scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

add DD Tracing

Browse source
This commit is contained in:
Ishaan Jaffer 2026-03-18 10:50:51 -07:00
parent 27f78084dc
commit 4032af34c9
3 changed files with 228 additions and 590 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

483
litellm/model_prices_and_context_window_backup.json
View file

@ -8535,227 +8535,6 @@
}
]
},
"dashscope/qwen3-max": {
"litellm_provider": "dashscope",
"max_input_tokens": 258048,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"source": "https://www.alibabacloud.com/help/en/model-studio/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"tiered_pricing": [
{
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 6e-06,
"range": [
0,
32000.0
]
},
{
"input_cost_per_token": 2.4e-06,
"output_cost_per_token": 1.2e-05,
"range": [
32000.0,
128000.0
]
},
{
"input_cost_per_token": 3e-06,
"output_cost_per_token": 1.5e-05,
"range": [
128000.0,
252000.0
]
}
]
},
"dashscope/qwen3-max-2026-01-23": {
"litellm_provider": "dashscope",
"max_input_tokens": 258048,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"source": "https://www.alibabacloud.com/help/en/model-studio/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"tiered_pricing": [
{
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 6e-06,
"range": [
0,
32000.0
]
},
{
"input_cost_per_token": 2.4e-06,
"output_cost_per_token": 1.2e-05,
"range": [
32000.0,
128000.0
]
},
{
"input_cost_per_token": 3e-06,
"output_cost_per_token": 1.5e-05,
"range": [
128000.0,
252000.0
]
}
]
},
"dashscope/qwen3-next-80b-a3b-instruct": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "dashscope",
"max_input_tokens": 262144,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
"supports_function_calling": true,
"supports_tool_choice": true
},
"dashscope/qwen3-next-80b-a3b-thinking": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "dashscope",
"max_input_tokens": 262144,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"dashscope/qwen3-vl-235b-a22b-instruct": {
"input_cost_per_token": 4e-07,
"litellm_provider": "dashscope",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.6e-06,
"source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
},
"dashscope/qwen3-vl-235b-a22b-thinking": {
"input_cost_per_token": 4e-07,
"litellm_provider": "dashscope",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"dashscope/qwen3-vl-32b-instruct": {
"input_cost_per_token": 1.6e-07,
"litellm_provider": "dashscope",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6.4e-07,
"source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
},
"dashscope/qwen3-vl-32b-thinking": {
"input_cost_per_token": 1.6e-07,
"litellm_provider": "dashscope",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 2.87e-06,
"source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"dashscope/qwen3-vl-plus": {
"litellm_provider": "dashscope",
"max_input_tokens": 260096,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"source": "https://www.alibabacloud.com/help/en/model-studio/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"tiered_pricing": [
{
"input_cost_per_token": 2e-07,
"output_cost_per_token": 1.6e-06,
"range": [
0,
32000.0
]
},
{
"input_cost_per_token": 3e-07,
"output_cost_per_token": 2.4e-06,
"range": [
32000.0,
128000.0
]
},
{
"input_cost_per_token": 6e-07,
"output_cost_per_token": 4.8e-06,
"range": [
128000.0,
256000.0
]
}
]
},
"dashscope/qwen3.5-plus": {
"litellm_provider": "dashscope",
"max_input_tokens": 991808,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"source": "https://www.alibabacloud.com/help/en/model-studio/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"tiered_pricing": [
{
"input_cost_per_token": 4e-07,
"output_cost_per_token": 2.4e-06,
"range": [
0,
256000.0
]
},
{
"input_cost_per_token": 5e-07,
"output_cost_per_token": 3e-06,
"range": [
256000.0,
1000000.0
]
}
]
},
"dashscope/qwq-plus": {
"input_cost_per_token": 8e-07,
"litellm_provider": "dashscope",
@ -23372,59 +23151,14 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 159
},
"openrouter/anthropic/claude-sonnet-4.6": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_read_input_token_cost": 3e-07,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
"source": "https://openrouter.ai/anthropic/claude-sonnet-4.6",
"supports_assistant_prefill": true,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 159
},
"openrouter/anthropic/claude-opus-4.5": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 5e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
"source": "https://openrouter.ai/anthropic/claude-sonnet-4.6",
"supports_assistant_prefill": true,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 159
},
"openrouter/anthropic/claude-opus-4.6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 5e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"max_input_tokens": 200000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"supports_assistant_prefill": true,
@ -23434,7 +23168,7 @@
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 346
"tool_use_system_prompt_tokens": 159
},
"openrouter/anthropic/claude-sonnet-4.5": {
"input_cost_per_image": 0.0048,
@ -23791,39 +23525,46 @@
"supports_web_search": true,
"tpm": 800000
},
"openrouter/google/gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"openrouter/google/gemini-pro-1.5": {
"input_cost_per_image": 0.00265,
"input_cost_per_token": 2.5e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"max_input_tokens": 1000000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-05,
"source": "https://openrouter.ai/google/gemini-3.1-pro-preview",
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"output_cost_per_token": 7.5e-06,
"supports_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
},
"openrouter/google/gemini-pro-vision": {
"input_cost_per_image": 0.0025,
"input_cost_per_token": 1.25e-07,
"litellm_provider": "openrouter",
"max_tokens": 45875,
"mode": "chat",
"output_cost_per_token": 3.75e-07,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
},
"openrouter/google/palm-2-chat-bison": {
"input_cost_per_token": 5e-07,
"litellm_provider": "openrouter",
"max_tokens": 25804,
"mode": "chat",
"output_cost_per_token": 5e-07,
"supports_tool_choice": true
},
"openrouter/google/palm-2-codechat-bison": {
"input_cost_per_token": 5e-07,
"litellm_provider": "openrouter",
"max_tokens": 20070,
"mode": "chat",
"output_cost_per_token": 5e-07,
"supports_tool_choice": true
},
"openrouter/gryphe/mythomax-l2-13b": {
"input_cost_per_token": 1.875e-06,
"litellm_provider": "openrouter",
@ -24359,29 +24100,6 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"openrouter/openai/gpt-5.1-codex-max": {
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1e-05,
"source": "https://openrouter.ai/openai/gpt-5.1-codex-max",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"openrouter/openai/gpt-5.2": {
"input_cost_per_image": 0,
"cache_read_input_token_cost": 1.75e-07,
@ -24596,44 +24314,6 @@
"supports_tool_choice": true,
"supports_function_calling": true
},
"openrouter/qwen/qwen3-coder-plus": {
"input_cost_per_token": 1e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 997952,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 5e-06,
"source": "https://openrouter.ai/qwen/qwen3-coder-plus",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"openrouter/qwen/qwen3-235b-a22b-2507": {
"input_cost_per_token": 7.1e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507",
"supports_function_calling": true,
"supports_tool_choice": true
},
"openrouter/qwen/qwen3-235b-a22b-thinking-2507": {
"input_cost_per_token": 1.1e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 6e-07,
"source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"openrouter/switchpoint/router": {
"input_cost_per_token": 8.5e-07,
"litellm_provider": "openrouter",
@ -24710,21 +24390,21 @@
"supports_tool_choice": true
},
"openrouter/xiaomi/mimo-v2-flash": {
"input_cost_per_token": 9e-08,
"output_cost_per_token": 2.9e-07,
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 0.0,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_vision": false,
"supports_prompt_caching": false
},
"input_cost_per_token": 9e-08,
"output_cost_per_token": 2.9e-07,
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 0.0,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_vision": false,
"supports_prompt_caching": false
},
"openrouter/z-ai/glm-4.7": {
"input_cost_per_token": 4e-07,
"output_cost_per_token": 1.5e-06,
@ -24758,19 +24438,6 @@
"supports_vision": true,
"supports_prompt_caching": false
},
"openrouter/z-ai/glm-5": {
"input_cost_per_token": 8e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 202752,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.56e-06,
"source": "https://openrouter.ai/z-ai/glm-5",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"openrouter/minimax/minimax-m2.1": {
"input_cost_per_token": 2.7e-07,
"output_cost_per_token": 1.2e-06,
@ -31413,50 +31080,6 @@
"supports_vision": true,
"supports_web_search": true
},
"zai.glm-4.7": {
"input_cost_per_token": 6e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"zai/glm-5": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 1e-06,
"output_cost_per_token": 3.2e-06,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5-code": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 5e-06,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.7": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 1.1e-07,

106
litellm/proxy/auth/auth_checks.py
View file

@ -28,6 +28,7 @@ from litellm.constants import (
DEFAULT_MAX_RECURSE_DEPTH,
EMAIL_BUDGET_ALERT_MAX_SPEND_ALERT_PERCENTAGE,
)
from litellm.litellm_core_utils.dd_tracing import tracer
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
from litellm.proxy._types import (
RBAC_ROLES,
@ -118,50 +119,55 @@ async def common_checks(
# 2. If team can call model
if _model and team_object:
if not can_team_access_model(
model=_model,
team_object=team_object,
llm_router=llm_router,
team_model_aliases=valid_token.team_model_aliases if valid_token else None,
):
raise ProxyException(
message=f"Team not allowed to access model. Team={team_object.team_id}, Model={_model}. Allowed team models = {team_object.models}",
type=ProxyErrorTypes.team_model_access_denied,
param="model",
code=status.HTTP_401_UNAUTHORIZED,
)
with tracer.trace("litellm.proxy.auth.common_checks.can_team_access_model"):
if not can_team_access_model(
model=_model,
team_object=team_object,
llm_router=llm_router,
team_model_aliases=valid_token.team_model_aliases if valid_token else None,
):
raise ProxyException(
message=f"Team not allowed to access model. Team={team_object.team_id}, Model={_model}. Allowed team models = {team_object.models}",
type=ProxyErrorTypes.team_model_access_denied,
param="model",
code=status.HTTP_401_UNAUTHORIZED,
)
## 2.1 If user can call model (if personal key)
if _model and team_object is None and user_object is not None:
await can_user_call_model(
model=_model,
llm_router=llm_router,
user_object=user_object,
)
with tracer.trace("litellm.proxy.auth.common_checks.can_user_call_model"):
await can_user_call_model(
model=_model,
llm_router=llm_router,
user_object=user_object,
)
# 3. If team is in budget
await _team_max_budget_check(
team_object=team_object,
proxy_logging_obj=proxy_logging_obj,
valid_token=valid_token,
)
with tracer.trace("litellm.proxy.auth.common_checks.team_max_budget_check"):
await _team_max_budget_check(
team_object=team_object,
proxy_logging_obj=proxy_logging_obj,
valid_token=valid_token,
)
# 3.1. If organization is in budget
await _organization_max_budget_check(
valid_token=valid_token,
team_object=team_object,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
)
with tracer.trace("litellm.proxy.auth.common_checks.organization_max_budget_check"):
await _organization_max_budget_check(
valid_token=valid_token,
team_object=team_object,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
)
await _tag_max_budget_check(
request_body=request_body,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
valid_token=valid_token,
)
with tracer.trace("litellm.proxy.auth.common_checks.tag_max_budget_check"):
await _tag_max_budget_check(
request_body=request_body,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
valid_token=valid_token,
)
# 4. If user is in budget
## 4.1 check personal budget, if personal key
@ -179,14 +185,15 @@ async def common_checks(
)
## 4.2 check team member budget, if team key
await _check_team_member_budget(
team_object=team_object,
user_object=user_object,
valid_token=valid_token,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
)
with tracer.trace("litellm.proxy.auth.common_checks.check_team_member_budget"):
await _check_team_member_budget(
team_object=team_object,
user_object=user_object,
valid_token=valid_token,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
)
# 5. If end_user ('user' passed to /chat/completions, /embeddings endpoint) is in budget
if end_user_object is not None and end_user_object.litellm_budget_table is not None:
@ -294,11 +301,12 @@ async def common_checks(
)
# 11. [OPTIONAL] Vector store checks - is the object allowed to access the vector store
await vector_store_access_check(
request_body=request_body,
team_object=team_object,
valid_token=valid_token,
)
with tracer.trace("litellm.proxy.auth.common_checks.vector_store_access_check"):
await vector_store_access_check(
request_body=request_body,
team_object=team_object,
valid_token=valid_token,
)
return True

229
litellm/proxy/auth/user_api_key_auth.py
View file

@ -419,13 +419,12 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
custom_auth_api_key: bool = False
try:
# get the request body
await pre_db_read_auth_checks(
request_data=request_data,
request=request,
route=route,
)
with tracer.trace("litellm.proxy.auth.pre_db_read_auth_checks"):
await pre_db_read_auth_checks(
request_data=request_data,
request=request,
route=route,
)
pass_through_endpoints: Optional[List[dict]] = general_settings.get(
"pass_through_endpoints", None
)
@ -459,9 +458,10 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
### USER-DEFINED AUTH FUNCTION ###
if enterprise_custom_auth is not None:
response = await enterprise_custom_auth(
request=request, api_key=api_key, user_custom_auth=user_custom_auth
)
with tracer.trace("litellm.proxy.auth.enterprise_custom_auth"):
response = await enterprise_custom_auth(
request=request, api_key=api_key, user_custom_auth=user_custom_auth
)
if response is not None and isinstance(response, UserAPIKeyAuth):
return UserAPIKeyAuth.model_validate(response)
elif response is not None and isinstance(response, str):
@ -522,18 +522,19 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
is_jwt = jwt_handler.is_jwt(token=api_key)
verbose_proxy_logger.debug("is_jwt: %s", is_jwt)
if is_jwt:
result = await JWTAuthManager.auth_builder(
request_data=request_data,
general_settings=general_settings,
api_key=api_key,
jwt_handler=jwt_handler,
route=route,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
parent_otel_span=parent_otel_span,
request_headers=dict(request.headers),
)
with tracer.trace("litellm.proxy.auth.jwt_auth_builder"):
result = await JWTAuthManager.auth_builder(
request_data=request_data,
general_settings=general_settings,
api_key=api_key,
jwt_handler=jwt_handler,
route=route,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
parent_otel_span=parent_otel_span,
request_headers=dict(request.headers),
)
is_proxy_admin = result["is_proxy_admin"]
team_id = result["team_id"]
@ -605,19 +606,20 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
else None,
)
# run through common checks
_ = await common_checks(
request=request,
request_body=request_data,
team_object=team_object,
user_object=user_object,
end_user_object=end_user_object,
general_settings=general_settings,
global_proxy_spend=global_proxy_spend,
route=route,
llm_router=llm_router,
proxy_logging_obj=proxy_logging_obj,
valid_token=valid_token,
)
with tracer.trace("litellm.proxy.auth.common_checks"):
_ = await common_checks(
request=request,
request_body=request_data,
team_object=team_object,
user_object=user_object,
end_user_object=end_user_object,
general_settings=general_settings,
global_proxy_spend=global_proxy_spend,
route=route,
llm_router=llm_router,
proxy_logging_obj=proxy_logging_obj,
valid_token=valid_token,
)
# return UserAPIKeyAuth object
return cast(UserAPIKeyAuth, valid_token)
@ -675,15 +677,15 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
try:
end_user_params["end_user_id"] = end_user_id
# get end-user object
_end_user_object = await get_end_user_object(
end_user_id=end_user_id,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
parent_otel_span=parent_otel_span,
proxy_logging_obj=proxy_logging_obj,
route=route,
)
with tracer.trace("litellm.proxy.auth.get_end_user_object"):
_end_user_object = await get_end_user_object(
end_user_id=end_user_id,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
parent_otel_span=parent_otel_span,
proxy_logging_obj=proxy_logging_obj,
route=route,
)
if _end_user_object is not None:
end_user_params[
"allowed_model_region"
@ -725,14 +727,15 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
# note: never string compare api keys, this is vulenerable to a time attack. Use secrets.compare_digest instead
## Check CACHE
try:
valid_token = await get_key_object(
hashed_token=hash_token(api_key),
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
parent_otel_span=parent_otel_span,
proxy_logging_obj=proxy_logging_obj,
check_cache_only=True,
)
with tracer.trace("litellm.proxy.auth.get_key_object_check_cache"):
valid_token = await get_key_object(
hashed_token=hash_token(api_key),
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
parent_otel_span=parent_otel_span,
proxy_logging_obj=proxy_logging_obj,
check_cache_only=True,
)
except Exception:
verbose_logger.debug("api key not found in cache.")
valid_token = None
@ -992,14 +995,15 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
# Check 2. If user_id for this token is in budget - done in common_checks()
if valid_token.user_id is not None:
try:
user_obj = await get_user_object(
user_id=valid_token.user_id,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
user_id_upsert=False,
parent_otel_span=parent_otel_span,
proxy_logging_obj=proxy_logging_obj,
)
with tracer.trace("litellm.proxy.auth.get_user_object"):
user_obj = await get_user_object(
user_id=valid_token.user_id,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
user_id_upsert=False,
parent_otel_span=parent_otel_span,
proxy_logging_obj=proxy_logging_obj,
)
except Exception as e:
verbose_logger.debug(
"litellm.proxy.auth.user_api_key_auth.py::user_api_key_auth() - Unable to get user from db/cache. Setting user_obj to None. Exception received - {}".format(
@ -1073,46 +1077,47 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
param=abbreviate_api_key(api_key=api_key),
)
# Check 4. Token Spend is under budget
if RouteChecks.is_llm_api_route(route=route):
await _virtual_key_max_budget_check(
with tracer.trace("litellm.proxy.auth.budget_checks"):
# Check 4. Token Spend is under budget
if RouteChecks.is_llm_api_route(route=route):
await _virtual_key_max_budget_check(
valid_token=valid_token,
proxy_logging_obj=proxy_logging_obj,
user_obj=user_obj,
)
# Check 5. Max Budget Alert Check
await _virtual_key_max_budget_alert_check(
valid_token=valid_token,
proxy_logging_obj=proxy_logging_obj,
user_obj=user_obj,
)
# Check 5. Max Budget Alert Check
await _virtual_key_max_budget_alert_check(
valid_token=valid_token,
proxy_logging_obj=proxy_logging_obj,
user_obj=user_obj,
)
# Check 6. Soft Budget Check
await _virtual_key_soft_budget_check(
valid_token=valid_token,
proxy_logging_obj=proxy_logging_obj,
user_obj=user_obj,
)
# Check 5. Token Model Spend is under Model budget
max_budget_per_model = valid_token.model_max_budget
current_model = request_data.get("model", None)
if (
max_budget_per_model is not None
and isinstance(max_budget_per_model, dict)
and len(max_budget_per_model) > 0
and prisma_client is not None
and current_model is not None
and valid_token.token is not None
):
## GET THE SPEND FOR THIS MODEL
await model_max_budget_limiter.is_key_within_model_budget(
user_api_key_dict=valid_token,
model=current_model,
# Check 6. Soft Budget Check
await _virtual_key_soft_budget_check(
valid_token=valid_token,
proxy_logging_obj=proxy_logging_obj,
user_obj=user_obj,
)
# Check 5. Token Model Spend is under Model budget
max_budget_per_model = valid_token.model_max_budget
current_model = request_data.get("model", None)
if (
max_budget_per_model is not None
and isinstance(max_budget_per_model, dict)
and len(max_budget_per_model) > 0
and prisma_client is not None
and current_model is not None
and valid_token.token is not None
):
## GET THE SPEND FOR THIS MODEL
await model_max_budget_limiter.is_key_within_model_budget(
user_api_key_dict=valid_token,
model=current_model,
)
# Check 6: Additional Common Checks across jwt + key auth
if valid_token.team_id is not None:
_team_obj: Optional[LiteLLM_TeamTable] = LiteLLM_TeamTable(
@ -1138,11 +1143,12 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
litellm.max_budget > 0 and prisma_client is not None
): # user set proxy max budget
cache_key = "{}:spend".format(litellm_proxy_admin_name)
global_proxy_spend = await _fetch_global_spend_with_event_coordination(
cache_key=cache_key,
user_api_key_cache=user_api_key_cache,
prisma_client=prisma_client,
)
with tracer.trace("litellm.proxy.auth.get_global_proxy_spend"):
global_proxy_spend = await _fetch_global_spend_with_event_coordination(
cache_key=cache_key,
user_api_key_cache=user_api_key_cache,
prisma_client=prisma_client,
)
if global_proxy_spend is not None:
call_info = CallInfo(
@ -1159,19 +1165,20 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
user_info=call_info,
)
)
_ = await common_checks(
request=request,
request_body=request_data,
team_object=_team_obj,
user_object=user_obj,
end_user_object=_end_user_object,
general_settings=general_settings,
global_proxy_spend=global_proxy_spend,
route=route,
llm_router=llm_router,
proxy_logging_obj=proxy_logging_obj,
valid_token=valid_token,
)
with tracer.trace("litellm.proxy.auth.common_checks"):
_ = await common_checks(
request=request,
request_body=request_data,
team_object=_team_obj,
user_object=user_obj,
end_user_object=_end_user_object,
general_settings=general_settings,
global_proxy_spend=global_proxy_spend,
route=route,
llm_router=llm_router,
proxy_logging_obj=proxy_logging_obj,
valid_token=valid_token,
)
# Token passed all checks
if valid_token is None:
raise HTTPException(401, detail="Invalid API key")