scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

fix(model_prices): add above-272k priority rates to azure us/eu gpt-5.6 entries

Browse source
This commit is contained in:
mateo-berri 2026-08-26 11:40:19 -07:00
parent 8d750a2468
commit e97a84afcf
3 changed files with 68 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
litellm/model_prices_and_context_window_backup.json
View file

@ -6813,12 +6813,15 @@
"azure/us/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -6827,6 +6830,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -6863,13 +6867,16 @@
"azure/us/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -6878,6 +6885,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -6914,13 +6922,16 @@
"azure/us/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
"cache_creation_input_token_cost_priority": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -6929,6 +6940,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.96e-05,
"output_cost_per_token_priority": 2.64e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -6965,13 +6977,16 @@
"azure/us/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.75e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06,
"cache_creation_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
"input_cost_per_token_priority": 4.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -6980,6 +6995,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.96e-06,
"output_cost_per_token_priority": 2.64e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -7016,12 +7032,15 @@
"azure/eu/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -7030,6 +7049,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -7066,13 +7086,16 @@
"azure/eu/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -7081,6 +7104,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -7117,13 +7141,16 @@
"azure/eu/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
"cache_creation_input_token_cost_priority": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -7132,6 +7159,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.96e-05,
"output_cost_per_token_priority": 2.64e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -7168,13 +7196,16 @@
"azure/eu/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.75e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06,
"cache_creation_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
"input_cost_per_token_priority": 4.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -7183,6 +7214,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.96e-06,
"output_cost_per_token_priority": 2.64e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,

32
model_prices_and_context_window.json
View file

@ -6813,12 +6813,15 @@
"azure/us/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -6827,6 +6830,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -6863,13 +6867,16 @@
"azure/us/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -6878,6 +6885,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -6914,13 +6922,16 @@
"azure/us/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
"cache_creation_input_token_cost_priority": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -6929,6 +6940,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.96e-05,
"output_cost_per_token_priority": 2.64e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -6965,13 +6977,16 @@
"azure/us/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.75e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06,
"cache_creation_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
"input_cost_per_token_priority": 4.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -6980,6 +6995,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.96e-06,
"output_cost_per_token_priority": 2.64e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -7016,12 +7032,15 @@
"azure/eu/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -7030,6 +7049,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -7066,13 +7086,16 @@
"azure/eu/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -7081,6 +7104,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -7117,13 +7141,16 @@
"azure/eu/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
"cache_creation_input_token_cost_priority": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -7132,6 +7159,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.96e-05,
"output_cost_per_token_priority": 2.64e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -7168,13 +7196,16 @@
"azure/eu/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.75e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06,
"cache_creation_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
"input_cost_per_token_priority": 4.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
@ -7183,6 +7214,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.96e-06,
"output_cost_per_token_priority": 2.64e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,

9
tests/test_litellm/test_cost_calculator.py
View file

@ -1777,12 +1777,11 @@ def test_azure_gpt_5_6_rates_match_azure_price_page(_local_model_cost_map, model
zone = model.split("/")[1]
if zone in ("us", "eu"):
global_entry = litellm.model_cost["azure/" + model.split("/", 2)[2]]
token_cost_keys = [
key
for key in entry
if key.startswith(("input_cost_per_token", "output_cost_per_token", "cache_read", "cache_creation"))
]
prefixes = ("input_cost_per_token", "output_cost_per_token", "cache_read", "cache_creation")
token_cost_keys = [key for key in entry if key.startswith(prefixes)]
global_token_cost_keys = [key for key in global_entry if key.startswith(prefixes)]
assert len(token_cost_keys) >= 9
assert sorted(token_cost_keys) == sorted(global_token_cost_keys)
for key in token_cost_keys:
assert entry[key] == pytest.approx(global_entry[key] * 1.1), key