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): declare above_32k cost fields on ModelInfo (#42856)

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

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(model-catalog): drop redundant comments on above_32k fields

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-09-23 19:40:09 -07:00 • committed by GitHub
parent 153f13b913
commit b0980638c5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 8 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
litellm-rust/crates/model-catalog/src/model_info.rs
View file

@ -245,6 +245,8 @@ pub struct ModelInfo {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub cache_creation_input_token_cost_above_272k_tokens_priority: Option<f64>,
#[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.
#[serde(default, skip_serializing_if = "Option::is_none")]
@ -283,6 +285,8 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub cache_read_input_token_cost_above_272k_tokens_priority: Option<f64>,
#[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>,
@ -377,6 +381,8 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub input_cost_per_token_above_272k_tokens_priority: Option<f64>,
#[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>,
@ -498,6 +504,8 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub output_cost_per_token_above_272k_tokens_priority: Option<f64>,
#[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>,