scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

Merge pull request #31740 from BerriAI/litellm_add-claude-sonnet-5-c71c

Browse source 
feat(anthropic): add Claude Sonnet 5
This commit is contained in:
yuneng-jiang 2026-06-30 13:14:44 -07:00 • committed by GitHub
commit 8beb68aa9f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 829 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
litellm/constants.py
View file

@ -1127,6 +1127,7 @@ BEDROCK_CONVERSE_MODELS = [
"anthropic.claude-haiku-4-5-20251001-v1:0",
"anthropic.claude-sonnet-4-5-20250929-v1:0",
"anthropic.claude-fable-5",
"anthropic.claude-sonnet-5",
"anthropic.claude-opus-4-8",
"anthropic.claude-opus-4-7",
"anthropic.claude-opus-4-6-v1:0",

322
litellm/model_prices_and_context_window_backup.json
View file

@ -1671,6 +1671,204 @@
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
"anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"global.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"us.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.125e-06,
"cache_creation_input_token_cost_above_1hr": 6.6e-06,
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"eu.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.125e-06,
"cache_creation_input_token_cost_above_1hr": 6.6e-06,
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"au.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.125e-06,
"cache_creation_input_token_cost_above_1hr": 6.6e-06,
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"jp.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.125e-06,
"cache_creation_input_token_cost_above_1hr": 6.6e-06,
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"anthropic.claude-sonnet-4-6": {
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 3.75e-06,
@ -2511,6 +2709,36 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure_ai/claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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
},
"azure_ai/claude-sonnet-4-6": {
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 3.75e-06,
@ -10245,6 +10473,40 @@
"supports_vision": true,
"supports_web_search": true
},
"claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"provider_specific_entry": {
"us": 1.1
},
"supports_output_config": true
},
"claude-sonnet-4-6": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
@ -34944,6 +35206,36 @@
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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
},
"vertex_ai/claude-sonnet-4-6": {
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 3.75e-06,
@ -42381,6 +42673,36 @@
"search_context_size_high": 0.035
}
},
"vertex_ai/claude-sonnet-5@default": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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
},
"vertex_ai/claude-sonnet-4-6@default": {
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 3.75e-06,

1
litellm/setup_wizard.py
View file

@ -58,6 +58,7 @@ PROVIDERS: List[Dict] = [
"test_model": "claude-haiku-4-5-20251001",
"models": [
"claude-fable-5",
"claude-sonnet-5",
"claude-opus-4-8",
"claude-opus-4-7",
"claude-opus-4-6",

322
model_prices_and_context_window.json
View file

@ -1671,6 +1671,204 @@
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
},
"anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"global.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"us.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.125e-06,
"cache_creation_input_token_cost_above_1hr": 6.6e-06,
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"eu.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.125e-06,
"cache_creation_input_token_cost_above_1hr": 6.6e-06,
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"au.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.125e-06,
"cache_creation_input_token_cost_above_1hr": 6.6e-06,
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"jp.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.125e-06,
"cache_creation_input_token_cost_above_1hr": 6.6e-06,
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh"
},
"anthropic.claude-sonnet-4-6": {
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 3.75e-06,
@ -2511,6 +2709,36 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure_ai/claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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
},
"azure_ai/claude-sonnet-4-6": {
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 3.75e-06,
@ -10245,6 +10473,40 @@
"supports_vision": true,
"supports_web_search": true
},
"claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"provider_specific_entry": {
"us": 1.1
},
"supports_output_config": true
},
"claude-sonnet-4-6": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
@ -35121,6 +35383,36 @@
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/claude-sonnet-5": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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
},
"vertex_ai/claude-sonnet-4-6": {
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 3.75e-06,
@ -42616,6 +42908,36 @@
"search_context_size_high": 0.035
}
},
"vertex_ai/claude-sonnet-5@default": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-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,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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
},
"vertex_ai/claude-sonnet-4-6@default": {
"supports_adaptive_thinking": true,
"cache_creation_input_token_cost": 3.75e-06,

7
tests/llm_translation/reasoning_effort_grid/grid_spec.py
View file

@ -181,6 +181,13 @@ ANTHROPIC_DIRECT_MODELS: Tuple[ModelEntry, ...] = (
required_env=_ANTHROPIC_REQ,
caps=_CAPS_XHIGH_MAX,
),
ModelEntry(
alias="claude-sonnet-5",
model="anthropic/claude-sonnet-5",
mode="adaptive",
required_env=_ANTHROPIC_REQ,
caps=_CAPS_XHIGH_MAX,
),
ModelEntry(
alias="claude-sonnet-4-6",
model="anthropic/claude-sonnet-4-6",

4
tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py
View file

@ -201,8 +201,8 @@ async def test_reasoning_effort_grid(
def test_grid_cell_count() -> None:
assert len(_PARAMS) == 29 * 11, (
f"expected 319 cells (29 provider x model combos x 11 efforts), "
assert len(_PARAMS) == 30 * 11, (
f"expected 330 cells (30 provider x model combos x 11 efforts), "
f"got {len(_PARAMS)}"
)

174
tests/test_litellm/test_claude_sonnet_5_config.py Normal file
View file

@ -0,0 +1,174 @@
"""
Validate Claude Sonnet 5 model configuration entries.
Sonnet 5 ships with the gen-5 adaptive-thinking profile (adaptive thinking
always on, no extended thinking, ``effort`` defaults to ``high``), so it must
mirror the sampling-param and prefill restrictions that Fable 5 / Opus 4.8 carry
rather than the older Sonnet 4.6 behavior. The cost-map entries are also what
populate ``litellm.anthropic_models`` at import, which is what lets a bare
``claude-sonnet-5`` name resolve to the ``anthropic`` provider (and match an
``anthropic/*`` wildcard deployment).
"""
import json
import os
import pytest
import litellm
from litellm.constants import BEDROCK_CONVERSE_MODELS
from litellm.litellm_core_utils.get_model_cost_map import GetModelCostMap
REPO_ROOT = os.path.join(os.path.dirname(__file__), "../..")
ALL_SONNET_5_VARIANTS = (
"claude-sonnet-5",
"anthropic.claude-sonnet-5",
"global.anthropic.claude-sonnet-5",
"us.anthropic.claude-sonnet-5",
"eu.anthropic.claude-sonnet-5",
"au.anthropic.claude-sonnet-5",
"jp.anthropic.claude-sonnet-5",
"vertex_ai/claude-sonnet-5",
"vertex_ai/claude-sonnet-5@default",
"azure_ai/claude-sonnet-5",
)
def _load_root_cost_map() -> dict:
json_path = os.path.join(REPO_ROOT, "model_prices_and_context_window.json")
with open(json_path) as f:
return json.load(f)
@pytest.fixture
def local_model_cost_map(monkeypatch):
"""Force the bundled backup cost map so assertions don't depend on the
network-fetched ``main`` copy (which lags this branch until merge)."""
original_model_cost = litellm.model_cost
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
litellm.model_cost = litellm.get_model_cost_map(url="")
litellm.get_model_info.cache_clear()
try:
yield
finally:
litellm.model_cost = original_model_cost
litellm.get_model_info.cache_clear()
def test_sonnet_5_pricing_and_capabilities():
model_data = _load_root_cost_map()
expected_providers = {
"claude-sonnet-5": "anthropic",
"anthropic.claude-sonnet-5": "bedrock_converse",
"vertex_ai/claude-sonnet-5": "vertex_ai-anthropic_models",
"azure_ai/claude-sonnet-5": "azure_ai",
}
for model_name, provider in expected_providers.items():
assert model_name in model_data, f"Missing model entry: {model_name}"
info = model_data[model_name]
assert info["litellm_provider"] == provider
assert info["mode"] == "chat"
assert info["max_input_tokens"] == 1000000
assert info["max_output_tokens"] == 128000
assert info["max_tokens"] == 128000
# Standard Sonnet pricing: $3 / $15 per MTok, with the 1.25x cache-write
# and 0.1x cache-read multipliers.
assert info["input_cost_per_token"] == 3e-06
assert info["output_cost_per_token"] == 1.5e-05
assert info["cache_creation_input_token_cost"] == 3.75e-06
assert info["cache_read_input_token_cost"] == 3e-07
# gen-5 adaptive-thinking profile: effort-driven, no sampling params, no
# assistant prefill.
assert info["supports_adaptive_thinking"] is True
assert info["supports_reasoning"] is True
assert info["supports_sampling_params"] is False
assert info["supports_assistant_prefill"] is False
assert info["supports_function_calling"] is True
assert info["supports_prompt_caching"] is True
assert info["supports_tool_choice"] is True
assert info["supports_vision"] is True
def test_sonnet_5_bedrock_regional_pricing():
"""Global/base endpoints use base pricing; the us./eu./au./jp. regional
cross-region inference profiles carry a 10% premium."""
model_data = _load_root_cost_map()
base_pricing = {
"input_cost_per_token": 3e-06,
"output_cost_per_token": 1.5e-05,
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
}
regional_pricing = {
"input_cost_per_token": 3.3e-06,
"output_cost_per_token": 1.65e-05,
"cache_creation_input_token_cost": 4.125e-06,
"cache_read_input_token_cost": 3.3e-07,
}
expected = {
"anthropic.claude-sonnet-5": base_pricing,
"global.anthropic.claude-sonnet-5": base_pricing,
"us.anthropic.claude-sonnet-5": regional_pricing,
"eu.anthropic.claude-sonnet-5": regional_pricing,
"au.anthropic.claude-sonnet-5": regional_pricing,
"jp.anthropic.claude-sonnet-5": regional_pricing,
}
for model_name, pricing in expected.items():
assert model_name in model_data, f"Missing model entry: {model_name}"
info = model_data[model_name]
assert info["litellm_provider"] == "bedrock_converse"
assert info["bedrock_output_config_effort_ceiling"] == "xhigh"
for key, value in pricing.items():
assert info[key] == value, f"{model_name}.{key} = {info[key]}, want {value}"
def test_sonnet_5_present_in_bundled_backup():
"""The bundled backup is the runtime fallback (and what tests load with
``LITELLM_LOCAL_MODEL_COST_MAP=True``); it must carry the same entries as the
root cost map, otherwise the model resolves on one path but not the other."""
backup = GetModelCostMap.load_local_model_cost_map()
for model_name in ALL_SONNET_5_VARIANTS:
assert model_name in backup, f"Missing from backup cost map: {model_name}"
def test_sonnet_5_registered_for_bedrock_converse():
assert "anthropic.claude-sonnet-5" in BEDROCK_CONVERSE_MODELS
def test_sonnet_5_provider_resolves_via_model_info(local_model_cost_map):
"""Regression: ``claude-sonnet-5`` must resolve to provider ``anthropic``.
Before the cost-map entry existed, the model was unknown to LiteLLM, so it
could not be tied to the ``anthropic`` provider and an ``anthropic/*``
wildcard deployment would not match it."""
info = litellm.get_model_info(model="claude-sonnet-5")
assert info["litellm_provider"] == "anthropic"
assert info["max_input_tokens"] == 1000000
assert info["max_output_tokens"] == 128000
@pytest.mark.parametrize(
"cost_map",
[_load_root_cost_map(), GetModelCostMap.load_local_model_cost_map()],
ids=["root", "bundled_backup"],
)
def test_sonnet_5_all_variants_carry_adaptive_thinking_flag(cost_map):
"""Every Sonnet 5 entry must advertise ``supports_adaptive_thinking``.
Adaptive-thinking detection is cost-map driven, so a single variant missing
the flag silently sends the legacy ``thinking.type='enabled'`` shape and the
provider 400s. This guards against a future variant being added without it."""
variants = [k for k in cost_map if "claude-sonnet-5" in k]
assert variants, "no claude-sonnet-5 entries found in cost map"
missing = [k for k in variants if cost_map[k].get("supports_adaptive_thinking") is not True]
assert not missing, f"missing supports_adaptive_thinking: {missing}"