scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-21 00:21:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 74

fix: set vertex gemma-4-26b-a4b-it-maas context window to 262144

Browse source
This commit is contained in:
mateo-berri 2026-09-18 14:58:58 -07:00
parent a6bd779bd1
commit 55249c7128
3 changed files with 13 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/model_prices_and_context_window_backup.json
View file

@ -50721,7 +50721,7 @@
"vertex_ai/google/gemma-4-26b-a4b-it-maas": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai-openai_models",
"max_input_tokens": 256000,
"max_input_tokens": 262144,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",

2
model_prices_and_context_window.json
View file

@ -50721,7 +50721,7 @@
"vertex_ai/google/gemma-4-26b-a4b-it-maas": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai-openai_models",
"max_input_tokens": 256000,
"max_input_tokens": 262144,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",

12
tests/test_litellm/llms/vertex_ai/vertex_ai_partner_models/gemma/test_vertex_ai_gemma_global_endpoint.py
View file

@ -30,7 +30,7 @@ from litellm.types.llms.vertex_ai import VertexPartnerProvider
_GEMMA_MODEL_COST_ENTRY = {
"vertex_ai/google/gemma-4-26b-a4b-it-maas": {
"litellm_provider": "vertex_ai-openai_models",
"max_input_tokens": 256000,
"max_input_tokens": 262144,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -180,6 +180,16 @@ class TestCreateVertexURLGemma:
# ---------------------------------------------------------------------------
def test_gemma_maas_context_window_matches_google(monkeypatch):
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
info = litellm.get_model_info("vertex_ai/google/gemma-4-26b-a4b-it-maas")
assert info["max_input_tokens"] == 262144
assert info["max_output_tokens"] == 128000
# ---------------------------------------------------------------------------
# Integration tests: verify payloads reach the global OpenAI endpoint
#