scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

Merge pull request #33796 from BerriAI/litellm_fireworks_glm5p2_cache_read

Browse source 
fix(fireworks_ai): correct glm-5p2 prompt-cache read price to $0.14/1M
This commit is contained in:
tin-berri 2026-07-17 20:13:04 -07:00 • committed by GitHub
commit 3829fa3014
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 9 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/model_prices_and_context_window_backup.json
View file

@ -16272,7 +16272,7 @@
"supports_vision": false
},
"fireworks_ai/accounts/fireworks/models/glm-5p2": {
"cache_read_input_token_cost": 2.6e-07,
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
@ -16686,7 +16686,7 @@
"supports_vision": false
},
"fireworks_ai/glm-5p2": {
"cache_read_input_token_cost": 2.6e-07,
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,

4
model_prices_and_context_window.json
View file

@ -16272,7 +16272,7 @@
"supports_vision": false
},
"fireworks_ai/accounts/fireworks/models/glm-5p2": {
"cache_read_input_token_cost": 2.6e-07,
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
@ -16686,7 +16686,7 @@
"supports_vision": false
},
"fireworks_ai/glm-5p2": {
"cache_read_input_token_cost": 2.6e-07,
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,

5
tests/test_litellm/llms/fireworks_ai/test_fireworks_ai_cost_calculator.py
View file

@ -5,12 +5,15 @@ import pytest
sys.path.insert(0, os.path.abspath("../../../../.."))
import litellm
from litellm.llms.fireworks_ai.cost_calculator import cost_per_token
from litellm.types.utils import PromptTokensDetailsWrapper, Usage
MODEL = "accounts/fireworks/models/glm-5p2"
INPUT_COST = 1.4e-06
CACHE_READ_COST = 2.6e-07
# Read the cached rate from the price map so this test tracks the shipped value
# (glm-5p2 is $0.14/1M) instead of hardcoding a number that breaks when it changes.
CACHE_READ_COST = litellm.get_model_info(model=MODEL, custom_llm_provider="fireworks_ai")["cache_read_input_token_cost"]
OUTPUT_COST = 4.4e-06

2
tests/test_litellm/test_utils.py
View file

@ -4317,7 +4317,7 @@ _FIREWORKS_MODELS = [
"accounts/fireworks/models/glm-5p2",
1.4e-06,
4.4e-06,
2.6e-07,
1.4e-07,
1048576,
131072,
False,