diff --git a/litellm/integrations/sqs.py b/litellm/integrations/sqs.py index c03f134b6df..ad4df97f98e 100644 --- a/litellm/integrations/sqs.py +++ b/litellm/integrations/sqs.py @@ -29,7 +29,6 @@ from litellm.llms.custom_httpx.http_handler import ( from litellm.types.utils import StandardLoggingPayload from .custom_batch_logger import CustomBatchLogger -from litellm.litellm_core_utils.app_crypto import AppCrypto class SQSLogger(CustomBatchLogger, BaseAWSLLM): @@ -205,8 +204,9 @@ class SQSLogger(CustomBatchLogger, BaseAWSLLM): litellm.aws_sqs_callback_params.get("sqs_app_encryption_aad") or sqs_app_encryption_aad ) - self.app_crypto: Optional[AppCrypto] = None + self.app_crypto: Optional["AppCrypto"] = None if self.sqs_aws_use_application_level_encryption: + from litellm.litellm_core_utils.app_crypto import AppCrypto if not self.sqs_app_encryption_key_b64: raise ValueError("sqs_app_encryption_key_b64 is required when encryption is enabled.") key = base64.b64decode(self.sqs_app_encryption_key_b64) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 0e6324ac60b..03fc835ded9 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -12198,25 +12198,6 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "global.anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 5e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, "gpt-3.5-turbo": { "input_cost_per_token": 0.5e-06, "litellm_provider": "openai", @@ -23589,7 +23570,9 @@ "max_tokens": 2e6, "mode": "chat", "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, "output_cost_per_token": 0.5e-06, + "output_cost_per_token_above_128k_tokens": 1e-06, "cache_read_input_token_cost": 0.05e-06, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, @@ -23605,7 +23588,9 @@ "max_tokens": 2e6, "mode": "chat", "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, "output_cost_per_token": 0.5e-06, + "output_cost_per_token_above_128k_tokens": 1e-06, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_tool_choice": true, @@ -23613,12 +23598,14 @@ }, "xai/grok-4-0709": { "input_cost_per_token": 3e-06, + "input_cost_per_token_above_128k_tokens": 6e-06, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_128k_tokens": 30e-06, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_reasoning": true, @@ -23627,12 +23614,14 @@ }, "xai/grok-4-latest": { "input_cost_per_token": 3e-06, + "input_cost_per_token_above_128k_tokens": 6e-06, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_128k_tokens": 30e-06, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_reasoning": true,