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

Merge pull request #35481 from mubashir1osmani/litellm_azure_gpt56_price_cut

Browse source 
fix(pricing): apply OpenAI's gpt-5.6 terra/luna cut to Azure cost map
This commit is contained in:
Mateo Wang 2026-08-04 17:02:12 -07:00 • committed by GitHub
commit e926097fec
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 124 additions and 124 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

@ -6431,23 +6431,23 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-terra": {
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_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,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_priority": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_priority": 3e-05,
"output_cost_per_token_above_272k_tokens_priority": 4.5e-05,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"output_cost_per_token_priority": 2.4e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6476,23 +6476,23 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-luna": {
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2e-07,
"cache_read_input_token_cost_priority": 2e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 4e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"input_cost_per_token_priority": 2e-06,
"input_cost_per_token_above_272k_tokens_priority": 4e-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,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_priority": 4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_272k_tokens": 9e-06,
"output_cost_per_token_priority": 1.2e-05,
"output_cost_per_token_above_272k_tokens_priority": 1.8e-05,
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_priority": 2.4e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6605,20 +6605,20 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-terra": {
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_priority": 6.875e-07,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_above_272k_tokens": 5.5e-06,
"input_cost_per_token_priority": 6.875e-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,
"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,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-05,
"output_cost_per_token_above_272k_tokens": 2.475e-05,
"output_cost_per_token_priority": 4.125e-05,
"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,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6647,20 +6647,20 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-luna": {
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.1e-06,
"input_cost_per_token_above_272k_tokens": 2.2e-06,
"input_cost_per_token_priority": 2.75e-06,
"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,
"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,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.6e-06,
"output_cost_per_token_above_272k_tokens": 9.9e-06,
"output_cost_per_token_priority": 1.65e-05,
"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,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6773,20 +6773,20 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-terra": {
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_priority": 6.875e-07,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_above_272k_tokens": 5.5e-06,
"input_cost_per_token_priority": 6.875e-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,
"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,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-05,
"output_cost_per_token_above_272k_tokens": 2.475e-05,
"output_cost_per_token_priority": 4.125e-05,
"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,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6815,20 +6815,20 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-luna": {
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.1e-06,
"input_cost_per_token_above_272k_tokens": 2.2e-06,
"input_cost_per_token_priority": 2.75e-06,
"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,
"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,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.6e-06,
"output_cost_per_token_above_272k_tokens": 9.9e-06,
"output_cost_per_token_priority": 1.65e-05,
"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,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",

120
model_prices_and_context_window.json
View file

@ -6431,23 +6431,23 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-terra": {
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_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,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_priority": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_priority": 3e-05,
"output_cost_per_token_above_272k_tokens_priority": 4.5e-05,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"output_cost_per_token_priority": 2.4e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6476,23 +6476,23 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-luna": {
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2e-07,
"cache_read_input_token_cost_priority": 2e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 4e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"input_cost_per_token_priority": 2e-06,
"input_cost_per_token_above_272k_tokens_priority": 4e-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,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_priority": 4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_272k_tokens": 9e-06,
"output_cost_per_token_priority": 1.2e-05,
"output_cost_per_token_above_272k_tokens_priority": 1.8e-05,
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_priority": 2.4e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6605,20 +6605,20 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-terra": {
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_priority": 6.875e-07,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_above_272k_tokens": 5.5e-06,
"input_cost_per_token_priority": 6.875e-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,
"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,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-05,
"output_cost_per_token_above_272k_tokens": 2.475e-05,
"output_cost_per_token_priority": 4.125e-05,
"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,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6647,20 +6647,20 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-luna": {
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.1e-06,
"input_cost_per_token_above_272k_tokens": 2.2e-06,
"input_cost_per_token_priority": 2.75e-06,
"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,
"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,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.6e-06,
"output_cost_per_token_above_272k_tokens": 9.9e-06,
"output_cost_per_token_priority": 1.65e-05,
"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,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6773,20 +6773,20 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-terra": {
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_priority": 6.875e-07,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_above_272k_tokens": 5.5e-06,
"input_cost_per_token_priority": 6.875e-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,
"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,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.65e-05,
"output_cost_per_token_above_272k_tokens": 2.475e-05,
"output_cost_per_token_priority": 4.125e-05,
"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,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -6815,20 +6815,20 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-luna": {
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.1e-06,
"input_cost_per_token_above_272k_tokens": 2.2e-06,
"input_cost_per_token_priority": 2.75e-06,
"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,
"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,
"litellm_provider": "azure",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.6e-06,
"output_cost_per_token_above_272k_tokens": 9.9e-06,
"output_cost_per_token_priority": 1.65e-05,
"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,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",

8
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -757,11 +757,11 @@ def test_generic_cost_per_token_gpt56_terra_cache_costs_by_tier_and_context(
[
("azure/gpt-5.6", 5e-6, 3e-5, 5e-7),
("azure/gpt-5.6-sol", 5e-6, 3e-5, 5e-7),
("azure/gpt-5.6-terra", 2.5e-6, 1.5e-5, 2.5e-7),
("azure/gpt-5.6-luna", 1e-6, 6e-6, 1e-7),
("azure/gpt-5.6-terra", 2e-6, 1.2e-5, 2e-7),
("azure/gpt-5.6-luna", 2e-7, 1.2e-6, 2e-8),
("azure/us/gpt-5.6", 5.5e-6, 3.3e-5, 5.5e-7),
("azure/eu/gpt-5.6-terra", 2.75e-6, 1.65e-5, 2.75e-7),
("azure/eu/gpt-5.6-luna", 1.1e-6, 6.6e-6, 1.1e-7),
("azure/eu/gpt-5.6-terra", 2.2e-6, 1.32e-5, 2.2e-7),
("azure/eu/gpt-5.6-luna", 2.2e-7, 1.32e-6, 2.2e-8),
],
)
def test_generic_cost_per_token_azure_gpt56(