scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-12 23:01:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 182

fix(model_prices): set prompt_cache_min_tokens=4096 for gemini 3.5/3.6/3.7 flash and 3.1 pro preview

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
milan 2026-08-19 03:02:30 +00:00
parent bc6e7df05b
commit 5bc7fe574e
2 changed files with 24 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
litellm/model_prices_and_context_window_backup.json
View file

@ -19163,6 +19163,7 @@
},
"gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
"input_cost_per_token": 2e-06,
@ -19374,6 +19375,7 @@
},
"vertex_ai/gemini-3.5-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"input_cost_per_token": 1.5e-06,
"input_cost_per_audio_token": 1e-06,
"litellm_provider": "vertex_ai",
@ -19425,6 +19427,7 @@
},
"vertex_ai/gemini-3.6-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 7.5e-08,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_batches": 7.5e-07,
@ -19479,6 +19482,7 @@
},
"vertex_ai/gemini-3.7-flash": {
"cache_read_input_token_cost": 7.5e-08,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
@ -19533,6 +19537,7 @@
},
"vertex_ai/gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
"input_cost_per_token": 2e-06,
@ -21097,6 +21102,7 @@
},
"gemini/gemini-3.5-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "gemini",
@ -21151,6 +21157,7 @@
},
"gemini/gemini-3.6-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 7.5e-08,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_batches": 7.5e-07,
@ -21208,6 +21215,7 @@
},
"gemini/gemini-3.7-flash": {
"cache_read_input_token_cost": 7.5e-08,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
@ -21298,6 +21306,7 @@
},
"gemini/gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
@ -21493,6 +21502,7 @@
},
"gemini-3.5-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "vertex_ai-language-models",
@ -21545,6 +21555,7 @@
},
"gemini-3.6-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 7.5e-08,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_batches": 7.5e-07,
@ -21600,6 +21611,7 @@
},
"gemini-3.7-flash": {
"cache_read_input_token_cost": 7.5e-08,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,

12
model_prices_and_context_window.json
View file

@ -19163,6 +19163,7 @@
},
"gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
"input_cost_per_token": 2e-06,
@ -19374,6 +19375,7 @@
},
"vertex_ai/gemini-3.5-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"input_cost_per_token": 1.5e-06,
"input_cost_per_audio_token": 1e-06,
"litellm_provider": "vertex_ai",
@ -19425,6 +19427,7 @@
},
"vertex_ai/gemini-3.6-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 7.5e-08,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_batches": 7.5e-07,
@ -19479,6 +19482,7 @@
},
"vertex_ai/gemini-3.7-flash": {
"cache_read_input_token_cost": 7.5e-08,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
@ -19533,6 +19537,7 @@
},
"vertex_ai/gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
"input_cost_per_token": 2e-06,
@ -21097,6 +21102,7 @@
},
"gemini/gemini-3.5-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "gemini",
@ -21151,6 +21157,7 @@
},
"gemini/gemini-3.6-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 7.5e-08,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_batches": 7.5e-07,
@ -21208,6 +21215,7 @@
},
"gemini/gemini-3.7-flash": {
"cache_read_input_token_cost": 7.5e-08,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
@ -21298,6 +21306,7 @@
},
"gemini/gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
@ -21493,6 +21502,7 @@
},
"gemini-3.5-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "vertex_ai-language-models",
@ -21545,6 +21555,7 @@
},
"gemini-3.6-flash": {
"cache_read_input_token_cost": 1.5e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 7.5e-08,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_batches": 7.5e-07,
@ -21600,6 +21611,7 @@
},
"gemini-3.7-flash": {
"cache_read_input_token_cost": 7.5e-08,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,