scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-13 03:59:12 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 66

test(cost): add tier 1 Claude 5 and gpt-6 native cost cases (#46124)

Browse source 
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-10-13 01:18:41 +00:00 • committed by GitHub
parent f97d3df6de
commit 9720aefc8e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 6828 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1790
tests/integration/cost_calculation/cases/anthropic.py
View file

File diff suppressed because it is too large Load diff

1557
tests/integration/cost_calculation/cases/azure.py
View file

File diff suppressed because it is too large Load diff

1797
tests/integration/cost_calculation/cases/bedrock_converse.py
View file

File diff suppressed because it is too large Load diff

1454
tests/integration/cost_calculation/cases/openai.py
View file

File diff suppressed because it is too large Load diff

230
tests/integration/cost_calculation/cost_map.py
View file

@ -33,6 +33,10 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
"output_cost_per_token": 1.6e-05,
},
"gpt-6-luna": {
"output_cost_per_token_priority": 1e-06,
"input_cost_per_token_priority": 2e-07,
"output_cost_per_token_flex": 2.5e-07,
"input_cost_per_token_flex": 5e-08,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_decisions": 1e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
@ -787,6 +791,7 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
"supports_function_calling": True,
},
"us.anthropic.claude-opus-5-5": {
"cache_creation_input_token_cost_above_1hr": 8.8e-06,
"litellm_provider": "bedrock_converse",
"mode": "chat",
"input_cost_per_token": 4.4e-06,
@ -799,6 +804,7 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
"supports_function_calling": True,
},
"claude-opus-5-5": {
"cache_creation_input_token_cost_above_1hr": 8e-06,
"litellm_provider": "anthropic",
"mode": "chat",
"input_cost_per_token": 4e-06,
@ -811,6 +817,10 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
"supports_function_calling": True,
},
"gpt-6.1-sol": {
"output_cost_per_token_priority": 2e-05,
"input_cost_per_token_priority": 4e-06,
"output_cost_per_token_flex": 5e-06,
"input_cost_per_token_flex": 1e-06,
"litellm_provider": "openai",
"mode": "chat",
"input_cost_per_token": 2e-06,
@ -821,4 +831,224 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
"max_output_tokens": 128000,
"supports_function_calling": True,
},
"claude-sonnet-5-5": {
"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": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-05,
"supports_function_calling": True,
},
"claude-haiku-5-5": {
"cache_creation_input_token_cost": 1.375e-06,
"cache_creation_input_token_cost_above_1hr": 2.2e-06,
"cache_read_input_token_cost": 1.1e-07,
"input_cost_per_token": 1.1e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.5e-06,
"supports_function_calling": True,
},
"claude-fable-5": {
"cache_creation_input_token_cost": 1.875e-05,
"cache_creation_input_token_cost_above_1hr": 3e-05,
"cache_read_input_token_cost": 1.5e-06,
"input_cost_per_token": 1.5e-05,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.5e-05,
"supports_function_calling": True,
},
"claude-fable-5-1": {
"cache_creation_input_token_cost": 2e-05,
"cache_creation_input_token_cost_above_1hr": 3.2e-05,
"cache_read_input_token_cost": 1.6e-06,
"input_cost_per_token": 1.6e-05,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 8e-05,
"supports_function_calling": True,
},
"us.anthropic.claude-sonnet-5": {
"cache_creation_input_token_cost": 4.5e-06,
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
"cache_read_input_token_cost": 3.6e-07,
"input_cost_per_token": 3.6e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.8e-05,
"supports_function_calling": True,
},
"us.anthropic.claude-sonnet-5-5": {
"cache_creation_input_token_cost": 4.625e-06,
"cache_creation_input_token_cost_above_1hr": 7.4e-06,
"cache_read_input_token_cost": 3.7e-07,
"input_cost_per_token": 3.7e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.85e-05,
"supports_function_calling": True,
},
"us.anthropic.claude-opus-5": {
"cache_creation_input_token_cost": 7.5e-06,
"cache_creation_input_token_cost_above_1hr": 1.2e-05,
"cache_read_input_token_cost": 6e-07,
"input_cost_per_token": 6e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"supports_function_calling": True,
},
"us.anthropic.claude-haiku-5-5": {
"cache_creation_input_token_cost": 1.5e-06,
"cache_creation_input_token_cost_above_1hr": 2.4e-06,
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 1.2e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"supports_function_calling": True,
},
"us.anthropic.claude-fable-5": {
"cache_creation_input_token_cost": 2.125e-05,
"cache_creation_input_token_cost_above_1hr": 3.4e-05,
"cache_read_input_token_cost": 1.7e-06,
"input_cost_per_token": 1.7e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 8.5e-05,
"supports_function_calling": True,
},
"us.anthropic.claude-fable-5-1": {
"cache_creation_input_token_cost": 2.25e-05,
"cache_creation_input_token_cost_above_1hr": 3.6e-05,
"cache_read_input_token_cost": 1.8e-06,
"input_cost_per_token": 1.8e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 9e-05,
"supports_function_calling": True,
},
"gpt-6-sol": {
"cache_read_input_token_cost": 2.2e-07,
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_flex": 1.1e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "openai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_flex": 5.5e-06,
"output_cost_per_token_priority": 2.2e-05,
"supports_function_calling": True,
},
"gpt-6-astra": {
"cache_read_input_token_cost": 1.2e-06,
"input_cost_per_token": 1.2e-05,
"input_cost_per_token_flex": 6e-06,
"input_cost_per_token_priority": 2.4e-05,
"litellm_provider": "openai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-05,
"output_cost_per_token_flex": 3e-05,
"output_cost_per_token_priority": 0.00012,
"supports_function_calling": True,
},
"azure/gpt-6-sol": {
"cache_read_input_token_cost": 2.3e-07,
"input_cost_per_token": 2.3e-06,
"input_cost_per_token_flex": 1.15e-06,
"input_cost_per_token_priority": 4.6e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.15e-05,
"output_cost_per_token_flex": 5.75e-06,
"output_cost_per_token_priority": 2.3e-05,
"supports_function_calling": True,
},
"azure/gpt-6-luna": {
"cache_read_input_token_cost": 1.3e-08,
"input_cost_per_token": 1.3e-07,
"input_cost_per_token_flex": 6.5e-08,
"input_cost_per_token_priority": 2.6e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.5e-07,
"output_cost_per_token_flex": 3.25e-07,
"output_cost_per_token_priority": 1.3e-06,
"supports_function_calling": True,
},
"azure/gpt-6-astra": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 1.25e-05,
"input_cost_per_token_flex": 6.25e-06,
"input_cost_per_token_priority": 2.5e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.25e-05,
"output_cost_per_token_flex": 3.125e-05,
"output_cost_per_token_priority": 0.000125,
"supports_function_calling": True,
},
"azure/gpt-6.1-sol": {
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 2.4e-06,
"input_cost_per_token_flex": 1.2e-06,
"input_cost_per_token_priority": 4.8e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_flex": 6e-06,
"output_cost_per_token_priority": 2.4e-05,
"supports_function_calling": True,
},
}