scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 114

feat(openai): apply regional-processing cost uplift for EU/US data residency

Browse source 
OpenAI charges a 10% uplift on the latest GPT models when requests are
served from a regionalized hostname (eu./us.api.openai.com).  Infer the
region from `api_base`, expose it on `kwargs["litellm_params"]["data_residency"]`,
and multiply the computed cost by a per-model
`regional_processing_uplift_multiplier_<region>` field.

https://claude.ai/code/session_012ebH44s7ohYxjoix5CXzTW
This commit is contained in:
Claude 2026-05-22 16:48:09 +00:00
parent ef36e89638
commit 6f8bb8cd28
No known key found for this signature in database
13 changed files with 445 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
litellm/cost_calculator.py
View file

@ -312,6 +312,10 @@ def cost_per_token( # noqa: PLR0915
audio_transcription_file_duration: float = 0.0, # for audio transcription calls - the file time in seconds
### SERVICE TIER ###
service_tier: Optional[str] = None, # for OpenAI service tier pricing
### DATA RESIDENCY ###
data_residency: Optional[
str
] = None, # for OpenAI regional-processing uplift (e.g. "eu", "us")
response: Optional[Any] = None,
### REQUEST MODEL ###
request_model: Optional[str] = None, # original request model for router detection
@ -493,6 +497,7 @@ def cost_per_token( # noqa: PLR0915
usage=usage_block,
custom_llm_provider=custom_llm_provider,
service_tier=service_tier,
data_residency=data_residency,
)
return prompt_cost, completion_cost
@ -529,6 +534,7 @@ def cost_per_token( # noqa: PLR0915
model=model_without_prefix,
usage=usage_block,
service_tier=service_tier,
data_residency=data_residency,
)
return openai_cost_per_second(
@ -579,7 +585,10 @@ def cost_per_token( # noqa: PLR0915
)
elif custom_llm_provider == "openai":
return openai_cost_per_token(
model=model, usage=usage_block, service_tier=service_tier
model=model,
usage=usage_block,
service_tier=service_tier,
data_residency=data_residency,
)
elif custom_llm_provider == "databricks":
return databricks_cost_per_token(model=model, usage=usage_block)
@ -631,6 +640,7 @@ def cost_per_token( # noqa: PLR0915
usage=usage_block,
custom_llm_provider=custom_llm_provider,
service_tier=service_tier,
data_residency=data_residency,
)
if (
@ -1117,6 +1127,10 @@ def completion_cost( # noqa: PLR0915
litellm_logging_obj: Optional[LitellmLoggingObject] = None,
### SERVICE TIER ###
service_tier: Optional[str] = None, # for OpenAI service tier pricing
### DATA RESIDENCY ###
data_residency: Optional[
str
] = None, # for OpenAI regional-processing uplift (e.g. "eu", "us")
) -> float:
"""
Calculate the cost of a given completion call fot GPT-3.5-turbo, llama2, any litellm supported llm.
@ -1600,6 +1614,7 @@ def completion_cost( # noqa: PLR0915
audio_transcription_file_duration=audio_transcription_file_duration,
rerank_billed_units=rerank_billed_units,
service_tier=service_tier,
data_residency=data_residency,
response=completion_response,
request_model=request_model_for_cost,
)
@ -1811,6 +1826,10 @@ def response_cost_calculator(
litellm_logging_obj: Optional[LitellmLoggingObject] = None,
### SERVICE TIER ###
service_tier: Optional[str] = None, # for OpenAI service tier pricing
### DATA RESIDENCY ###
data_residency: Optional[
str
] = None, # for OpenAI regional-processing uplift (e.g. "eu", "us")
) -> float:
"""
Returns
@ -1844,6 +1863,7 @@ def response_cost_calculator(
router_model_id=router_model_id,
litellm_logging_obj=litellm_logging_obj,
service_tier=service_tier,
data_residency=data_residency,
)
return response_cost
except Exception as e:

38
litellm/litellm_core_utils/data_residency.py Normal file
View file

@ -0,0 +1,38 @@
"""
Helpers for resolving OpenAI data-residency (regional processing) from an
api_base URL.
OpenAI enforces hostname-per-region for projects with geography restrictions
enabled and rejects requests sent to the wrong host, so the api_base hostname
is the authoritative signal of which region a request was processed in.
"""
from typing import Dict, Optional
from urllib.parse import urlparse
# Mapping of OpenAI regional hostnames to the corresponding data-residency
# value used by the cost calculator. See
# https://developers.openai.com/api/docs/pricing for the regional-processing
# uplift these hostnames trigger.
_OPENAI_REGIONAL_HOSTS: Dict[str, str] = {
"eu.api.openai.com": "eu",
"us.api.openai.com": "us",
}
def infer_openai_data_residency(api_base: Optional[str]) -> Optional[str]:
"""
Derive the OpenAI data-residency region from an api_base URL.
Returns ``"eu"`` for the EU regional host, ``"us"`` for the US regional
host, and ``None`` for the default global host (or any non-OpenAI URL).
"""
if not api_base:
return None
try:
host = urlparse(api_base).hostname
except (TypeError, ValueError):
return None
if not host:
return None
return _OPENAI_REGIONAL_HOSTS.get(host.lower())

12
litellm/litellm_core_utils/get_litellm_params.py
View file

@ -1,5 +1,7 @@
from typing import Optional
from litellm.litellm_core_utils.data_residency import infer_openai_data_residency
# Pre-define optional kwargs keys as frozenset for O(1) lookups
# These are extracted from kwargs only if present, avoiding unnecessary .get() calls
_OPTIONAL_KWARGS_KEYS = frozenset(
@ -103,6 +105,15 @@ def get_litellm_params(
if litellm_trace_id is None:
litellm_trace_id = _meta.get("trace_id") or _meta.get("session_id")
# Derive data_residency from an OpenAI regional api_base (eu./us.api.openai.com)
# so custom callbacks can read kwargs["litellm_params"]["data_residency"]
# without having to parse the URL.
data_residency: Optional[str] = (
infer_openai_data_residency(api_base)
if custom_llm_provider == "openai" or custom_llm_provider is None
else None
)
# Build base dict with explicit parameters (always included)
litellm_params = {
"acompletion": acompletion,
@ -112,6 +123,7 @@ def get_litellm_params(
"verbose": verbose,
"custom_llm_provider": custom_llm_provider,
"api_base": api_base,
"data_residency": data_residency,
"litellm_call_id": litellm_call_id,
"model_alias_map": model_alias_map,
"completion_call_id": completion_call_id,

5
litellm/litellm_core_utils/litellm_logging.py
View file

@ -1546,6 +1546,11 @@ class Logging(LiteLLMLoggingBaseClass):
if self.optional_params
else None
),
"data_residency": (
self.litellm_params.get("data_residency")
if hasattr(self, "litellm_params") and self.litellm_params
else None
),
}
except Exception as e: # error creating kwargs for cost calculation
debug_info = StandardLoggingModelCostFailureDebugInformation(

46
litellm/litellm_core_utils/llm_cost_calc/utils.py
View file

@ -9,6 +9,7 @@ from litellm.types.utils import (
CacheCreationTokenDetails,
CallTypes,
CompletionTokensDetailsWrapper,
DataResidency,
ImageResponse,
ModelInfo,
PassthroughCallTypes,
@ -617,11 +618,46 @@ def _calculate_input_cost(
return prompt_cost
def _get_regional_uplift_multiplier(
model_info: ModelInfo, data_residency: Optional[str]
) -> float:
"""
Resolve the per-model regional-processing uplift multiplier for a given
data-residency region.
OpenAI applies a flat percentage uplift (e.g. +10%) on all token costs for
requests served from a regionalized hostname (eu./us.api.openai.com). The
multiplier is stored on the model entry as
``regional_processing_uplift_multiplier_<region>`` (e.g. 1.10).
Returns 1.0 (no uplift) when ``data_residency`` is ``None`` or when the
model has no multiplier configured for the given region.
"""
if data_residency is None:
return 1.0
residency = data_residency.lower()
if residency not in {r.value for r in DataResidency}:
return 1.0
multiplier = model_info.get(f"regional_processing_uplift_multiplier_{residency}")
if multiplier is None:
return 1.0
try:
return float(cast(float, multiplier))
except (TypeError, ValueError):
verbose_logger.exception(
"Invalid regional_processing_uplift_multiplier_%s for model; "
"defaulting to 1.0",
residency,
)
return 1.0
def generic_cost_per_token( # noqa: PLR0915
model: str,
usage: Usage,
custom_llm_provider: str,
service_tier: Optional[str] = None,
data_residency: Optional[str] = None,
) -> Tuple[float, float]:
"""
Calculates the cost per token for a given model, prompt tokens, and completion tokens.
@ -631,6 +667,8 @@ def generic_cost_per_token( # noqa: PLR0915
Input:
- model: str, the model name without provider prefix
- usage: LiteLLM Usage block, containing anthropic caching information
- data_residency: optional OpenAI data-residency region (e.g. "eu", "us"),
used to apply the per-model regional-processing uplift multiplier.
Returns:
Tuple[float, float] - prompt_cost_in_usd, completion_cost_in_usd
@ -781,6 +819,14 @@ def generic_cost_per_token( # noqa: PLR0915
)
completion_cost += float(image_tokens) * _output_cost_per_image_token
## REGIONAL DATA-RESIDENCY UPLIFT
# Applied as a flat multiplier across all token costs for the request
# when the upstream is a regionalized OpenAI host (eu./us.api.openai.com).
uplift = _get_regional_uplift_multiplier(model_info, data_residency)
if uplift != 1.0:
prompt_cost *= uplift
completion_cost *= uplift
return prompt_cost, completion_cost

9
litellm/llms/openai/cost_calculation.py
View file

@ -19,7 +19,10 @@ def cost_router(call_type: CallTypes) -> Literal["cost_per_token", "cost_per_sec
def cost_per_token(
model: str, usage: Usage, service_tier: Optional[str] = None
model: str,
usage: Usage,
service_tier: Optional[str] = None,
data_residency: Optional[str] = None,
) -> Tuple[float, float]:
"""
Calculates the cost per token for a given model, prompt tokens, and completion tokens.
@ -27,6 +30,9 @@ def cost_per_token(
Input:
- model: str, the model name without provider prefix
- usage: LiteLLM Usage block, containing anthropic caching information
- data_residency: optional OpenAI data-residency region (e.g. "eu", "us"),
inferred from api_base. Applies the model's regional-processing
uplift multiplier when set.
Returns:
Tuple[float, float] - prompt_cost_in_usd, completion_cost_in_usd
@ -37,6 +43,7 @@ def cost_per_token(
usage=usage,
custom_llm_provider="openai",
service_tier=service_tier,
data_residency=data_residency,
)
# ### Non-cached text tokens
# non_cached_text_tokens = usage.prompt_tokens

102
litellm/model_prices_and_context_window_backup.json
View file

@ -1011,6 +1011,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -1041,6 +1042,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -1071,6 +1073,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -1100,6 +1103,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -1129,6 +1133,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -1328,6 +1333,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"global.anthropic.claude-sonnet-4-6": {
@ -1358,6 +1364,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"us.anthropic.claude-sonnet-4-6": {
@ -1388,6 +1395,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"eu.anthropic.claude-sonnet-4-6": {
@ -1417,6 +1425,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"au.anthropic.claude-sonnet-4-6": {
@ -1446,6 +1455,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"jp.anthropic.claude-sonnet-4-6": {
@ -1475,6 +1485,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"anthropic.claude-sonnet-4-20250514-v1:0": {
@ -1996,6 +2007,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 159,
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -2093,6 +2105,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"azure/computer-use-preview": {
@ -9643,6 +9656,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"claude-sonnet-4-5-20250929-v1:0": {
@ -9840,6 +9854,7 @@
"us": 1.1,
"fast": 6.0
},
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -9875,7 +9890,8 @@
"fast": 6.0
},
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"supports_output_config": true
},
"claude-opus-4-7": {
"cache_creation_input_token_cost": 6.25e-06,
@ -9910,7 +9926,8 @@
"us": 1.1,
"fast": 6.0
},
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"supports_output_config": true
},
"claude-opus-4-7-20260416": {
"cache_creation_input_token_cost": 6.25e-06,
@ -9945,7 +9962,8 @@
"us": 1.1,
"fast": 6.0
},
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"supports_output_config": true
},
"claude-sonnet-4-20250514": {
"deprecation_date": "2026-05-14",
@ -14947,7 +14965,7 @@
"mode": "chat",
"output_cost_per_reasoning_token": 1.5e-06,
"output_cost_per_token": 1.5e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
"source": "https://ai.google.dev/gemini-api/docs/models",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -19003,6 +19021,8 @@
"output_cost_per_token": 8e-06,
"output_cost_per_token_batches": 4e-06,
"output_cost_per_token_priority": 1.4e-05,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -19076,6 +19096,8 @@
"output_cost_per_token": 1.6e-06,
"output_cost_per_token_batches": 8e-07,
"output_cost_per_token_priority": 2.8e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -19149,6 +19171,8 @@
"output_cost_per_token": 4e-07,
"output_cost_per_token_batches": 2e-07,
"output_cost_per_token_priority": 8e-07,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -19220,6 +19244,8 @@
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"output_cost_per_token_priority": 1.7e-05,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
@ -19261,6 +19287,8 @@
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
@ -19282,6 +19310,8 @@
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
@ -19570,6 +19600,8 @@
"output_cost_per_token": 6e-07,
"output_cost_per_token_batches": 3e-07,
"output_cost_per_token_priority": 1e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
@ -20273,6 +20305,8 @@
"output_cost_per_token": 1e-05,
"output_cost_per_token_flex": 5e-06,
"output_cost_per_token_priority": 2e-05,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -21195,6 +21229,8 @@
"mode": "responses",
"output_cost_per_token": 0.00012,
"output_cost_per_token_batches": 6e-05,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/batch",
"/v1/responses"
@ -21601,6 +21637,8 @@
"output_cost_per_token": 2e-06,
"output_cost_per_token_flex": 1e-06,
"output_cost_per_token_priority": 3.6e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -21682,6 +21720,8 @@
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"mode": "chat",
"output_cost_per_token": 4e-07,
"output_cost_per_token_flex": 2e-07,
@ -28187,10 +28227,10 @@
"supports_tool_choice": true
},
"openrouter/xiaomi/mimo-v2-flash": {
"input_cost_per_token": 9e-08,
"output_cost_per_token": 2.9e-07,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 3e-07,
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 0.0,
"cache_read_input_token_cost": 1e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 16384,
@ -28200,7 +28240,43 @@
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_vision": false,
"supports_prompt_caching": false
"supports_prompt_caching": true
},
"openrouter/xiaomi/mimo-v2.5-pro": {
"input_cost_per_token": 1e-06,
"output_cost_per_token": 3e-06,
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 2e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_vision": false,
"supports_response_schema": true,
"supports_prompt_caching": true
},
"openrouter/xiaomi/mimo-v2.5": {
"input_cost_per_token": 4e-07,
"output_cost_per_token": 2e-06,
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 8e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_vision": true,
"supports_audio_input": true,
"supports_video_input": true,
"supports_response_schema": true,
"supports_prompt_caching": true
},
"openrouter/z-ai/glm-4.7": {
"input_cost_per_token": 4e-07,
@ -28931,14 +29007,16 @@
"mode": "responses",
"supports_web_search": true,
"supports_reasoning": false,
"supports_function_calling": true
"supports_function_calling": true,
"supports_output_config": true
},
"perplexity/anthropic/claude-opus-4-7": {
"litellm_provider": "perplexity",
"mode": "responses",
"supports_web_search": true,
"supports_reasoning": false,
"supports_function_calling": true
"supports_function_calling": true,
"supports_output_config": true
},
"perplexity/anthropic/claude-opus-4-5": {
"litellm_provider": "perplexity",
@ -33349,6 +33427,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -33377,6 +33456,7 @@
"supports_tool_choice": true,
"supports_vision": true,
"tool_use_system_prompt_tokens": 346,
"supports_output_config": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
@ -33490,6 +33570,7 @@
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"vertex_ai/claude-sonnet-4-5@20250929": {
@ -40602,6 +40683,7 @@
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_output_config": true,
"supports_minimal_reasoning_effort": true
},
"duckduckgo/search": {

20
litellm/types/utils.py
View file

@ -219,6 +219,12 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
output_cost_per_token_priority: Optional[
float
] # OpenAI priority service tier pricing
regional_processing_uplift_multiplier_eu: Optional[
float
] # OpenAI EU data-residency uplift multiplier applied to all token costs (e.g. 1.10 = +10%)
regional_processing_uplift_multiplier_us: Optional[
float
] # OpenAI US data-residency uplift multiplier applied to all token costs (e.g. 1.10 = +10%)
output_cost_per_character: Optional[float] # only for vertex ai models
output_cost_per_audio_token: Optional[float]
output_cost_per_token_above_128k_tokens: Optional[
@ -3601,6 +3607,20 @@ class ServiceTier(Enum):
PRIORITY = "priority"
class DataResidency(Enum):
"""
OpenAI data-residency / regional-processing regions.
Inferred from the OpenAI api_base host (eu.api.openai.com -> EU,
us.api.openai.com -> US). Used to apply the regional-processing
cost uplift (see ``regional_processing_uplift_multiplier_<region>``
on ModelInfo).
"""
US = "us"
EU = "eu"
LLMResponseTypes = Union[
ModelResponse,
EmbeddingResponse,

6
litellm/utils.py
View file

@ -5902,6 +5902,12 @@ def _get_model_info_helper( # noqa: PLR0915
output_cost_per_token_priority=_model_info.get(
"output_cost_per_token_priority", None
),
regional_processing_uplift_multiplier_eu=_model_info.get(
"regional_processing_uplift_multiplier_eu", None
),
regional_processing_uplift_multiplier_us=_model_info.get(
"regional_processing_uplift_multiplier_us", None
),
output_cost_per_audio_token=_model_info.get(
"output_cost_per_audio_token", None
),

22
model_prices_and_context_window.json
View file

@ -19021,6 +19021,8 @@
"output_cost_per_token": 8e-06,
"output_cost_per_token_batches": 4e-06,
"output_cost_per_token_priority": 1.4e-05,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -19094,6 +19096,8 @@
"output_cost_per_token": 1.6e-06,
"output_cost_per_token_batches": 8e-07,
"output_cost_per_token_priority": 2.8e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -19167,6 +19171,8 @@
"output_cost_per_token": 4e-07,
"output_cost_per_token_batches": 2e-07,
"output_cost_per_token_priority": 8e-07,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -19238,6 +19244,8 @@
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"output_cost_per_token_priority": 1.7e-05,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
@ -19279,6 +19287,8 @@
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
@ -19300,6 +19310,8 @@
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
@ -19588,6 +19600,8 @@
"output_cost_per_token": 6e-07,
"output_cost_per_token_batches": 3e-07,
"output_cost_per_token_priority": 1e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
@ -20291,6 +20305,8 @@
"output_cost_per_token": 1e-05,
"output_cost_per_token_flex": 5e-06,
"output_cost_per_token_priority": 2e-05,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -21213,6 +21229,8 @@
"mode": "responses",
"output_cost_per_token": 0.00012,
"output_cost_per_token_batches": 6e-05,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/batch",
"/v1/responses"
@ -21619,6 +21637,8 @@
"output_cost_per_token": 2e-06,
"output_cost_per_token_flex": 1e-06,
"output_cost_per_token_priority": 3.6e-06,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -21700,6 +21720,8 @@
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"regional_processing_uplift_multiplier_eu": 1.10,
"regional_processing_uplift_multiplier_us": 1.10,
"mode": "chat",
"output_cost_per_token": 4e-07,
"output_cost_per_token_flex": 2e-07,

112
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -1418,3 +1418,115 @@ def test_image_count_prevents_text_tokens_fallback():
f"got {prompt_cost}. text_tokens fallback may be double-charging."
)
assert completion_cost == 0.0
# ---------------------------------------------------------------------------
# Data-residency (OpenAI regional processing) tests
# ---------------------------------------------------------------------------
@pytest.fixture
def _local_model_cost_map():
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
yield
os.environ.pop("LITELLM_LOCAL_MODEL_COST_MAP", None)
@pytest.mark.parametrize("data_residency", ["eu", "us"])
def test_data_residency_applies_uplift(data_residency, _local_model_cost_map):
"""gpt-5 should apply the regional processing uplift multiplier when
data_residency is set."""
from litellm.types.utils import Usage
usage = Usage(prompt_tokens=1000, completion_tokens=500, total_tokens=1500)
base = generic_cost_per_token(
model="gpt-5",
usage=usage,
custom_llm_provider="openai",
)
regional = generic_cost_per_token(
model="gpt-5",
usage=usage,
custom_llm_provider="openai",
data_residency=data_residency,
)
base_total = base[0] + base[1]
regional_total = regional[0] + regional[1]
assert base_total > 0
assert regional_total == pytest.approx(base_total * 1.10, rel=1e-9)
assert regional[0] == pytest.approx(base[0] * 1.10, rel=1e-9)
assert regional[1] == pytest.approx(base[1] * 1.10, rel=1e-9)
def test_data_residency_no_uplift_for_unmarked_model(_local_model_cost_map):
"""A model without a regional_processing_uplift_multiplier_* entry should
fall back to base pricing, not error."""
from litellm.types.utils import Usage
usage = Usage(prompt_tokens=1000, completion_tokens=500, total_tokens=1500)
base = generic_cost_per_token(
model="gpt-3.5-turbo",
usage=usage,
custom_llm_provider="openai",
)
with_residency = generic_cost_per_token(
model="gpt-3.5-turbo",
usage=usage,
custom_llm_provider="openai",
data_residency="eu",
)
assert base == with_residency
def test_data_residency_none_no_uplift(_local_model_cost_map):
"""data_residency=None should be a no-op even for models with a multiplier."""
from litellm.types.utils import Usage
usage = Usage(prompt_tokens=1000, completion_tokens=500, total_tokens=1500)
base = generic_cost_per_token(
model="gpt-5",
usage=usage,
custom_llm_provider="openai",
)
explicit_none = generic_cost_per_token(
model="gpt-5",
usage=usage,
custom_llm_provider="openai",
data_residency=None,
)
assert base == explicit_none
def test_data_residency_composes_with_service_tier(_local_model_cost_map):
"""The uplift multiplies the priority-tier cost, not the standard one."""
from litellm.types.utils import Usage
usage = Usage(prompt_tokens=1000, completion_tokens=500, total_tokens=1500)
priority_base = generic_cost_per_token(
model="gpt-5",
usage=usage,
custom_llm_provider="openai",
service_tier="priority",
)
priority_eu = generic_cost_per_token(
model="gpt-5",
usage=usage,
custom_llm_provider="openai",
service_tier="priority",
data_residency="eu",
)
priority_base_total = priority_base[0] + priority_base[1]
priority_eu_total = priority_eu[0] + priority_eu[1]
assert priority_base_total > 0
assert priority_eu_total == pytest.approx(priority_base_total * 1.10, rel=1e-9)

26
tests/test_litellm/litellm_core_utils/test_data_residency.py Normal file
View file

@ -0,0 +1,26 @@
"""Tests for the OpenAI data-residency inference helper."""
import pytest
from litellm.litellm_core_utils.data_residency import infer_openai_data_residency
@pytest.mark.parametrize(
"api_base, expected",
[
("https://eu.api.openai.com/v1", "eu"),
("https://eu.api.openai.com", "eu"),
("https://us.api.openai.com/v1", "us"),
("https://us.api.openai.com", "us"),
("https://EU.api.openai.com/v1", "eu"),
("https://api.openai.com/v1", None),
("https://api.openai.com", None),
("https://example.com/v1", None),
("https://my-azure-endpoint.openai.azure.com/openai/deployments/foo", None),
("", None),
(None, None),
("not a url", None),
],
)
def test_infer_openai_data_residency(api_base, expected):
assert infer_openai_data_residency(api_base) == expected

37
tests/test_litellm/litellm_core_utils/test_get_litellm_params.py
View file

@ -125,3 +125,40 @@ class TestGetLitellmParamsExplicitFields:
def test_no_log_from_explicit_param(self):
result = get_litellm_params(no_log=True)
assert result["no-log"] is True
class TestGetLitellmParamsDataResidency:
"""Verify that data_residency is inferred from OpenAI regional api_base."""
def test_eu_host_resolves_to_eu(self):
result = get_litellm_params(
custom_llm_provider="openai",
api_base="https://eu.api.openai.com/v1",
)
assert result["data_residency"] == "eu"
def test_us_host_resolves_to_us(self):
result = get_litellm_params(
custom_llm_provider="openai",
api_base="https://us.api.openai.com/v1",
)
assert result["data_residency"] == "us"
def test_global_host_resolves_to_none(self):
result = get_litellm_params(
custom_llm_provider="openai",
api_base="https://api.openai.com/v1",
)
assert result["data_residency"] is None
def test_no_api_base_is_none(self):
result = get_litellm_params(custom_llm_provider="openai")
assert result["data_residency"] is None
def test_non_openai_provider_does_not_resolve(self):
"""Regional OpenAI host doesn't apply to other providers."""
result = get_litellm_params(
custom_llm_provider="anthropic",
api_base="https://eu.api.openai.com/v1",
)
assert result["data_residency"] is None