scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-25 01:02:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 81

chore(prices): sync Azure prices: 34 models (#42502)

Browse source 
azure/eu/gpt-5: cache_read_input_token_cost_batches
azure/eu/gpt-5-mini: cache_read_input_token_cost_batches
azure/eu/gpt-5-nano: cache_read_input_token_cost_batches
azure/eu/gpt-5.1: cache_read_input_token_cost_batches
azure/eu/gpt-5.2: cache_read_input_token_cost_batches
azure/eu/gpt-5.4: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches
azure/eu/gpt-5.4-mini: cache_read_input_token_cost_batches
azure/eu/gpt-5.4-nano: cache_read_input_token_cost_batches
azure/eu/gpt-5.4-pro: input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches
azure/eu/gpt-5.5: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches
azure/eu/gpt-5.5-2026-04-23: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches
azure/gpt-5: cache_read_input_token_cost_batches
azure/gpt-5-mini: cache_read_input_token_cost_batches
azure/gpt-5-nano: cache_read_input_token_cost_batches
azure/gpt-5.1: cache_read_input_token_cost_batches
azure/global/gpt-5.1: cache_read_input_token_cost_batches
azure/gpt-5.2: cache_read_input_token_cost_batches
azure/gpt-5.4: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches
azure/gpt-5.4-mini: cache_read_input_token_cost_batches
azure/gpt-5.4-nano: cache_read_input_token_cost_batches
azure/gpt-5.4-pro: input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches
azure/gpt-5.5: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches
azure/gpt-5.5-2026-04-23: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches
azure/us/gpt-5: cache_read_input_token_cost_batches
azure/us/gpt-5-mini: cache_read_input_token_cost_batches
azure/us/gpt-5-nano: cache_read_input_token_cost_batches
azure/us/gpt-5.1: cache_read_input_token_cost_batches
azure/us/gpt-5.2: cache_read_input_token_cost_batches
azure/us/gpt-5.4: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches
azure/us/gpt-5.4-mini: cache_read_input_token_cost_batches
azure/us/gpt-5.4-nano: cache_read_input_token_cost_batches
azure/us/gpt-5.4-pro: input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches
azure/us/gpt-5.5: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches
azure/us/gpt-5.5-2026-04-23: cache_read_input_token_cost_batches, input_cost_per_token_above_272k_tokens_batches, output_cost_per_token_above_272k_tokens_batches, cache_read_input_token_cost_above_272k_tokens_batches

Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
This commit is contained in:
berriai-litellm-provider-info-sync[bot] 2026-09-22 11:21:06 -07:00 • committed by GitHub
parent 9e92fadacf
commit c3389d7901
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 128 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

64
litellm/model_prices_and_context_window_backup.json
View file

@ -4472,6 +4472,7 @@
"azure/eu/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -4814,6 +4815,7 @@
"azure/global/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
@ -6232,6 +6234,7 @@
"azure/gpt-5": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_batches": 6.25e-07,
@ -6409,6 +6412,7 @@
"azure/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
@ -6487,6 +6491,7 @@
"azure/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 5e-09,
"cache_read_input_token_cost_batches": 2.5e-09,
"input_cost_per_token": 5e-08,
"input_cost_per_token_batches": 2.5e-08,
"litellm_provider": "azure",
@ -6591,6 +6596,7 @@
"azure/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
@ -6766,6 +6772,7 @@
"azure/gpt-5.2": {
"deprecation_date": "2027-06-08",
"cache_read_input_token_cost": 1.75e-07,
"cache_read_input_token_cost_batches": 8.75e-08,
"cache_read_input_token_cost_priority": 3.5e-07,
"input_cost_per_token": 1.75e-06,
"input_cost_per_token_batches": 8.75e-07,
@ -7100,9 +7107,11 @@
"deprecation_date": "2027-09-02",
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07,
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"cache_read_input_token_cost_batches": 1.3e-07,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
@ -7140,9 +7149,11 @@
"supports_vision": true,
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"input_cost_per_token_above_272k_tokens_batches": 2.5e-06,
"input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
"input_cost_per_token_batches": 1.25e-06,
"input_cost_per_token_flex": 1.25e-06,
"output_cost_per_token_above_272k_tokens_batches": 1.125e-05,
"output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
"output_cost_per_token_batches": 7.5e-06,
"output_cost_per_token_flex": 7.5e-06,
@ -7154,6 +7165,8 @@
"deprecation_date": "2027-09-02",
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07,
"cache_read_input_token_cost_batches": 1.43e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_priority": 5.5e-06,
@ -7189,8 +7202,10 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"input_cost_per_token_above_272k_tokens": 5.5e-06,
"input_cost_per_token_above_272k_tokens_batches": 2.75e-06,
"input_cost_per_token_batches": 1.375e-06,
"output_cost_per_token_above_272k_tokens": 2.475e-05,
"output_cost_per_token_above_272k_tokens_batches": 1.2375e-05,
"output_cost_per_token_batches": 8.25e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_xhigh_reasoning_effort": true,
@ -7200,6 +7215,8 @@
"deprecation_date": "2027-09-02",
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07,
"cache_read_input_token_cost_batches": 1.43e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_priority": 5.5e-06,
@ -7235,8 +7252,10 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"input_cost_per_token_above_272k_tokens": 5.5e-06,
"input_cost_per_token_above_272k_tokens_batches": 2.75e-06,
"input_cost_per_token_batches": 1.375e-06,
"output_cost_per_token_above_272k_tokens": 2.475e-05,
"output_cost_per_token_above_272k_tokens_batches": 1.2375e-05,
"output_cost_per_token_batches": 8.25e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_xhigh_reasoning_effort": true,
@ -7394,6 +7413,7 @@
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_above_272k_tokens_batches": 3e-05,
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
"input_cost_per_token_batches": 1.5e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -7404,6 +7424,7 @@
"mode": "responses",
"output_cost_per_token": 0.00018,
"output_cost_per_token_above_272k_tokens": 0.00027,
"output_cost_per_token_above_272k_tokens_batches": 0.000135,
"output_cost_per_token_above_272k_tokens_flex": 0.000135,
"output_cost_per_token_batches": 9e-05,
"output_cost_per_token_flex": 9e-05,
@ -8625,11 +8646,14 @@
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
"cache_read_input_token_cost_priority": 1.25e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"cache_read_input_token_cost_batches": 2.5e-07,
"cache_read_input_token_cost_flex": 2.5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_above_272k_tokens_batches": 5e-06,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_priority": 1.25e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
@ -8642,6 +8666,7 @@
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_above_272k_tokens_batches": 2.25e-05,
"output_cost_per_token_priority": 7.5e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"output_cost_per_token_batches": 1.5e-05,
@ -8682,9 +8707,12 @@
"deprecation_date": "2027-10-26",
"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_batches": 5.5e-07,
"cache_read_input_token_cost_batches": 2.75e-07,
"cache_read_input_token_cost_priority": 1.375e-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_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"input_cost_per_token_priority": 1.375e-05,
"output_cost_per_token": 3.3e-05,
@ -8695,6 +8723,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
"output_cost_per_token_batches": 1.65e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -8733,9 +8762,12 @@
"deprecation_date": "2027-10-26",
"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_batches": 5.5e-07,
"cache_read_input_token_cost_batches": 2.75e-07,
"cache_read_input_token_cost_priority": 1.375e-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_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"input_cost_per_token_priority": 1.375e-05,
"output_cost_per_token": 3.3e-05,
@ -8746,6 +8778,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
"output_cost_per_token_batches": 1.65e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -8783,8 +8816,10 @@
"azure/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
"cache_read_input_token_cost_priority": 1.25e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"cache_read_input_token_cost_batches": 2.5e-07,
"cache_read_input_token_cost_flex": 2.5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
@ -8828,9 +8863,11 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"input_cost_per_token_above_272k_tokens_batches": 5e-06,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_batches": 2.5e-06,
"input_cost_per_token_flex": 2.5e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.25e-05,
"output_cost_per_token_batches": 1.5e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
@ -8894,6 +8931,8 @@
"azure/us/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07,
"cache_read_input_token_cost_batches": 2.75e-07,
"cache_read_input_token_cost_priority": 1.375e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
@ -8935,7 +8974,9 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"input_cost_per_token_above_272k_tokens_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
"output_cost_per_token_batches": 1.65e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
@ -8993,6 +9034,8 @@
"azure/eu/gpt-5.5-2026-04-23": {
"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_batches": 5.5e-07,
"cache_read_input_token_cost_batches": 2.75e-07,
"cache_read_input_token_cost_priority": 1.375e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
@ -9034,7 +9077,9 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"input_cost_per_token_above_272k_tokens_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
"output_cost_per_token_batches": 1.65e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
@ -9176,6 +9221,7 @@
"azure/gpt-5.4-mini": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_batches": 3.75e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"cache_read_input_token_cost_priority": 1.5e-07,
"input_cost_per_token": 7.5e-07,
@ -9278,6 +9324,7 @@
"azure/gpt-5.4-nano": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_batches": 1e-08,
"cache_read_input_token_cost_flex": 1e-08,
"input_cost_per_token": 2e-07,
"litellm_provider": "azure",
@ -10496,6 +10543,7 @@
"azure/us/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -71324,6 +71372,7 @@
"azure/eu/gpt-5": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.375e-06,
"input_cost_per_token_batches": 6.875e-07,
@ -71347,6 +71396,7 @@
"azure/eu/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_batches": 1.375e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
"input_cost_per_token": 2.75e-07,
"input_cost_per_token_batches": 1.375e-07,
@ -71361,6 +71411,7 @@
"azure/eu/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 5.5e-09,
"cache_read_input_token_cost_batches": 2.75e-09,
"input_cost_per_token": 5.5e-08,
"input_cost_per_token_batches": 2.75e-08,
"litellm_provider": "azure",
@ -71391,6 +71442,7 @@
"azure/eu/gpt-5.2": {
"deprecation_date": "2027-06-08",
"cache_read_input_token_cost": 1.925e-07,
"cache_read_input_token_cost_batches": 9.625e-08,
"cache_read_input_token_cost_priority": 3.85e-07,
"input_cost_per_token": 1.925e-06,
"input_cost_per_token_batches": 9.625e-07,
@ -71453,6 +71505,7 @@
"azure/eu/gpt-5.4-mini": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 8.25e-08,
"cache_read_input_token_cost_batches": 4.125e-08,
"cache_read_input_token_cost_priority": 1.65e-07,
"input_cost_per_token": 8.25e-07,
"input_cost_per_token_batches": 4.125e-07,
@ -71467,6 +71520,7 @@
"azure/eu/gpt-5.4-nano": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_batches": 1.1e-08,
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_batches": 1.1e-07,
"litellm_provider": "azure",
@ -71479,11 +71533,13 @@
"deprecation_date": "2027-09-07",
"input_cost_per_token": 3.3e-05,
"input_cost_per_token_above_272k_tokens": 6.6e-05,
"input_cost_per_token_above_272k_tokens_batches": 3.3e-05,
"input_cost_per_token_batches": 1.65e-05,
"litellm_provider": "azure",
"mode": "chat",
"output_cost_per_token": 0.000198,
"output_cost_per_token_above_272k_tokens": 0.000297,
"output_cost_per_token_above_272k_tokens_batches": 0.0001485,
"output_cost_per_token_batches": 9.9e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
@ -71678,6 +71734,7 @@
"azure/us/gpt-5": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.375e-06,
"input_cost_per_token_batches": 6.875e-07,
@ -71701,6 +71758,7 @@
"azure/us/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_batches": 1.375e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
"input_cost_per_token": 2.75e-07,
"input_cost_per_token_batches": 1.375e-07,
@ -71715,6 +71773,7 @@
"azure/us/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 5.5e-09,
"cache_read_input_token_cost_batches": 2.75e-09,
"input_cost_per_token": 5.5e-08,
"input_cost_per_token_batches": 2.75e-08,
"litellm_provider": "azure",
@ -71745,6 +71804,7 @@
"azure/us/gpt-5.2": {
"deprecation_date": "2027-06-08",
"cache_read_input_token_cost": 1.925e-07,
"cache_read_input_token_cost_batches": 9.625e-08,
"cache_read_input_token_cost_priority": 3.85e-07,
"input_cost_per_token": 1.925e-06,
"input_cost_per_token_batches": 9.625e-07,
@ -71807,6 +71867,7 @@
"azure/us/gpt-5.4-mini": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 8.25e-08,
"cache_read_input_token_cost_batches": 4.125e-08,
"cache_read_input_token_cost_priority": 1.65e-07,
"input_cost_per_token": 8.25e-07,
"input_cost_per_token_batches": 4.125e-07,
@ -71821,6 +71882,7 @@
"azure/us/gpt-5.4-nano": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_batches": 1.1e-08,
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_batches": 1.1e-07,
"litellm_provider": "azure",
@ -71833,11 +71895,13 @@
"deprecation_date": "2027-09-07",
"input_cost_per_token": 3.3e-05,
"input_cost_per_token_above_272k_tokens": 6.6e-05,
"input_cost_per_token_above_272k_tokens_batches": 3.3e-05,
"input_cost_per_token_batches": 1.65e-05,
"litellm_provider": "azure",
"mode": "chat",
"output_cost_per_token": 0.000198,
"output_cost_per_token_above_272k_tokens": 0.000297,
"output_cost_per_token_above_272k_tokens_batches": 0.0001485,
"output_cost_per_token_batches": 9.9e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},

64
model_prices_and_context_window.json
View file

@ -4472,6 +4472,7 @@
"azure/eu/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -4814,6 +4815,7 @@
"azure/global/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
@ -6232,6 +6234,7 @@
"azure/gpt-5": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_batches": 6.25e-07,
@ -6409,6 +6412,7 @@
"azure/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
@ -6487,6 +6491,7 @@
"azure/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 5e-09,
"cache_read_input_token_cost_batches": 2.5e-09,
"input_cost_per_token": 5e-08,
"input_cost_per_token_batches": 2.5e-08,
"litellm_provider": "azure",
@ -6591,6 +6596,7 @@
"azure/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
@ -6766,6 +6772,7 @@
"azure/gpt-5.2": {
"deprecation_date": "2027-06-08",
"cache_read_input_token_cost": 1.75e-07,
"cache_read_input_token_cost_batches": 8.75e-08,
"cache_read_input_token_cost_priority": 3.5e-07,
"input_cost_per_token": 1.75e-06,
"input_cost_per_token_batches": 8.75e-07,
@ -7100,9 +7107,11 @@
"deprecation_date": "2027-09-02",
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07,
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"cache_read_input_token_cost_batches": 1.3e-07,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
@ -7140,9 +7149,11 @@
"supports_vision": true,
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"input_cost_per_token_above_272k_tokens_batches": 2.5e-06,
"input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
"input_cost_per_token_batches": 1.25e-06,
"input_cost_per_token_flex": 1.25e-06,
"output_cost_per_token_above_272k_tokens_batches": 1.125e-05,
"output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
"output_cost_per_token_batches": 7.5e-06,
"output_cost_per_token_flex": 7.5e-06,
@ -7154,6 +7165,8 @@
"deprecation_date": "2027-09-02",
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07,
"cache_read_input_token_cost_batches": 1.43e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_priority": 5.5e-06,
@ -7189,8 +7202,10 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"input_cost_per_token_above_272k_tokens": 5.5e-06,
"input_cost_per_token_above_272k_tokens_batches": 2.75e-06,
"input_cost_per_token_batches": 1.375e-06,
"output_cost_per_token_above_272k_tokens": 2.475e-05,
"output_cost_per_token_above_272k_tokens_batches": 1.2375e-05,
"output_cost_per_token_batches": 8.25e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_xhigh_reasoning_effort": true,
@ -7200,6 +7215,8 @@
"deprecation_date": "2027-09-02",
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07,
"cache_read_input_token_cost_batches": 1.43e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_priority": 5.5e-06,
@ -7235,8 +7252,10 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"input_cost_per_token_above_272k_tokens": 5.5e-06,
"input_cost_per_token_above_272k_tokens_batches": 2.75e-06,
"input_cost_per_token_batches": 1.375e-06,
"output_cost_per_token_above_272k_tokens": 2.475e-05,
"output_cost_per_token_above_272k_tokens_batches": 1.2375e-05,
"output_cost_per_token_batches": 8.25e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_xhigh_reasoning_effort": true,
@ -7394,6 +7413,7 @@
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_above_272k_tokens_batches": 3e-05,
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
"input_cost_per_token_batches": 1.5e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -7404,6 +7424,7 @@
"mode": "responses",
"output_cost_per_token": 0.00018,
"output_cost_per_token_above_272k_tokens": 0.00027,
"output_cost_per_token_above_272k_tokens_batches": 0.000135,
"output_cost_per_token_above_272k_tokens_flex": 0.000135,
"output_cost_per_token_batches": 9e-05,
"output_cost_per_token_flex": 9e-05,
@ -8625,11 +8646,14 @@
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
"cache_read_input_token_cost_priority": 1.25e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"cache_read_input_token_cost_batches": 2.5e-07,
"cache_read_input_token_cost_flex": 2.5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_above_272k_tokens_batches": 5e-06,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_priority": 1.25e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
@ -8642,6 +8666,7 @@
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_above_272k_tokens_batches": 2.25e-05,
"output_cost_per_token_priority": 7.5e-05,
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
"output_cost_per_token_batches": 1.5e-05,
@ -8682,9 +8707,12 @@
"deprecation_date": "2027-10-26",
"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_batches": 5.5e-07,
"cache_read_input_token_cost_batches": 2.75e-07,
"cache_read_input_token_cost_priority": 1.375e-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_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"input_cost_per_token_priority": 1.375e-05,
"output_cost_per_token": 3.3e-05,
@ -8695,6 +8723,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
"output_cost_per_token_batches": 1.65e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -8733,9 +8762,12 @@
"deprecation_date": "2027-10-26",
"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_batches": 5.5e-07,
"cache_read_input_token_cost_batches": 2.75e-07,
"cache_read_input_token_cost_priority": 1.375e-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_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"input_cost_per_token_priority": 1.375e-05,
"output_cost_per_token": 3.3e-05,
@ -8746,6 +8778,7 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
"output_cost_per_token_batches": 1.65e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
@ -8783,8 +8816,10 @@
"azure/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
"cache_read_input_token_cost_priority": 1.25e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
"cache_read_input_token_cost_batches": 2.5e-07,
"cache_read_input_token_cost_flex": 2.5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
@ -8828,9 +8863,11 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"input_cost_per_token_above_272k_tokens_batches": 5e-06,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_batches": 2.5e-06,
"input_cost_per_token_flex": 2.5e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.25e-05,
"output_cost_per_token_batches": 1.5e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
@ -8894,6 +8931,8 @@
"azure/us/gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07,
"cache_read_input_token_cost_batches": 2.75e-07,
"cache_read_input_token_cost_priority": 1.375e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
@ -8935,7 +8974,9 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"input_cost_per_token_above_272k_tokens_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
"output_cost_per_token_batches": 1.65e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
@ -8993,6 +9034,8 @@
"azure/eu/gpt-5.5-2026-04-23": {
"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_batches": 5.5e-07,
"cache_read_input_token_cost_batches": 2.75e-07,
"cache_read_input_token_cost_priority": 1.375e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
@ -9034,7 +9077,9 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"input_cost_per_token_above_272k_tokens_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
"output_cost_per_token_batches": 1.65e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
@ -9176,6 +9221,7 @@
"azure/gpt-5.4-mini": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_batches": 3.75e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"cache_read_input_token_cost_priority": 1.5e-07,
"input_cost_per_token": 7.5e-07,
@ -9278,6 +9324,7 @@
"azure/gpt-5.4-nano": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_batches": 1e-08,
"cache_read_input_token_cost_flex": 1e-08,
"input_cost_per_token": 2e-07,
"litellm_provider": "azure",
@ -10496,6 +10543,7 @@
"azure/us/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -71324,6 +71372,7 @@
"azure/eu/gpt-5": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.375e-06,
"input_cost_per_token_batches": 6.875e-07,
@ -71347,6 +71396,7 @@
"azure/eu/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_batches": 1.375e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
"input_cost_per_token": 2.75e-07,
"input_cost_per_token_batches": 1.375e-07,
@ -71361,6 +71411,7 @@
"azure/eu/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 5.5e-09,
"cache_read_input_token_cost_batches": 2.75e-09,
"input_cost_per_token": 5.5e-08,
"input_cost_per_token_batches": 2.75e-08,
"litellm_provider": "azure",
@ -71391,6 +71442,7 @@
"azure/eu/gpt-5.2": {
"deprecation_date": "2027-06-08",
"cache_read_input_token_cost": 1.925e-07,
"cache_read_input_token_cost_batches": 9.625e-08,
"cache_read_input_token_cost_priority": 3.85e-07,
"input_cost_per_token": 1.925e-06,
"input_cost_per_token_batches": 9.625e-07,
@ -71453,6 +71505,7 @@
"azure/eu/gpt-5.4-mini": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 8.25e-08,
"cache_read_input_token_cost_batches": 4.125e-08,
"cache_read_input_token_cost_priority": 1.65e-07,
"input_cost_per_token": 8.25e-07,
"input_cost_per_token_batches": 4.125e-07,
@ -71467,6 +71520,7 @@
"azure/eu/gpt-5.4-nano": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_batches": 1.1e-08,
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_batches": 1.1e-07,
"litellm_provider": "azure",
@ -71479,11 +71533,13 @@
"deprecation_date": "2027-09-07",
"input_cost_per_token": 3.3e-05,
"input_cost_per_token_above_272k_tokens": 6.6e-05,
"input_cost_per_token_above_272k_tokens_batches": 3.3e-05,
"input_cost_per_token_batches": 1.65e-05,
"litellm_provider": "azure",
"mode": "chat",
"output_cost_per_token": 0.000198,
"output_cost_per_token_above_272k_tokens": 0.000297,
"output_cost_per_token_above_272k_tokens_batches": 0.0001485,
"output_cost_per_token_batches": 9.9e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
@ -71678,6 +71734,7 @@
"azure/us/gpt-5": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
"input_cost_per_token": 1.375e-06,
"input_cost_per_token_batches": 6.875e-07,
@ -71701,6 +71758,7 @@
"azure/us/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_batches": 1.375e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
"input_cost_per_token": 2.75e-07,
"input_cost_per_token_batches": 1.375e-07,
@ -71715,6 +71773,7 @@
"azure/us/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"cache_read_input_token_cost": 5.5e-09,
"cache_read_input_token_cost_batches": 2.75e-09,
"input_cost_per_token": 5.5e-08,
"input_cost_per_token_batches": 2.75e-08,
"litellm_provider": "azure",
@ -71745,6 +71804,7 @@
"azure/us/gpt-5.2": {
"deprecation_date": "2027-06-08",
"cache_read_input_token_cost": 1.925e-07,
"cache_read_input_token_cost_batches": 9.625e-08,
"cache_read_input_token_cost_priority": 3.85e-07,
"input_cost_per_token": 1.925e-06,
"input_cost_per_token_batches": 9.625e-07,
@ -71807,6 +71867,7 @@
"azure/us/gpt-5.4-mini": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 8.25e-08,
"cache_read_input_token_cost_batches": 4.125e-08,
"cache_read_input_token_cost_priority": 1.65e-07,
"input_cost_per_token": 8.25e-07,
"input_cost_per_token_batches": 4.125e-07,
@ -71821,6 +71882,7 @@
"azure/us/gpt-5.4-nano": {
"deprecation_date": "2027-09-21",
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_batches": 1.1e-08,
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_batches": 1.1e-07,
"litellm_provider": "azure",
@ -71833,11 +71895,13 @@
"deprecation_date": "2027-09-07",
"input_cost_per_token": 3.3e-05,
"input_cost_per_token_above_272k_tokens": 6.6e-05,
"input_cost_per_token_above_272k_tokens_batches": 3.3e-05,
"input_cost_per_token_batches": 1.65e-05,
"litellm_provider": "azure",
"mode": "chat",
"output_cost_per_token": 0.000198,
"output_cost_per_token_above_272k_tokens": 0.000297,
"output_cost_per_token_above_272k_tokens_batches": 0.0001485,
"output_cost_per_token_batches": 9.9e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},