diff --git a/litellm-rust/crates/model-catalog/src/model_info.rs b/litellm-rust/crates/model-catalog/src/model_info.rs index 77a8b768e38..7eb12cdaff4 100644 --- a/litellm-rust/crates/model-catalog/src/model_info.rs +++ b/litellm-rust/crates/model-catalog/src/model_info.rs @@ -244,6 +244,9 @@ pub struct ModelInfo { /// Priority service-tier rate for the same-named base field. #[serde(default, skip_serializing_if = "Option::is_none")] pub cache_creation_input_token_cost_above_272k_tokens_priority: Option, + /// Rate applied once the prompt exceeds the token threshold in the field name. + #[serde(default, skip_serializing_if = "Option::is_none")] + pub cache_creation_input_token_cost_above_32k_tokens: Option, #[serde(default, skip_serializing_if = "Option::is_none")] pub cache_creation_input_token_cost_batches: Option, /// Flex service-tier rate for the same-named base field. @@ -285,6 +288,9 @@ pub struct ModelInfo { pub cache_read_input_token_cost_above_272k_tokens_priority: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(default, skip_serializing_if = "Option::is_none")] + pub cache_read_input_token_cost_above_32k_tokens: Option, + /// Rate applied once the prompt exceeds the token threshold in the field name. + #[serde(default, skip_serializing_if = "Option::is_none")] pub cache_read_input_token_cost_above_512k_tokens: Option, #[serde(default, skip_serializing_if = "Option::is_none")] pub cache_read_input_token_cost_batches: Option, @@ -379,6 +385,9 @@ pub struct ModelInfo { pub input_cost_per_token_above_272k_tokens_priority: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(default, skip_serializing_if = "Option::is_none")] + pub input_cost_per_token_above_32k_tokens: Option, + /// Rate applied once the prompt exceeds the token threshold in the field name. + #[serde(default, skip_serializing_if = "Option::is_none")] pub input_cost_per_token_above_512k_tokens: Option, /// USD per prompt token via the provider's batch API. #[serde(default, skip_serializing_if = "Option::is_none")] @@ -500,6 +509,9 @@ pub struct ModelInfo { pub output_cost_per_token_above_272k_tokens_priority: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(default, skip_serializing_if = "Option::is_none")] + pub output_cost_per_token_above_32k_tokens: Option, + /// Rate applied once the prompt exceeds the token threshold in the field name. + #[serde(default, skip_serializing_if = "Option::is_none")] pub output_cost_per_token_above_512k_tokens: Option, /// USD per generated token via the provider's batch API. #[serde(default, skip_serializing_if = "Option::is_none")]