tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-21 08:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(bedrock): add bedrock mantle gemma 4 models (#30264)

Browse Source 
* feat(bedrock): add bedrock mantle gemma 4 models

* test(bedrock): harden mantle local cost fixture
This commit is contained in:
Emerson Gomes
2026-06-12 16:04:55 +05:30
committed by Sameer Kankute
parent 1fd8ab4c5f
commit 73781d9a54
3 changed files with 150 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+42
View File
@@ -41753,6 +41753,48 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/google.gemma-4-31b": {
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/google.gemma-4-26b-a4b": {
"input_cost_per_token": 1.3e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/google.gemma-4-e2b": {
"input_cost_per_token": 4e-08,
"output_cost_per_token": 8e-08,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"volcengine/doubao-seed-2-0-pro-260215": {
"litellm_provider": "volcengine",
"max_input_tokens": 256000,
model_prices_and_context_window.json
+42
View File
@@ -41793,6 +41793,48 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/google.gemma-4-31b": {
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/google.gemma-4-26b-a4b": {
"input_cost_per_token": 1.3e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/google.gemma-4-e2b": {
"input_cost_per_token": 4e-08,
"output_cost_per_token": 8e-08,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"volcengine/doubao-seed-2-0-pro-260215": {
"litellm_provider": "volcengine",
"max_input_tokens": 256000,
tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_transformation.py
+66
View File
@@ -20,6 +20,23 @@ from litellm.llms.bedrock_mantle.chat.transformation import BedrockMantleChatCon
from litellm.types.utils import LlmProviders
@pytest.fixture
def local_cost_map(monkeypatch):
original_model_cost = litellm.model_cost
original_bedrock_mantle_models = set(litellm.bedrock_mantle_models)
try:
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "true")
litellm.model_cost = litellm.get_model_cost_map(url="")
litellm.get_model_info.cache_clear()
litellm.add_known_models()
yield
finally:
litellm.model_cost = original_model_cost
litellm.bedrock_mantle_models.clear()
litellm.bedrock_mantle_models.update(original_bedrock_mantle_models)
litellm.get_model_info.cache_clear()
class TestBedrockMantleProviderRegistration:
def test_provider_enum_exists(self):
assert LlmProviders.BEDROCK_MANTLE == "bedrock_mantle"
@@ -245,3 +262,52 @@ class TestBedrockMantlePricing:
litellm.add_known_models()
info = litellm.get_model_info("bedrock_mantle/openai.gpt-oss-120b")
assert info["max_input_tokens"] == 131072
@pytest.mark.parametrize(
"model_id,input_cost,output_cost,max_tokens",
[
("google.gemma-4-31b", 1.4e-07, 4e-07, 256000),
("google.gemma-4-26b-a4b", 1.3e-07, 4e-07, 256000),
("google.gemma-4-e2b", 4e-08, 8e-08, 128000),
],
)
def test_gemma_4_bedrock_mantle_model_metadata(
local_cost_map, model_id, input_cost, output_cost, max_tokens
):
full_model_name = f"bedrock_mantle/{model_id}"
info = litellm.get_model_info(full_model_name)
assert info["mode"] == "chat"
assert info["input_cost_per_token"] == pytest.approx(input_cost)
assert info["output_cost_per_token"] == pytest.approx(output_cost)
assert info["max_input_tokens"] == max_tokens
assert info["max_output_tokens"] == max_tokens
assert info["supports_function_calling"] is True
assert info["supports_reasoning"] is True
assert info["supports_tool_choice"] is True
assert info["supports_vision"] is True
assert (
litellm.supports_parallel_function_calling(
model=full_model_name, custom_llm_provider="bedrock_mantle"
)
is False
)
@pytest.mark.parametrize(
"model_id",
[
"google.gemma-4-31b",
"google.gemma-4-26b-a4b",
"google.gemma-4-e2b",
],
)
def test_gemma_4_models_register_under_bedrock_mantle(local_cost_map, model_id):
full_model_name = f"bedrock_mantle/{model_id}"
assert full_model_name in litellm.bedrock_mantle_models
resolved_model, provider, _, _ = litellm.get_llm_provider(full_model_name)
assert provider == "bedrock_mantle"
assert resolved_model == model_id