scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-24 00:52:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 91

feat(cost-map): add Claude Opus 5.5 for Vertex AI and Azure AI (#42599)

Browse source 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-09-22 21:48:07 +00:00 • committed by GitHub
parent f7ae9efad2
commit d31e8aac6d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 242 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

107
litellm/model_prices_and_context_window_backup.json
View file

@ -3527,6 +3527,41 @@
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"azure_ai/claude-opus-5-5": {
"supports_mid_conversation_system": true,
"input_cost_per_token": 4e-06,
"output_cost_per_token": 2e-05,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_1hr": 8e-06,
"cache_read_input_token_cost": 2e-07,
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_forced_tool_use": false,
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"azure_ai/claude-opus-4-8": {
"deprecation_date": "2027-09-01",
"supports_mid_conversation_system": true,
@ -47016,6 +47051,78 @@
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"vertex_ai/claude-opus-5-5": {
"regional_endpoint_uplift_multiplier": 1.1,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_1hr": 8e-06,
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 4e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_forced_tool_use": false,
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"vertex_ai/claude-opus-5-5@default": {
"regional_endpoint_uplift_multiplier": 1.1,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_1hr": 8e-06,
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 4e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_forced_tool_use": false,
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"vertex_ai/claude-opus-4-8": {
"deprecation_date": "2027-05-28",
"regional_endpoint_uplift_multiplier": 1.1,

107
model_prices_and_context_window.json
View file

@ -3527,6 +3527,41 @@
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"azure_ai/claude-opus-5-5": {
"supports_mid_conversation_system": true,
"input_cost_per_token": 4e-06,
"output_cost_per_token": 2e-05,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_1hr": 8e-06,
"cache_read_input_token_cost": 2e-07,
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_forced_tool_use": false,
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"azure_ai/claude-opus-4-8": {
"deprecation_date": "2027-09-01",
"supports_mid_conversation_system": true,
@ -47016,6 +47051,78 @@
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"vertex_ai/claude-opus-5-5": {
"regional_endpoint_uplift_multiplier": 1.1,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_1hr": 8e-06,
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 4e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_forced_tool_use": false,
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"vertex_ai/claude-opus-5-5@default": {
"regional_endpoint_uplift_multiplier": 1.1,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_1hr": 8e-06,
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 4e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"thinking_always_on": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_forced_tool_use": false,
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"prompt_cache_min_tokens": 512
},
"vertex_ai/claude-opus-4-8": {
"deprecation_date": "2027-05-28",
"regional_endpoint_uplift_multiplier": 1.1,

36
tests/test_litellm/test_claude_opus_5_config.py
View file

@ -41,7 +41,10 @@ ALL_OPUS_5_VARIANTS = (
"jp.anthropic.claude-opus-5",
"vertex_ai/claude-opus-5",
"vertex_ai/claude-opus-5@default",
"vertex_ai/claude-opus-5-5",
"vertex_ai/claude-opus-5-5@default",
"azure_ai/claude-opus-5",
"azure_ai/claude-opus-5-5",
)
BEDROCK_OPUS_5_VARIANTS = (
@ -69,20 +72,37 @@ def test_opus_5_registered_for_bedrock_converse():
assert "anthropic.claude-opus-5" in BEDROCK_CONVERSE_MODELS
def test_opus_5_5_present_in_bundled_backup():
OPUS_5_5_VARIANTS = (
"claude-opus-5-5",
"vertex_ai/claude-opus-5-5",
"vertex_ai/claude-opus-5-5@default",
"azure_ai/claude-opus-5-5",
)
@pytest.mark.parametrize("model_name", OPUS_5_5_VARIANTS)
def test_opus_5_5_present_in_bundled_backup(model_name):
backup = GetModelCostMap.load_local_model_cost_map()
root = _load_root_cost_map()
assert "claude-opus-5-5" in backup
assert "claude-opus-5-5" in root
assert backup["claude-opus-5-5"] == root["claude-opus-5-5"]
assert model_name in backup
assert model_name in root
assert backup[model_name] == root[model_name]
@pytest.mark.parametrize("model", ["claude-opus-5-5", "anthropic/claude-opus-5-5"])
def test_opus_5_5_thinking_profile(local_model_cost_map, model):
@pytest.mark.parametrize(
("model", "provider"),
[
("claude-opus-5-5", "anthropic"),
("anthropic/claude-opus-5-5", "anthropic"),
("vertex_ai/claude-opus-5-5", "vertex_ai"),
("azure_ai/claude-opus-5-5", "azure_ai"),
],
)
def test_opus_5_5_thinking_profile(local_model_cost_map, model, provider):
"""Opus 5.5 has thinking always on with the adaptive thinking surface, and
no forced tool use, same as Fable 5.1."""
from litellm.llms.anthropic.common_utils import AnthropicModelInfo
assert AnthropicModelInfo._is_adaptive_thinking_model(model, "anthropic") is True
assert AnthropicModelInfo._is_always_on_thinking_model(model, "anthropic") is True
assert AnthropicModelInfo._is_adaptive_thinking_model(model, provider) is True
assert AnthropicModelInfo._is_always_on_thinking_model(model, provider) is True
assert AnthropicModelInfo.forced_tool_use_unsupported(model.removeprefix("anthropic/")) is True