scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-26 01:12:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 98

fix(model-catalog): add above_32k cost fields to ModelInfo round-trip

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-09-24 01:26:32 +00:00
parent efc36b96ac
commit c71d5a3de3
1 changed files with 12 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
litellm-rust/crates/model-catalog/src/model_info.rs
View file

@ -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<f64>,
/// 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<f64>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub cache_creation_input_token_cost_batches: Option<f64>,
/// 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<f64>,
/// 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<f64>,
/// 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<f64>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub cache_read_input_token_cost_batches: Option<f64>,
@ -379,6 +385,9 @@ pub struct ModelInfo {
pub input_cost_per_token_above_272k_tokens_priority: Option<f64>,
/// 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<f64>,
/// 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<f64>,
/// 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<f64>,
/// 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<f64>,
/// 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<f64>,
/// USD per generated token via the provider's batch API.
#[serde(default, skip_serializing_if = "Option::is_none")]