scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-11 03:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 84

fix(model_prices): add gpt-realtime-2.1 models with regional processing uplift (#32387)

Browse source 
* fix(model_prices): add gpt-realtime-2.1 models with regional processing uplift

* fix(model_prices): add cache_read_input_audio_token_cost to gpt-realtime-2.1
This commit is contained in:
Mateo Wang 2026-07-07 18:56:00 -07:00 • committed by GitHub
parent a05a1eef94
commit bd6cabee83
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 147 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

70
litellm/model_prices_and_context_window_backup.json
View file

@ -23503,6 +23503,76 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-realtime-2.1": {
"cache_creation_input_audio_token_cost": 4e-07,
"cache_read_input_audio_token_cost": 4e-07,
"cache_read_input_token_cost": 4e-07,
"input_cost_per_audio_token": 3.2e-05,
"input_cost_per_image": 5e-06,
"input_cost_per_token": 4e-06,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_audio_token": 6.4e-05,
"output_cost_per_token": 2.4e-05,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-realtime-2.1-mini": {
"cache_creation_input_audio_token_cost": 3e-07,
"cache_read_input_audio_token_cost": 3e-07,
"cache_read_input_token_cost": 6e-08,
"input_cost_per_audio_token": 1e-05,
"input_cost_per_image": 8e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_audio_token": 2e-05,
"output_cost_per_token": 2.4e-06,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-realtime-mini": {
"cache_creation_input_audio_token_cost": 3e-07,
"cache_read_input_audio_token_cost": 3e-07,

70
model_prices_and_context_window.json
View file

@ -23661,6 +23661,76 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-realtime-2.1": {
"cache_creation_input_audio_token_cost": 4e-07,
"cache_read_input_audio_token_cost": 4e-07,
"cache_read_input_token_cost": 4e-07,
"input_cost_per_audio_token": 3.2e-05,
"input_cost_per_image": 5e-06,
"input_cost_per_token": 4e-06,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_audio_token": 6.4e-05,
"output_cost_per_token": 2.4e-05,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-realtime-2.1-mini": {
"cache_creation_input_audio_token_cost": 3e-07,
"cache_read_input_audio_token_cost": 3e-07,
"cache_read_input_token_cost": 6e-08,
"input_cost_per_audio_token": 1e-05,
"input_cost_per_image": 8e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_audio_token": 2e-05,
"output_cost_per_token": 2.4e-06,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-realtime-mini": {
"cache_creation_input_audio_token_cost": 3e-07,
"cache_read_input_audio_token_cost": 3e-07,

13
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -1538,22 +1538,23 @@ def _local_model_cost_map():
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = prev_env
@pytest.mark.parametrize("model", ["gpt-5.4", "gpt-realtime-2.1", "gpt-realtime-2.1-mini"])
@pytest.mark.parametrize("data_residency", ["eu", "us"])
def test_data_residency_applies_uplift(data_residency, _local_model_cost_map):
"""gpt-5.4 should apply the regional processing uplift multiplier when
data_residency is set. gpt-5.4+ (released 2026-03-05) carry the 10% uplift;
gpt-5 and older models do not."""
def test_data_residency_applies_uplift(data_residency, model, _local_model_cost_map):
"""Models released on/after 2026-03-05 (gpt-5.4/5.5 and gpt-realtime-2.1
series) apply the 10% regional processing uplift multiplier when
data_residency is set; gpt-5 and older models do not."""
from litellm.types.utils import Usage
usage = Usage(prompt_tokens=1000, completion_tokens=500, total_tokens=1500)
base = generic_cost_per_token(
model="gpt-5.4",
model=model,
usage=usage,
custom_llm_provider="openai",
)
regional = generic_cost_per_token(
model="gpt-5.4",
model=model,
usage=usage,
custom_llm_provider="openai",
data_residency=data_residency,