scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_fix_responses_reasoning_items

Browse source
This commit is contained in:
Devin AI 2026-07-15 19:04:12 +00:00
commit e8c014362c
3 changed files with 201 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

84
litellm/model_prices_and_context_window_backup.json
View file

@ -44261,6 +44261,90 @@
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-5.6-sol": {
"input_cost_per_token": 5.5e-06,
"cache_creation_input_token_cost": 6.875e-06,
"cache_read_input_token_cost": 5.5e-07,
"output_cost_per_token": 3.3e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.6-terra": {
"input_cost_per_token": 2.75e-06,
"cache_creation_input_token_cost": 3.4375e-06,
"cache_read_input_token_cost": 2.75e-07,
"output_cost_per_token": 1.65e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.6-luna": {
"input_cost_per_token": 1.1e-06,
"cache_creation_input_token_cost": 1.375e-06,
"cache_read_input_token_cost": 1.1e-07,
"output_cost_per_token": 6.6e-06,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.5": {
"input_cost_per_token": 5.5e-06,
"cache_read_input_token_cost": 5.5e-07,

84
model_prices_and_context_window.json
View file

@ -44382,6 +44382,90 @@
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-5.6-sol": {
"input_cost_per_token": 5.5e-06,
"cache_creation_input_token_cost": 6.875e-06,
"cache_read_input_token_cost": 5.5e-07,
"output_cost_per_token": 3.3e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.6-terra": {
"input_cost_per_token": 2.75e-06,
"cache_creation_input_token_cost": 3.4375e-06,
"cache_read_input_token_cost": 2.75e-07,
"output_cost_per_token": 1.65e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.6-luna": {
"input_cost_per_token": 1.1e-06,
"cache_creation_input_token_cost": 1.375e-06,
"cache_read_input_token_cost": 1.1e-07,
"output_cost_per_token": 6.6e-06,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.5": {
"input_cost_per_token": 5.5e-06,
"cache_read_input_token_cost": 5.5e-07,

33
tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py
View file

@ -397,6 +397,20 @@ class TestBedrockMantleResponsesRegistry:
assert isinstance(cfg, BedrockMantleResponsesAPIConfig)
assert cfg.use_openai_path is True
@pytest.mark.parametrize(
"model",
["openai.gpt-5.6-sol", "openai.gpt-5.6-terra", "openai.gpt-5.6-luna"],
)
def test_registry_returns_config_for_gpt_5_6_family(self, local_cost_map, model):
from litellm.utils import ProviderConfigManager
cfg = ProviderConfigManager.get_provider_responses_api_config(
provider="bedrock_mantle",
model=model,
)
assert isinstance(cfg, BedrockMantleResponsesAPIConfig)
assert cfg.use_openai_path is True
def test_registry_returns_native_config_for_gpt_oss(self, local_cost_map):
# Core regression: gpt-oss-120b supports the native Responses API (AWS
# model card), so it must get a BedrockMantleResponsesAPIConfig on the
@ -1237,6 +1251,25 @@ class TestBedrockMantleResponsesPricing:
assert info["cache_read_input_token_cost"] == pytest.approx(2.75e-07)
assert info["max_input_tokens"] == 272000
@pytest.mark.parametrize(
"model, input_cost, cache_creation_cost, cache_read_cost, output_cost",
[
("openai.gpt-5.6-sol", 5.5e-06, 6.875e-06, 5.5e-07, 3.3e-05),
("openai.gpt-5.6-terra", 2.75e-06, 3.4375e-06, 2.75e-07, 1.65e-05),
("openai.gpt-5.6-luna", 1.1e-06, 1.375e-06, 1.1e-07, 6.6e-06),
],
)
def test_gpt_5_6_pricing_and_mode(
self, local_cost_map, model, input_cost, cache_creation_cost, cache_read_cost, output_cost
):
info = litellm.get_model_info(f"bedrock_mantle/{model}")
assert info["mode"] == "responses"
assert info["input_cost_per_token"] == pytest.approx(input_cost)
assert info["cache_creation_input_token_cost"] == pytest.approx(cache_creation_cost)
assert info["cache_read_input_token_cost"] == pytest.approx(cache_read_cost)
assert info["output_cost_per_token"] == pytest.approx(output_cost)
assert info["max_input_tokens"] == 272000
def test_models_registered(self, local_cost_map):
assert "bedrock_mantle/openai.gpt-5.5" in litellm.bedrock_mantle_models
assert "bedrock_mantle/openai.gpt-5.4" in litellm.bedrock_mantle_models