scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-30 01:52:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 70

chore(cost-map): add openai gpt-6-astra ultrafast tier prices from the pricing page (#43745)

Browse source 
* chore(cost-map): add openai gpt-6-astra ultrafast tier prices from the pricing page

Price-Sync: litellm-providers

* feat(cost): support openai ultrafast tier fields in the model catalog

---------

Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
Co-authored-by: Kerry <kerry@berri.ai>
This commit is contained in:
berriai-litellm-provider-info-sync[bot] 2026-09-29 19:05:57 +00:00 • committed by GitHub
parent abc85c2651
commit f4a7c04d99
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 76 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
litellm-rust/crates/model-catalog/src/model_info.rs
View file

@ -57,6 +57,9 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_creation_input_token_cost_above_272k_tokens_priority: Option<f64>,
/// Ultrafast service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_creation_input_token_cost_above_272k_tokens_ultrafast: Option<f64>,
#[serde(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.
@ -65,6 +68,9 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_creation_input_token_cost_priority: Option<f64>,
/// Ultrafast service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_creation_input_token_cost_ultrafast: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_read_input_audio_token_cost: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
@ -101,6 +107,9 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_read_input_token_cost_above_272k_tokens_priority: Option<f64>,
/// Ultrafast service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_read_input_token_cost_above_272k_tokens_ultrafast: Option<f64>,
/// Rate applied once the prompt exceeds the token threshold in the field name.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_read_input_token_cost_above_512k_tokens: Option<f64>,
@ -115,6 +124,9 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_read_input_token_cost_priority: Option<f64>,
/// Ultrafast service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub cache_read_input_token_cost_ultrafast: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub citation_cost_per_token: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
@ -213,6 +225,9 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub input_cost_per_token_above_272k_tokens_priority: Option<f64>,
/// Ultrafast service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub input_cost_per_token_above_272k_tokens_ultrafast: Option<f64>,
/// Rate applied once the prompt exceeds the token threshold in the field name.
#[serde(skip_serializing_if = "Option::is_none")]
pub input_cost_per_token_above_512k_tokens: Option<f64>,
@ -230,6 +245,9 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub input_cost_per_token_priority: Option<f64>,
/// Ultrafast service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub input_cost_per_token_ultrafast: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub input_cost_per_video_per_second: Option<f64>,
/// Rate applied once the prompt exceeds the token threshold in the field name.
@ -362,6 +380,9 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub output_cost_per_token_above_272k_tokens_priority: Option<f64>,
/// Ultrafast service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub output_cost_per_token_above_272k_tokens_ultrafast: Option<f64>,
/// Rate applied once the prompt exceeds the token threshold in the field name.
#[serde(skip_serializing_if = "Option::is_none")]
pub output_cost_per_token_above_512k_tokens: Option<f64>,
@ -377,6 +398,9 @@ pub struct ModelInfo {
/// Priority service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub output_cost_per_token_priority: Option<f64>,
/// Ultrafast service-tier rate for the same-named base field.
#[serde(skip_serializing_if = "Option::is_none")]
pub output_cost_per_token_ultrafast: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub output_cost_per_video_per_second: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]

8
litellm/model_prices_and_context_window_backup.json
View file

@ -33870,16 +33870,22 @@
"cache_read_input_token_cost_above_272k_tokens_batches": 1e-06,
"cache_creation_input_token_cost_batches": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015,
"cache_creation_input_token_cost_ultrafast": 7.5e-05,
"cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05,
"cache_read_input_token_cost_flex": 5e-07,
"cache_read_input_token_cost_priority": 2e-06,
"cache_read_input_token_cost_ultrafast": 6e-06,
"input_cost_per_token": 1e-05,
"input_cost_per_token_above_272k_tokens": 2e-05,
"input_cost_per_token_above_272k_tokens_flex": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 4e-05,
"input_cost_per_token_batches": 5e-06,
"input_cost_per_token_above_272k_tokens_batches": 1e-05,
"input_cost_per_token_above_272k_tokens_ultrafast": 0.00012,
"input_cost_per_token_flex": 5e-06,
"input_cost_per_token_priority": 2e-05,
"input_cost_per_token_ultrafast": 6e-05,
"litellm_provider": "openai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -33891,8 +33897,10 @@
"output_cost_per_token_above_272k_tokens_priority": 0.00015,
"output_cost_per_token_batches": 2.5e-05,
"output_cost_per_token_above_272k_tokens_batches": 3.75e-05,
"output_cost_per_token_above_272k_tokens_ultrafast": 0.00045,
"output_cost_per_token_flex": 2.5e-05,
"output_cost_per_token_priority": 0.0001,
"output_cost_per_token_ultrafast": 0.0003,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"search_context_cost_per_query": {

8
model_prices_and_context_window.json
View file

@ -33870,16 +33870,22 @@
"cache_read_input_token_cost_above_272k_tokens_batches": 1e-06,
"cache_creation_input_token_cost_batches": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015,
"cache_creation_input_token_cost_ultrafast": 7.5e-05,
"cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05,
"cache_read_input_token_cost_flex": 5e-07,
"cache_read_input_token_cost_priority": 2e-06,
"cache_read_input_token_cost_ultrafast": 6e-06,
"input_cost_per_token": 1e-05,
"input_cost_per_token_above_272k_tokens": 2e-05,
"input_cost_per_token_above_272k_tokens_flex": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 4e-05,
"input_cost_per_token_batches": 5e-06,
"input_cost_per_token_above_272k_tokens_batches": 1e-05,
"input_cost_per_token_above_272k_tokens_ultrafast": 0.00012,
"input_cost_per_token_flex": 5e-06,
"input_cost_per_token_priority": 2e-05,
"input_cost_per_token_ultrafast": 6e-05,
"litellm_provider": "openai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -33891,8 +33897,10 @@
"output_cost_per_token_above_272k_tokens_priority": 0.00015,
"output_cost_per_token_batches": 2.5e-05,
"output_cost_per_token_above_272k_tokens_batches": 3.75e-05,
"output_cost_per_token_above_272k_tokens_ultrafast": 0.00045,
"output_cost_per_token_flex": 2.5e-05,
"output_cost_per_token_priority": 0.0001,
"output_cost_per_token_ultrafast": 0.0003,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"search_context_cost_per_query": {

36
model_prices_and_context_window.schema.json
View file

@ -133,6 +133,11 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"cache_creation_input_token_cost_above_272k_tokens_ultrafast": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_creation_input_token_cost_above_32k_tokens": {
"type": "number",
"minimum": 0,
@ -152,6 +157,10 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"cache_creation_input_token_cost_ultrafast": {
"type": "number",
"minimum": 0
},
"cache_read_input_audio_token_cost": {
"type": "number",
"minimum": 0
@ -210,6 +219,11 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"cache_read_input_token_cost_above_272k_tokens_ultrafast": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_read_input_token_cost_above_32k_tokens": {
"type": "number",
"minimum": 0,
@ -238,6 +252,10 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"cache_read_input_token_cost_ultrafast": {
"type": "number",
"minimum": 0
},
"citation_cost_per_token": {
"type": "number",
"minimum": 0
@ -404,6 +422,11 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"input_cost_per_token_above_272k_tokens_ultrafast": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"input_cost_per_token_above_32k_tokens": {
"type": "number",
"minimum": 0,
@ -437,6 +460,10 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"input_cost_per_token_ultrafast": {
"type": "number",
"minimum": 0
},
"input_cost_per_video_per_second": {
"type": "number",
"minimum": 0
@ -770,6 +797,11 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"output_cost_per_token_above_272k_tokens_ultrafast": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"output_cost_per_token_above_32k_tokens": {
"type": "number",
"minimum": 0,
@ -799,6 +831,10 @@
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"output_cost_per_token_ultrafast": {
"type": "number",
"minimum": 0
},
"output_cost_per_video_per_second": {
"type": "number",
"minimum": 0