scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-07 07:58:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 150

test(cost): sync Azure GPT flex price fields with the real cost map (#50410)

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] 2026-11-06 09:33:52 -08:00 • committed by GitHub
parent ddd162439f
commit 6e66b8281f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 20 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
tests/integration/cost_calculation/cost_map.py
View file

@ -1603,32 +1603,44 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
},
"azure/gpt-6-luna": {
"cache_read_input_token_cost": 1.3e-08,
"cache_read_input_token_cost_flex": 6.5e-09,
"cache_creation_input_token_cost": 1.625e-07,
"cache_creation_input_token_cost_flex": 8.125e-08,
"cache_creation_input_token_cost_above_272k_tokens": 3.25e-07,
"cache_creation_input_token_cost_above_272k_tokens_flex": 1.625e-07,
"input_cost_per_token": 1.3e-07,
"input_cost_per_token_flex": 6.5e-08,
"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,
"supports_function_calling": True,
"supports_none_reasoning_effort": True,
"input_cost_per_token_above_272k_tokens": 2.6e-07,
"input_cost_per_token_above_272k_tokens_flex": 1.3e-07,
"output_cost_per_token_above_272k_tokens": 1.3e-06,
"output_cost_per_token_above_272k_tokens_flex": 4.875e-07,
"cache_read_input_token_cost_above_272k_tokens": 2.6e-08,
"cache_read_input_token_cost_above_272k_tokens_flex": 1.3e-08,
},
"azure/gpt-6-astra": {
"cache_read_input_token_cost": 1.25e-06,
"cache_read_input_token_cost_flex": 6.25e-07,
"cache_creation_input_token_cost": 1.5625e-05,
"cache_creation_input_token_cost_flex": 7.8125e-06,
"cache_creation_input_token_cost_above_272k_tokens": 3.125e-05,
"input_cost_per_token": 1.25e-05,
"input_cost_per_token_flex": 6.25e-06,
"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,
"supports_function_calling": True,
"supports_none_reasoning_effort": True,
"input_cost_per_token_above_272k_tokens": 2.5e-05,
@ -1637,20 +1649,28 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
},
"azure/gpt-6.1-sol": {
"cache_read_input_token_cost": 2.4e-07,
"cache_read_input_token_cost_flex": 6e-08,
"cache_creation_input_token_cost": 3e-06,
"cache_creation_input_token_cost_flex": 1.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6e-06,
"cache_creation_input_token_cost_above_272k_tokens_flex": 3e-06,
"input_cost_per_token": 2.4e-06,
"input_cost_per_token_flex": 1.2e-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,
"supports_function_calling": True,
"supports_none_reasoning_effort": True,
"input_cost_per_token_above_272k_tokens": 4.8e-06,
"input_cost_per_token_above_272k_tokens_flex": 2.4e-06,
"output_cost_per_token_above_272k_tokens": 2.4e-05,
"output_cost_per_token_above_272k_tokens_flex": 9e-06,
"cache_read_input_token_cost_above_272k_tokens": 4.8e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 1.2e-07,
},
}