scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 115

feat(types): declare above_100k_tokens price fields on ModelInfoBase

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
kerry 2026-10-07 19:07:36 +00:00
parent 1c6f714187
commit 186f6c81a0
1 changed files with 9 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
litellm/types/utils.py
View file

@ -291,6 +291,8 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_token_ultrafast: ReadOnly[float | None] # OpenAI ultrafast service tier pricing
cache_creation_input_token_cost: float | None
cache_creation_input_token_cost_above_200k_tokens: float | None
cache_creation_input_token_cost_above_100k_tokens: float | None
cache_creation_input_token_cost_above_1hr_above_100k_tokens: float | None
cache_creation_input_token_cost_above_272k_tokens: float | None
cache_creation_input_token_cost_above_272k_tokens_priority: float | None
cache_creation_input_token_cost_above_272k_tokens_flex: float | None
@ -307,6 +309,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
cache_read_input_token_cost_balanced: ReadOnly[float | None]
cache_read_input_token_cost_ultrafast: ReadOnly[float | None] # OpenAI ultrafast service tier pricing
cache_read_input_token_cost_above_200k_tokens: float | None
cache_read_input_token_cost_above_100k_tokens: float | None
cache_read_input_token_cost_above_200k_tokens_priority: float | None
cache_read_input_token_cost_above_272k_tokens: float | None
cache_read_input_token_cost_above_272k_tokens_priority: float | None
@ -315,9 +318,11 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
cache_read_input_token_cost_above_512k_tokens: float | None
cache_read_input_token_cost_batches: ReadOnly[float | None]
cache_read_input_token_cost_above_200k_tokens_batches: ReadOnly[float | None]
cache_read_input_token_cost_above_100k_tokens_batches: ReadOnly[float | None]
cache_read_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None]
cache_creation_input_token_cost_batches: ReadOnly[float | None]
cache_creation_input_token_cost_above_200k_tokens_batches: ReadOnly[float | None]
cache_creation_input_token_cost_above_100k_tokens_batches: ReadOnly[float | None]
cache_creation_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None]
# Smallest prefix this model will actually cache, whatever caching mechanism its provider uses.
# Absent means the provider-agnostic default applies; see MINIMUM_PROMPT_CACHE_TOKEN_COUNT.
@ -327,6 +332,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_audio_token: float | None
input_cost_per_token_above_128k_tokens: float | None # only for vertex ai models
input_cost_per_token_above_200k_tokens: float | None # only for vertex ai gemini-2.5-pro models
input_cost_per_token_above_100k_tokens: float | None
input_cost_per_token_above_200k_tokens_priority: float | None
input_cost_per_token_above_272k_tokens: float | None # GPT-5.4/5.4-pro: prompts >272K priced at 2x input
input_cost_per_token_above_272k_tokens_priority: float | None
@ -347,9 +353,11 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_token_batches: float | None
input_cost_per_video_token_batches: ReadOnly[float | None]
input_cost_per_token_above_200k_tokens_batches: ReadOnly[float | None]
input_cost_per_token_above_100k_tokens_batches: ReadOnly[float | None]
input_cost_per_token_above_272k_tokens_batches: ReadOnly[float | None]
output_cost_per_token_batches: float | None
output_cost_per_token_above_200k_tokens_batches: ReadOnly[float | None]
output_cost_per_token_above_100k_tokens_batches: ReadOnly[float | None]
output_cost_per_token_above_272k_tokens_batches: ReadOnly[float | None]
output_cost_per_token: Required[float | None]
output_cost_per_token_flex: float | None # OpenAI flex service tier pricing
@ -369,6 +377,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
output_cost_per_audio_token: float | None
output_cost_per_token_above_128k_tokens: float | None # only for vertex ai models
output_cost_per_token_above_200k_tokens: float | None # only for vertex ai gemini-2.5-pro models
output_cost_per_token_above_100k_tokens: float | None
output_cost_per_token_above_200k_tokens_priority: float | None
output_cost_per_token_above_272k_tokens: float | None # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output
output_cost_per_token_above_272k_tokens_priority: float | None