scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(azure): add gpt-6-sol priority processing prices (#44829)

Browse source 
Price-Sync: litellm-providers

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] 2026-10-06 01:49:46 -07:00 • committed by GitHub
parent 5455152913
commit 18c3118eb6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 54 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
litellm/model_prices_and_context_window_backup.json
View file

@ -8480,11 +8480,17 @@
"azure/gpt-6-sol": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_priority": 4e-07,
"deprecation_date": "2028-03-11",
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"input_cost_per_token_priority": 4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -8492,11 +8498,9 @@
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"output_cost_per_token_above_272k_tokens_priority": 3e-05,
"output_cost_per_token_priority": 2e-05,
"search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
@ -8529,11 +8533,17 @@
"azure/gpt-6-sol-2026-09-22": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_priority": 4e-07,
"deprecation_date": "2028-03-11",
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"input_cost_per_token_priority": 4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -8541,11 +8551,9 @@
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"output_cost_per_token_above_272k_tokens_priority": 3e-05,
"output_cost_per_token_priority": 2e-05,
"search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
@ -9071,10 +9079,16 @@
"deprecation_date": "2028-03-11",
"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,
"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,
"max_output_tokens": 128000,
@ -9082,11 +9096,9 @@
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_above_272k_tokens": 1.65e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"output_cost_per_token_above_272k_tokens_priority": 3.3e-05,
"output_cost_per_token_priority": 2.2e-05,
"search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",

42
model_prices_and_context_window.json
View file

@ -8480,11 +8480,17 @@
"azure/gpt-6-sol": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_priority": 4e-07,
"deprecation_date": "2028-03-11",
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"input_cost_per_token_priority": 4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -8492,11 +8498,9 @@
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"output_cost_per_token_above_272k_tokens_priority": 3e-05,
"output_cost_per_token_priority": 2e-05,
"search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
@ -8529,11 +8533,17 @@
"azure/gpt-6-sol-2026-09-22": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_priority": 4e-07,
"deprecation_date": "2028-03-11",
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"input_cost_per_token_priority": 4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -8541,11 +8551,9 @@
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"output_cost_per_token_above_272k_tokens_priority": 3e-05,
"output_cost_per_token_priority": 2e-05,
"search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
@ -9071,10 +9079,16 @@
"deprecation_date": "2028-03-11",
"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,
"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,
"max_output_tokens": 128000,
@ -9082,11 +9096,9 @@
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_above_272k_tokens": 1.65e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"output_cost_per_token_above_272k_tokens_priority": 3.3e-05,
"output_cost_per_token_priority": 2.2e-05,
"search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",