diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d5f412b9279..86c9eb0b70d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -23678,14 +23678,17 @@ "gpt-5.6": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 6.25e-06, "cache_creation_input_token_cost_flex": 3.125e-06, "cache_creation_input_token_cost_priority": 1.25e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 1e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_priority": 1e-05, @@ -23696,6 +23699,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 2.25e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_priority": 6e-05, @@ -23731,14 +23735,17 @@ "gpt-5.6-sol": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 6.25e-06, "cache_creation_input_token_cost_flex": 3.125e-06, "cache_creation_input_token_cost_priority": 1.25e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 1e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_priority": 1e-05, @@ -23749,6 +23756,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 2.25e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_priority": 6e-05, @@ -23784,14 +23792,17 @@ "gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_flex": 1.25e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 4e-06, @@ -23802,6 +23813,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.4e-05, @@ -23837,14 +23849,17 @@ "gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_flex": 1.25e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_priority": 4e-07, @@ -23855,6 +23870,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.4e-06, diff --git a/litellm/types/utils.py b/litellm/types/utils.py index 9df44c6202c..b2d463e2e08 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -200,7 +200,12 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): input_cost_per_token_priority: Optional[float] # OpenAI priority service tier pricing cache_creation_input_token_cost: Optional[float] cache_creation_input_token_cost_above_200k_tokens: Optional[float] + cache_creation_input_token_cost_above_272k_tokens: Optional[float] + cache_creation_input_token_cost_above_272k_tokens_priority: Optional[float] + cache_creation_input_token_cost_above_272k_tokens_flex: Optional[float] cache_creation_input_token_cost_above_1hr: Optional[float] + cache_creation_input_token_cost_flex: Optional[float] # OpenAI flex service tier pricing + cache_creation_input_token_cost_priority: Optional[float] # OpenAI priority service tier pricing cache_read_input_token_cost: Optional[float] cache_read_input_token_cost_flex: Optional[float] # OpenAI flex service tier pricing cache_read_input_token_cost_priority: Optional[float] # OpenAI priority service tier pricing @@ -208,6 +213,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): cache_read_input_token_cost_above_200k_tokens_priority: Optional[float] cache_read_input_token_cost_above_272k_tokens: Optional[float] cache_read_input_token_cost_above_272k_tokens_priority: Optional[float] + cache_read_input_token_cost_above_272k_tokens_flex: Optional[float] cache_read_input_token_cost_above_512k_tokens: Optional[float] # Smallest prefix this model will actually cache, whatever caching mechanism its provider uses. # Absent means the provider-agnostic default applies; see MINIMUM_PROMPT_CACHE_TOKEN_COUNT. @@ -219,6 +225,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): input_cost_per_token_above_200k_tokens_priority: Optional[float] input_cost_per_token_above_272k_tokens: Optional[float] # GPT-5.4/5.4-pro: prompts >272K priced at 2x input input_cost_per_token_above_272k_tokens_priority: Optional[float] + input_cost_per_token_above_272k_tokens_flex: Optional[float] input_cost_per_token_above_512k_tokens: Optional[float] # MiniMax-M3: prompts >512K priced at 2x input input_cost_per_character_above_128k_tokens: Optional[float] # only for vertex ai models input_cost_per_query: Optional[float] # only for rerank models @@ -246,6 +253,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): output_cost_per_token_above_200k_tokens_priority: Optional[float] output_cost_per_token_above_272k_tokens: Optional[float] # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output output_cost_per_token_above_272k_tokens_priority: Optional[float] + output_cost_per_token_above_272k_tokens_flex: Optional[float] output_cost_per_token_above_512k_tokens: Optional[float] # MiniMax-M3: prompts >512K priced at 2x output output_cost_per_character_above_128k_tokens: Optional[float] # only for vertex ai models output_cost_per_image: Optional[float] @@ -3158,6 +3166,11 @@ class CustomPricingLiteLLMParams(BaseModel): cache_creation_input_token_cost: Optional[float] = None cache_creation_input_token_cost_above_1hr: Optional[float] = None cache_creation_input_token_cost_above_200k_tokens: Optional[float] = None + cache_creation_input_token_cost_above_272k_tokens: Optional[float] = None + cache_creation_input_token_cost_above_272k_tokens_priority: Optional[float] = None + cache_creation_input_token_cost_above_272k_tokens_flex: Optional[float] = None + cache_creation_input_token_cost_flex: Optional[float] = None + cache_creation_input_token_cost_priority: Optional[float] = None cache_creation_input_audio_token_cost: Optional[float] = None cache_read_input_token_cost: Optional[float] = None cache_read_input_token_cost_flex: Optional[float] = None @@ -3165,6 +3178,7 @@ class CustomPricingLiteLLMParams(BaseModel): cache_read_input_token_cost_above_200k_tokens: Optional[float] = None cache_read_input_token_cost_above_200k_tokens_priority: Optional[float] = None cache_read_input_token_cost_above_272k_tokens_priority: Optional[float] = None + cache_read_input_token_cost_above_272k_tokens_flex: Optional[float] = None cache_read_input_audio_token_cost: Optional[float] = None input_cost_per_character: Optional[float] = None input_cost_per_character_above_128k_tokens: Optional[float] = None @@ -3174,6 +3188,7 @@ class CustomPricingLiteLLMParams(BaseModel): input_cost_per_token_above_200k_tokens: Optional[float] = None input_cost_per_token_above_200k_tokens_priority: Optional[float] = None input_cost_per_token_above_272k_tokens_priority: Optional[float] = None + input_cost_per_token_above_272k_tokens_flex: Optional[float] = None input_cost_per_query: Optional[float] = None input_cost_per_image: Optional[float] = None input_cost_per_image_above_128k_tokens: Optional[float] = None @@ -3193,6 +3208,7 @@ class CustomPricingLiteLLMParams(BaseModel): output_cost_per_token_above_200k_tokens: Optional[float] = None output_cost_per_token_above_200k_tokens_priority: Optional[float] = None output_cost_per_token_above_272k_tokens_priority: Optional[float] = None + output_cost_per_token_above_272k_tokens_flex: Optional[float] = None output_cost_per_character_above_128k_tokens: Optional[float] = None output_cost_per_image: Optional[float] = None output_cost_per_image_token: Optional[float] = None diff --git a/litellm/utils.py b/litellm/utils.py index 944bb61d5e7..4c66955e366 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -5410,6 +5410,19 @@ def _get_model_info_helper( cache_creation_input_token_cost_above_200k_tokens=_model_info.get( "cache_creation_input_token_cost_above_200k_tokens", None ), + cache_creation_input_token_cost_above_272k_tokens=_model_info.get( + "cache_creation_input_token_cost_above_272k_tokens", None + ), + cache_creation_input_token_cost_above_272k_tokens_priority=_model_info.get( + "cache_creation_input_token_cost_above_272k_tokens_priority", None + ), + cache_creation_input_token_cost_above_272k_tokens_flex=_model_info.get( + "cache_creation_input_token_cost_above_272k_tokens_flex", None + ), + cache_creation_input_token_cost_flex=_model_info.get("cache_creation_input_token_cost_flex", None), + cache_creation_input_token_cost_priority=_model_info.get( + "cache_creation_input_token_cost_priority", None + ), cache_read_input_token_cost=_model_info.get("cache_read_input_token_cost", None), prompt_cache_min_tokens=_model_info.get("prompt_cache_min_tokens", None), cache_read_input_token_cost_above_200k_tokens=_model_info.get( @@ -5424,6 +5437,9 @@ def _get_model_info_helper( cache_read_input_token_cost_above_272k_tokens_priority=_model_info.get( "cache_read_input_token_cost_above_272k_tokens_priority", None ), + cache_read_input_token_cost_above_272k_tokens_flex=_model_info.get( + "cache_read_input_token_cost_above_272k_tokens_flex", None + ), cache_read_input_token_cost_above_512k_tokens=_model_info.get( "cache_read_input_token_cost_above_512k_tokens", None ), @@ -5442,6 +5458,9 @@ def _get_model_info_helper( input_cost_per_token_above_272k_tokens_priority=_model_info.get( "input_cost_per_token_above_272k_tokens_priority", None ), + input_cost_per_token_above_272k_tokens_flex=_model_info.get( + "input_cost_per_token_above_272k_tokens_flex", None + ), input_cost_per_token_above_512k_tokens=_model_info.get("input_cost_per_token_above_512k_tokens", None), input_cost_per_query=_model_info.get("input_cost_per_query", None), input_cost_per_second=_model_info.get("input_cost_per_second", None), @@ -5483,6 +5502,9 @@ def _get_model_info_helper( output_cost_per_token_above_272k_tokens_priority=_model_info.get( "output_cost_per_token_above_272k_tokens_priority", None ), + output_cost_per_token_above_272k_tokens_flex=_model_info.get( + "output_cost_per_token_above_272k_tokens_flex", None + ), output_cost_per_token_above_512k_tokens=_model_info.get( "output_cost_per_token_above_512k_tokens", None ), diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e0917ed87b4..90129dd5ddc 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -23753,14 +23753,17 @@ "gpt-5.6": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 6.25e-06, "cache_creation_input_token_cost_flex": 3.125e-06, "cache_creation_input_token_cost_priority": 1.25e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 1e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_priority": 1e-05, @@ -23771,6 +23774,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 2.25e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_priority": 6e-05, @@ -23806,14 +23810,17 @@ "gpt-5.6-sol": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 6.25e-06, "cache_creation_input_token_cost_flex": 3.125e-06, "cache_creation_input_token_cost_priority": 1.25e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 1e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_priority": 1e-05, @@ -23824,6 +23831,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 2.25e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_priority": 6e-05, @@ -23859,14 +23867,17 @@ "gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_flex": 1.25e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 4e-06, @@ -23877,6 +23888,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.4e-05, @@ -23912,14 +23924,17 @@ "gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_flex": 1.25e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_priority": 4e-07, @@ -23930,6 +23945,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.4e-06, diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 1ad271900f6..3454f160cfa 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -661,6 +661,54 @@ def test_generic_cost_per_token_gpt56( assert round(completion_cost, 10) == round(output_cost * completion_tokens, 10) +@pytest.mark.parametrize( + "model,flex_long_input_cost,flex_long_output_cost", + [ + ("gpt-5.6", 5e-6, 2.25e-5), + ("gpt-5.6-sol", 5e-6, 2.25e-5), + ("gpt-5.6-terra", 2e-6, 9e-6), + ("gpt-5.6-luna", 2e-7, 9e-7), + ], +) +def test_generic_cost_per_token_gpt56_flex_above_272k( + model, flex_long_input_cost, flex_long_output_cost +): + """A >272K flex request bills the flex long-context rate, not the standard one. + + Flex long-context is half the standard long-context rate. Without the + ``*_above_272k_tokens_flex`` keys these requests silently fell back to the + standard long-context price, billing 2x what OpenAI charges. + """ + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + + prompt_tokens = 300000 + completion_tokens = 1000 + usage = Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + ) + prompt_cost, completion_cost = generic_cost_per_token( + model=model, + usage=usage, + custom_llm_provider="openai", + service_tier="flex", + ) + + assert prompt_cost == pytest.approx(flex_long_input_cost * prompt_tokens) + assert completion_cost == pytest.approx(flex_long_output_cost * completion_tokens) + + standard_long_prompt_cost, standard_long_completion_cost = generic_cost_per_token( + model=model, + usage=usage, + custom_llm_provider="openai", + service_tier=None, + ) + assert prompt_cost == pytest.approx(standard_long_prompt_cost / 2) + assert completion_cost == pytest.approx(standard_long_completion_cost / 2) + + @pytest.mark.parametrize( "model,input_cost,output_cost,cache_read_cost", [ diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index b22e69f0942..83cb75636f2 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -768,11 +768,17 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_creation_input_token_cost_above_1hr": {"type": "number"}, "cache_creation_input_token_cost_above_200k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_272k_tokens": {"type": "number"}, + "cache_creation_input_token_cost_above_272k_tokens_flex": { + "type": "number" + }, "cache_creation_input_token_cost_flex": {"type": "number"}, "cache_creation_input_token_cost_priority": {"type": "number"}, "cache_read_input_token_cost": {"type": "number"}, "cache_read_input_token_cost_above_200k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_272k_tokens": {"type": "number"}, + "cache_read_input_token_cost_above_272k_tokens_flex": { + "type": "number" + }, "cache_read_input_token_cost_above_512k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": { "type": "number" @@ -806,11 +812,13 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "input_cost_per_token_priority": {"type": "number"}, "input_cost_per_token_above_200k_tokens_priority": {"type": "number"}, "input_cost_per_token_above_272k_tokens_priority": {"type": "number"}, + "input_cost_per_token_above_272k_tokens_flex": {"type": "number"}, "input_cost_per_audio_token_priority": {"type": "number"}, "output_cost_per_token_flex": {"type": "number"}, "output_cost_per_token_priority": {"type": "number"}, "output_cost_per_token_above_200k_tokens_priority": {"type": "number"}, "output_cost_per_token_above_272k_tokens_priority": {"type": "number"}, + "output_cost_per_token_above_272k_tokens_flex": {"type": "number"}, "regional_processing_uplift_multiplier_eu": {"type": "number"}, "regional_processing_uplift_multiplier_us": {"type": "number"}, "input_cost_per_pixel": {"type": "number"}, diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts index bc3110d4d3d..8f51778ded6 100644 --- a/ui/litellm-dashboard/src/lib/http/schema.d.ts +++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts @@ -25848,6 +25848,16 @@ export interface components { cache_creation_input_token_cost_above_1hr?: number | null; /** Cache Creation Input Token Cost Above 200K Tokens */ cache_creation_input_token_cost_above_200k_tokens?: number | null; + /** Cache Creation Input Token Cost Above 272K Tokens */ + cache_creation_input_token_cost_above_272k_tokens?: number | null; + /** Cache Creation Input Token Cost Above 272K Tokens Flex */ + cache_creation_input_token_cost_above_272k_tokens_flex?: number | null; + /** Cache Creation Input Token Cost Above 272K Tokens Priority */ + cache_creation_input_token_cost_above_272k_tokens_priority?: number | null; + /** Cache Creation Input Token Cost Flex */ + cache_creation_input_token_cost_flex?: number | null; + /** Cache Creation Input Token Cost Priority */ + cache_creation_input_token_cost_priority?: number | null; /** Cache Read Input Audio Token Cost */ cache_read_input_audio_token_cost?: number | null; /** Cache Read Input Token Cost */ @@ -25858,6 +25868,8 @@ export interface components { cache_read_input_token_cost_above_200k_tokens_priority?: number | null; /** Cache Read Input Token Cost Above 272K Tokens */ cache_read_input_token_cost_above_272k_tokens?: number | null; + /** Cache Read Input Token Cost Above 272K Tokens Flex */ + cache_read_input_token_cost_above_272k_tokens_flex?: number | null; /** Cache Read Input Token Cost Above 272K Tokens Priority */ cache_read_input_token_cost_above_272k_tokens_priority?: number | null; /** Cache Read Input Token Cost Above 512K Tokens */ @@ -25916,6 +25928,8 @@ export interface components { input_cost_per_token_above_200k_tokens_priority?: number | null; /** Input Cost Per Token Above 272K Tokens */ input_cost_per_token_above_272k_tokens?: number | null; + /** Input Cost Per Token Above 272K Tokens Flex */ + input_cost_per_token_above_272k_tokens_flex?: number | null; /** Input Cost Per Token Above 272K Tokens Priority */ input_cost_per_token_above_272k_tokens_priority?: number | null; /** Input Cost Per Token Above 512K Tokens */ @@ -26007,6 +26021,8 @@ export interface components { output_cost_per_token_above_200k_tokens_priority?: number | null; /** Output Cost Per Token Above 272K Tokens */ output_cost_per_token_above_272k_tokens?: number | null; + /** Output Cost Per Token Above 272K Tokens Flex */ + output_cost_per_token_above_272k_tokens_flex?: number | null; /** Output Cost Per Token Above 272K Tokens Priority */ output_cost_per_token_above_272k_tokens_priority?: number | null; /** Output Cost Per Token Above 512K Tokens */ @@ -33939,6 +33955,16 @@ export interface components { cache_creation_input_token_cost_above_1hr?: number | null; /** Cache Creation Input Token Cost Above 200K Tokens */ cache_creation_input_token_cost_above_200k_tokens?: number | null; + /** Cache Creation Input Token Cost Above 272K Tokens */ + cache_creation_input_token_cost_above_272k_tokens?: number | null; + /** Cache Creation Input Token Cost Above 272K Tokens Flex */ + cache_creation_input_token_cost_above_272k_tokens_flex?: number | null; + /** Cache Creation Input Token Cost Above 272K Tokens Priority */ + cache_creation_input_token_cost_above_272k_tokens_priority?: number | null; + /** Cache Creation Input Token Cost Flex */ + cache_creation_input_token_cost_flex?: number | null; + /** Cache Creation Input Token Cost Priority */ + cache_creation_input_token_cost_priority?: number | null; /** Cache Read Input Audio Token Cost */ cache_read_input_audio_token_cost?: number | null; /** Cache Read Input Token Cost */ @@ -33949,6 +33975,8 @@ export interface components { cache_read_input_token_cost_above_200k_tokens_priority?: number | null; /** Cache Read Input Token Cost Above 272K Tokens */ cache_read_input_token_cost_above_272k_tokens?: number | null; + /** Cache Read Input Token Cost Above 272K Tokens Flex */ + cache_read_input_token_cost_above_272k_tokens_flex?: number | null; /** Cache Read Input Token Cost Above 272K Tokens Priority */ cache_read_input_token_cost_above_272k_tokens_priority?: number | null; /** Cache Read Input Token Cost Above 512K Tokens */ @@ -34007,6 +34035,8 @@ export interface components { input_cost_per_token_above_200k_tokens_priority?: number | null; /** Input Cost Per Token Above 272K Tokens */ input_cost_per_token_above_272k_tokens?: number | null; + /** Input Cost Per Token Above 272K Tokens Flex */ + input_cost_per_token_above_272k_tokens_flex?: number | null; /** Input Cost Per Token Above 272K Tokens Priority */ input_cost_per_token_above_272k_tokens_priority?: number | null; /** Input Cost Per Token Above 512K Tokens */ @@ -34098,6 +34128,8 @@ export interface components { output_cost_per_token_above_200k_tokens_priority?: number | null; /** Output Cost Per Token Above 272K Tokens */ output_cost_per_token_above_272k_tokens?: number | null; + /** Output Cost Per Token Above 272K Tokens Flex */ + output_cost_per_token_above_272k_tokens_flex?: number | null; /** Output Cost Per Token Above 272K Tokens Priority */ output_cost_per_token_above_272k_tokens_priority?: number | null; /** Output Cost Per Token Above 512K Tokens */