","162","static/chunks/162-8529572226f208c5.js","418","static/chunks/app/model_hub/page-b26e0d313b582dbf.js"],"default",1]
3:I[52829,["416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","154","static/chunks/154-66d79df6143c694f.js","162","static/chunks/162-9e6f5133e328d61f.js","418","static/chunks/app/model_hub/page-b26e0d313b582dbf.js"],"default",1]
4:I[4707,[],""]
5:I[36423,[],""]
0:["rkJYRcYqQ8OBbL83KQCc4",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/fe37e928fd602d9e.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
0:["poVnZDt3J0aYERGVwpJKO",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/0dbff0867726409d.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
1:null

2
ui/litellm-dashboard/out/model_hub_table.html
View File

File diff suppressed because one or more lines are too long

4
ui/litellm-dashboard/out/model_hub_table.txt
View File

@ -1,7 +1,7 @@
2:I[19107,[],"ClientPageRoot"]
3:I[22775,["416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","866","static/chunks/866-9e1803a09e9ae8da.js","154","static/chunks/154-78c3416dcb61977f.js","162","static/chunks/162-8529572226f208c5.js","172","static/chunks/172-08ae62d50ce1f0e7.js","25","static/chunks/app/model_hub_table/page-d080c5775ebaf3a1.js"],"default",1]
3:I[22775,["416","static/chunks/416-ad6bd55a20a586bd.js","90","static/chunks/90-d2b5ed6f7f6e342e.js","866","static/chunks/866-3523e0e07cf314f6.js","154","static/chunks/154-66d79df6143c694f.js","162","static/chunks/162-9e6f5133e328d61f.js","172","static/chunks/172-1c7afccd96ceca39.js","25","static/chunks/app/model_hub_table/page-d080c5775ebaf3a1.js"],"default",1]
4:I[4707,[],""]
5:I[36423,[],""]
0:["rkJYRcYqQ8OBbL83KQCc4",[[["",{"children":["model_hub_table",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub_table",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub_table","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/fe37e928fd602d9e.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
0:["poVnZDt3J0aYERGVwpJKO",[[["",{"children":["model_hub_table",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub_table",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub_table","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/0dbff0867726409d.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
1:null

2
ui/litellm-dashboard/out/onboarding.html
View File

File diff suppressed because one or more lines are too long

4
ui/litellm-dashboard/out/onboarding.txt
View File

@ -1,7 +1,7 @@
2:I[19107,[],"ClientPageRoot"]
3:I[12011,["665","static/chunks/3014691f-b7b79b78e27792f3.js","416","static/chunks/416-ad6bd55a20a586bd.js","154","static/chunks/154-78c3416dcb61977f.js","461","static/chunks/app/onboarding/page-883c32e6b072b842.js"],"default",1]
3:I[12011,["665","static/chunks/3014691f-b7b79b78e27792f3.js","416","static/chunks/416-ad6bd55a20a586bd.js","154","static/chunks/154-66d79df6143c694f.js","461","static/chunks/app/onboarding/page-7e4cd2bb92dbf9ce.js"],"default",1]
4:I[4707,[],""]
5:I[36423,[],""]
0:["rkJYRcYqQ8OBbL83KQCc4",[[["",{"children":["onboarding",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["onboarding",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","onboarding","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/fe37e928fd602d9e.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
0:["poVnZDt3J0aYERGVwpJKO",[[["",{"children":["onboarding",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["onboarding",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","onboarding","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/0dbff0867726409d.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
1:null

52
ui/litellm-dashboard/src/components/add_model/conditional_public_model_name.tsx
View File

@ -1,12 +1,11 @@
import React, { useEffect, useState } from "react";
import { Form, Table, Input } from "antd";
import { Text, TextInput } from "@tremor/react";
import { Row, Col } from "antd";
import { Form, Table } from "antd";
import { TextInput } from "@tremor/react";
import { Tooltip } from "../atoms/index";
const ConditionalPublicModelName: React.FC = () => {
// Access the form instance
const form = Form.useFormInstance();
const [tableKey, setTableKey] = useState(0); // Add a key to force table re-render
const [tableKey, setTableKey] = useState(0);// Add a key to force table re-render
// Watch the 'model' field for changes and ensure it's always an array
const modelValue = Form.useWatch('model', form) || [];
@ -14,7 +13,6 @@ const ConditionalPublicModelName: React.FC = () => {
const customModelName = Form.useWatch('custom_model_name', form);
const showPublicModelName = !selectedModels.includes('all-wildcard');
// Force table to re-render when custom model name changes
useEffect(() => {
if (customModelName && selectedModels.includes('custom')) {
@ -71,9 +69,39 @@ const ConditionalPublicModelName: React.FC = () => {
if (!showPublicModelName) return null;
const publicNameTooltipContent = (
<>
<div className="mb-2 font-normal">
The name you specify in your API calls to LiteLLM Proxy
</div>
<div className="mb-2 font-normal">
<strong>Example:</strong> If you name your public model <code className="bg-gray-700 px-1 py-0.5 rounded text-xs">example-name</code>
, and choose <code className="bg-gray-700 px-1 py-0.5 rounded text-xs">openai/qwen-plus-latest</code> as the LiteLLM model
</div>
<div className="mb-2 font-normal">
<strong>Usage:</strong> You make an API call to the LiteLLM proxy with <code className="bg-gray-700 px-1 py-0.5 rounded text-xs">model = &quot;example-name&quot;</code>
</div>
<div className="font-normal">
<strong>Result:</strong> LiteLLM sends <code className="bg-gray-700 px-1 py-0.5 rounded text-xs">qwen-plus-latest</code> to the provider
</div>
</>
);
const liteLLMModelTooltipContent = (
<div>The model name LiteLLM will send to the LLM API</div>
);
const columns = [
{
title: 'Public Name',
title: (
<span className="flex items-center">
Public Model Name
<Tooltip
content={publicNameTooltipContent}
width="500px"
/>
</span>
),
dataIndex: 'public_name',
key: 'public_name',
render: (text: string, record: any, index: number) => {
@ -90,7 +118,15 @@ const ConditionalPublicModelName: React.FC = () => {
}
},
{
title: 'LiteLLM Model',
title: (
<span className="flex items-center">
LiteLLM Model Name
<Tooltip
content={liteLLMModelTooltipContent}
width="360px"
/>
</span>
),
dataIndex: 'litellm_model',
key: 'litellm_model',
}

6
ui/litellm-dashboard/src/components/add_model/litellm_model_name.tsx
View File

@ -70,7 +70,7 @@ const LiteLLMModelNameField: React.FC<LiteLLMModelNameFieldProps> = ({
<>
<Form.Item
label="LiteLLM Model Name(s)"
tooltip="Actual model name used for making litellm.completion() / litellm.embedding() call."
tooltip="The model name LiteLLM will send to the LLM API"
className="mb-0"
>
<Form.Item
@ -145,9 +145,9 @@ const LiteLLMModelNameField: React.FC<LiteLLMModelNameFieldProps> = ({
</Form.Item>
<Row>
<Col span={10}></Col>
<Col span={10}>
<Col span={14}>
<Text className="mb-3 mt-1">
Actual model name used for making litellm.completion() call. We loadbalance models with the same public name
The model name LiteLLM will send to the LLM API
</Text>
</Col>
</Row>

70
ui/litellm-dashboard/src/components/atoms/Tooltip.tsx Normal file
View File

@ -0,0 +1,70 @@
import React, { useState, useRef } from "react"
import { QuestionCircleOutlined } from "@ant-design/icons"
interface TooltipProps {
content: React.ReactNode
children?: React.ReactNode
width?: string
className?: string
}
export const Tooltip: React.FC<TooltipProps> = ({ content, children, width = "auto", className = "" }) => {
const [showTooltip, setShowTooltip] = useState(false)
const [tooltipPosition, setTooltipPosition] = useState<"top" | "bottom">("top")
const tooltipRef = useRef<HTMLDivElement>(null)
// Function to check if tooltip would fit above
const checkTooltipPosition = () => {
if (tooltipRef.current) {
const rect = tooltipRef.current.getBoundingClientRect()
const tooltipHeight = 300 // Approximate height of the tooltip
const spaceAbove = rect.top
const spaceBelow = window.innerHeight - rect.bottom
if (spaceAbove < tooltipHeight && spaceBelow > tooltipHeight) {
setTooltipPosition("bottom")
} else {
setTooltipPosition("top")
}
}
}
return (
<div className="relative inline-block" ref={tooltipRef}>
{children || (
<QuestionCircleOutlined
className="ml-1 text-gray-500 cursor-help"
onMouseEnter={() => {
checkTooltipPosition()
setShowTooltip(true)
}}
onMouseLeave={() => setShowTooltip(false)}
/>
)}
{showTooltip && (
<div
className={`absolute left-1/2 -translate-x-1/2 z-50 bg-black/90 text-white p-2 rounded-md text-sm font-normal shadow-lg ${className}`}
style={{
[tooltipPosition === "top" ? "bottom" : "top"]: "100%",
width: width,
marginBottom: tooltipPosition === "top" ? "8px" : "0",
marginTop: tooltipPosition === "bottom" ? "8px" : "0",
}}
>
{content}
<div
className="absolute left-1/2 -translate-x-1/2 w-0 h-0"
style={{
top: tooltipPosition === "top" ? "100%" : "auto",
bottom: tooltipPosition === "bottom" ? "100%" : "auto",
borderTop: tooltipPosition === "top" ? "6px solid rgba(0, 0, 0, 0.9)" : "6px solid transparent",
borderBottom: tooltipPosition === "bottom" ? "6px solid rgba(0, 0, 0, 0.9)" : "6px solid transparent",
borderLeft: "6px solid transparent",
borderRight: "6px solid transparent",
}}
/>
</div>
)}
</div>
)
}

1
ui/litellm-dashboard/src/components/atoms/index.ts Normal file
View File

@ -0,0 +1 @@
export { Tooltip } from './Tooltip';

77
ui/litellm-dashboard/src/components/networking.tsx
View File

@ -1,3 +1,10 @@
// Shared date formatter for daily activity endpoints
export const formatDate = (date: Date) => {
const year = date.getFullYear();
const month = String(date.getMonth() + 1).padStart(2, '0');
const day = String(date.getDate()).padStart(2, '0');
return `${year}-${month}-${day}`;
};
/**
* Helper file for calls being made to proxy
*/
@ -1457,13 +1464,6 @@ export const userDailyActivityCall = async (
? `${proxyBaseUrl}/user/daily/activity`
: `/user/daily/activity`;
const queryParams = new URLSearchParams();
// Format dates as YYYY-MM-DD for the API
const formatDate = (date: Date) => {
const year = date.getFullYear();
const month = String(date.getMonth() + 1).padStart(2, '0');
const day = String(date.getDate()).padStart(2, '0');
return `${year}-${month}-${day}`;
};
queryParams.append("start_date", formatDate(startTime));
queryParams.append("end_date", formatDate(endTime));
queryParams.append("page_size", "1000");
@ -1510,13 +1510,6 @@ export const tagDailyActivityCall = async (
? `${proxyBaseUrl}/tag/daily/activity`
: `/tag/daily/activity`;
const queryParams = new URLSearchParams();
// Format dates as YYYY-MM-DD for the API
const formatDate = (date: Date) => {
const year = date.getFullYear();
const month = String(date.getMonth() + 1).padStart(2, '0');
const day = String(date.getDate()).padStart(2, '0');
return `${year}-${month}-${day}`;
};
queryParams.append("start_date", formatDate(startTime));
queryParams.append("end_date", formatDate(endTime));
queryParams.append("page_size", "1000");
@ -1566,13 +1559,6 @@ export const teamDailyActivityCall = async (
? `${proxyBaseUrl}/team/daily/activity`
: `/team/daily/activity`;
const queryParams = new URLSearchParams();
// Format dates as YYYY-MM-DD for the API
const formatDate = (date: Date) => {
const year = date.getFullYear();
const month = String(date.getMonth() + 1).padStart(2, '0');
const day = String(date.getDate()).padStart(2, '0');
return `${year}-${month}-${day}`;
};
queryParams.append("start_date", formatDate(startTime));
queryParams.append("end_date", formatDate(endTime));
queryParams.append("page_size", "1000");
@ -3198,6 +3184,55 @@ export interface User {
[key: string]: string; // Include any other potential keys in the dictionary
}
export const userDailyActivityAggregatedCall = async (
accessToken: String,
startTime: Date,
endTime: Date
) => {
/**
* Get aggregated daily user activity (no pagination)
*/
try {
let url = proxyBaseUrl
? `${proxyBaseUrl}/user/daily/activity/aggregated`
: `/user/daily/activity/aggregated`;
const queryParams = new URLSearchParams();
// Format dates as YYYY-MM-DD for the API
const formatDate = (date: Date) => {
const year = date.getFullYear();
const month = String(date.getMonth() + 1).padStart(2, '0');
const day = String(date.getDate()).padStart(2, '0');
return `${year}-${month}-${day}`;
};
queryParams.append("start_date", formatDate(startTime));
queryParams.append("end_date", formatDate(endTime));
const queryString = queryParams.toString();
if (queryString) {
url += `?${queryString}`;
}
const response = await fetch(url, {
method: "GET",
headers: {
[globalLitellmHeaderName]: `Bearer ${accessToken}`,
"Content-Type": "application/json",
},
});
if (!response.ok) {
const errorData = await response.text();
handleError(errorData);
throw new Error("Network response was not ok");
}
const data = await response.json();
return data;
} catch (error) {
console.error("Failed to fetch aggregated user daily activity:", error);
throw error;
}
};
export const userGetAllUsersCall = async (
accessToken: String,
role: String

15
ui/litellm-dashboard/src/components/new_usage.tsx
View File

@ -34,7 +34,7 @@ import {
import AdvancedDatePicker from "./shared/advanced_date_picker"
import { AreaChart } from "@tremor/react"
import { userDailyActivityCall, tagListCall } from "./networking"
import { userDailyActivityCall, userDailyActivityAggregatedCall, tagListCall } from "./networking"
import { Tag } from "./tag_management/types"
import ViewUserSpend from "./view_user_spend"
import TopKeyView from "./top_key_view"
@ -304,16 +304,22 @@ const NewUsagePage: React.FC<NewUsagePageProps> = ({ accessToken, userRole, user
const endTime = new Date(dateValue.to)
try {
// Get first page
// Prefer aggregated endpoint to avoid many page requests
try {
const aggregated = await userDailyActivityAggregatedCall(accessToken, startTime, endTime)
setUserSpendData(aggregated)
return
} catch (e) {
// Fallback to paginated calls if aggregated endpoint is unavailable
}
const firstPageData = await userDailyActivityCall(accessToken, startTime, endTime)
// If only one page, just set the data
if (firstPageData.metadata.total_pages <= 1) {
setUserSpendData(firstPageData)
return
}
// Fetch all pages
const allResults = [...firstPageData.results]
const aggregatedMetadata = { ...firstPageData.metadata }
@ -329,7 +335,6 @@ const NewUsagePage: React.FC<NewUsagePageProps> = ({ accessToken, userRole, user
}
}
// Combine all results with the first page's metadata
setUserSpendData({
results: allResults,
metadata: aggregatedMetadata,