scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108

Merge pull request #38370 from BerriAI/litellm_azure_gpt_5_6_cache_write_pricing

Browse source 
fix(pricing): add azure gpt-5.6 cache write rates and correct data zone priority
This commit is contained in:
Mateo Wang 2026-08-26 12:21:39 -07:00 • committed by GitHub
commit 74b6149d18
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 267 additions and 48 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

120
litellm/model_prices_and_context_window_backup.json
View file

@ -6592,6 +6592,10 @@
"supports_web_search": true
},
"azure/gpt-5.6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
@ -6642,6 +6646,10 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
@ -6693,6 +6701,10 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_priority": 4e-07,
@ -6744,6 +6756,10 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_priority": 4e-08,
@ -6795,12 +6811,18 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 1.375e-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_priority": 1.375e-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,
"max_output_tokens": 128000,
@ -6808,7 +6830,8 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-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,
"search_context_size_low": 0.01,
@ -6842,13 +6865,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 1.375e-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_priority": 1.375e-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,
"max_output_tokens": 128000,
@ -6856,7 +6885,8 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-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,
"search_context_size_low": 0.01,
@ -6890,13 +6920,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 5.5e-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_priority": 5.5e-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,
"max_output_tokens": 128000,
@ -6904,7 +6940,8 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_priority": 3.3e-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,
"search_context_size_low": 0.01,
@ -6938,13 +6975,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 5.5e-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_priority": 5.5e-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,
"max_output_tokens": 128000,
@ -6952,7 +6995,8 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_priority": 3.3e-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,
"search_context_size_low": 0.01,
@ -6986,12 +7030,18 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 1.375e-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_priority": 1.375e-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,
"max_output_tokens": 128000,
@ -6999,7 +7049,8 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-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,
"search_context_size_low": 0.01,
@ -7033,13 +7084,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 1.375e-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_priority": 1.375e-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,
"max_output_tokens": 128000,
@ -7047,7 +7104,8 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-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,
"search_context_size_low": 0.01,
@ -7081,13 +7139,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 5.5e-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_priority": 5.5e-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,
"max_output_tokens": 128000,
@ -7095,7 +7159,8 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_priority": 3.3e-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,
"search_context_size_low": 0.01,
@ -7129,13 +7194,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 5.5e-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_priority": 5.5e-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,
"max_output_tokens": 128000,
@ -7143,7 +7214,8 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_priority": 3.3e-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,
"search_context_size_low": 0.01,

120
model_prices_and_context_window.json
View file

@ -6592,6 +6592,10 @@
"supports_web_search": true
},
"azure/gpt-5.6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
@ -6642,6 +6646,10 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
@ -6693,6 +6701,10 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_priority": 4e-07,
@ -6744,6 +6756,10 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_priority": 4e-08,
@ -6795,12 +6811,18 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 1.375e-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_priority": 1.375e-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,
"max_output_tokens": 128000,
@ -6808,7 +6830,8 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-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,
"search_context_size_low": 0.01,
@ -6842,13 +6865,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 1.375e-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_priority": 1.375e-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,
"max_output_tokens": 128000,
@ -6856,7 +6885,8 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-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,
"search_context_size_low": 0.01,
@ -6890,13 +6920,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 5.5e-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_priority": 5.5e-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,
"max_output_tokens": 128000,
@ -6904,7 +6940,8 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_priority": 3.3e-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,
"search_context_size_low": 0.01,
@ -6938,13 +6975,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 5.5e-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_priority": 5.5e-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,
"max_output_tokens": 128000,
@ -6952,7 +6995,8 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_priority": 3.3e-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,
"search_context_size_low": 0.01,
@ -6986,12 +7030,18 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 1.375e-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_priority": 1.375e-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,
"max_output_tokens": 128000,
@ -6999,7 +7049,8 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-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,
"search_context_size_low": 0.01,
@ -7033,13 +7084,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 1.375e-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_priority": 1.375e-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,
"max_output_tokens": 128000,
@ -7047,7 +7104,8 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-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,
"search_context_size_low": 0.01,
@ -7081,13 +7139,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 5.5e-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_priority": 5.5e-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,
"max_output_tokens": 128000,
@ -7095,7 +7159,8 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_priority": 3.3e-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,
"search_context_size_low": 0.01,
@ -7129,13 +7194,19 @@
"supports_minimal_reasoning_effort": false
},
"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_priority": 5.5e-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_priority": 5.5e-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,
"max_output_tokens": 128000,
@ -7143,7 +7214,8 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_priority": 3.3e-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,
"search_context_size_low": 0.01,

5
model_prices_and_context_window.schema.json
View file

@ -104,6 +104,11 @@
"minimum": 0,
"description": "Flex service-tier rate for the same-named base field."
},
"cache_creation_input_token_cost_above_272k_tokens_priority": {
"type": "number",
"minimum": 0,
"description": "Priority service-tier rate for the same-named base field."
},
"cache_creation_input_token_cost_flex": {
"type": "number",
"minimum": 0,

67
tests/test_litellm/test_cost_calculator.py
View file

@ -1727,6 +1727,73 @@ def test_azure_ai_cache_cost_calculation(_local_model_cost_map):
), f"Output cost mismatch: got {output_cost}, expected {expected_output_cost}"
AZURE_GPT_5_6_MAP_KEYS = (
"azure/gpt-5.6",
"azure/gpt-5.6-sol",
"azure/gpt-5.6-terra",
"azure/gpt-5.6-luna",
"azure/us/gpt-5.6",
"azure/us/gpt-5.6-sol",
"azure/us/gpt-5.6-terra",
"azure/us/gpt-5.6-luna",
"azure/eu/gpt-5.6",
"azure/eu/gpt-5.6-sol",
"azure/eu/gpt-5.6-terra",
"azure/eu/gpt-5.6-luna",
)
def test_azure_gpt_5_6_cache_write_tokens_are_billed(_local_model_cost_map):
"""
Azure bills gpt-5.6 prompt cache writes at 1.25x the input rate on every
tier, but the azure entries carried no ``cache_creation_input_token_cost``,
so cache-write tokens were billed at the plain input rate instead.
"""
from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token
from litellm.types.utils import PromptTokensDetailsWrapper, Usage
usage = Usage(
completion_tokens=100,
prompt_tokens=2000,
total_tokens=2100,
prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=0, text_tokens=687),
cache_creation_input_tokens=1313,
)
input_cost, output_cost = generic_cost_per_token(
model="azure/gpt-5.6-luna", usage=usage, custom_llm_provider="azure"
)
assert input_cost == pytest.approx(687 * 2e-07 + 1313 * 2.5e-07)
assert output_cost == pytest.approx(100 * 1.2e-06)
@pytest.mark.parametrize("model", AZURE_GPT_5_6_MAP_KEYS)
def test_azure_gpt_5_6_rates_match_azure_price_page(_local_model_cost_map, model):
"""
Per the Azure OpenAI price page (rendered 2026-08-26): cache writes cost
1.25x input on every gpt-5.6 tier, and Data Zone costs 1.1x Global for
standard and priority alike (us/eu priority rates previously sat at 1.25x).
"""
entry = litellm.model_cost[model]
input_keys = [key for key in entry if key.startswith("input_cost_per_token")]
assert input_keys
for key in input_keys:
suffix = key[len("input_cost_per_token") :]
assert entry["cache_creation_input_token_cost" + suffix] == pytest.approx(entry[key] * 1.25)
zone = model.split("/")[1]
if zone in ("us", "eu"):
global_entry = litellm.model_cost["azure/" + model.split("/", 2)[2]]
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
def test_vertex_regional_deployment_costs_uplift_over_global(monkeypatch):
"""
Regression for https://github.com/BerriAI/litellm/issues/34393: two Vertex

3
tests/test_litellm/test_utils.py
View file

@ -845,6 +845,9 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"cache_creation_input_token_cost_above_272k_tokens_flex": {
"type": "number"
},
"cache_creation_input_token_cost_above_272k_tokens_priority": {
"type": "number"
},
"cache_creation_input_token_cost_flex": {"type": "number"},
"cache_creation_input_token_cost_priority": {"type": "number"},
"cache_read_input_token_cost": {"type": "number"},