scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-26 01:12:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 99

fix(cost-map): add vertex priority prices for gemini-3-pro-image-preview and batch price for gemini-embedding-001 (#43069)

Browse source 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-09-24 16:26:44 -07:00 • committed by GitHub
parent 3fa688223d
commit 1dc3b62dbc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 26 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
litellm/model_prices_and_context_window_backup.json
View file

@ -26312,10 +26312,14 @@
"gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_priority": 3.6e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
"cache_read_input_token_cost_batches": 1e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_priority": 3.6e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
@ -26325,7 +26329,9 @@
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_priority": 2.16e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-05,
"output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
@ -27848,6 +27854,7 @@
"gemini-embedding-001": {
"deprecation_date": "2028-05-20",
"input_cost_per_token": 1.5e-07,
"input_cost_per_token_batches": 1.2e-07,
"litellm_provider": "vertex_ai-embedding-models",
"max_input_tokens": 2048,
"max_tokens": 2048,
@ -49492,10 +49499,14 @@
"vertex_ai/gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_priority": 3.6e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
"cache_read_input_token_cost_batches": 1e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_priority": 3.6e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
@ -49505,7 +49516,9 @@
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_priority": 2.16e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-05,
"output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
"output_cost_per_token_batches": 6e-06,
"supports_reasoning": false,
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"

13
model_prices_and_context_window.json
View file

@ -26312,10 +26312,14 @@
"gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_priority": 3.6e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
"cache_read_input_token_cost_batches": 1e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_priority": 3.6e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
@ -26325,7 +26329,9 @@
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_priority": 2.16e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-05,
"output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
@ -27848,6 +27854,7 @@
"gemini-embedding-001": {
"deprecation_date": "2028-05-20",
"input_cost_per_token": 1.5e-07,
"input_cost_per_token_batches": 1.2e-07,
"litellm_provider": "vertex_ai-embedding-models",
"max_input_tokens": 2048,
"max_tokens": 2048,
@ -49492,10 +49499,14 @@
"vertex_ai/gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_priority": 3.6e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
"cache_read_input_token_cost_batches": 1e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_priority": 3.6e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
@ -49505,7 +49516,9 @@
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_priority": 2.16e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-05,
"output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
"output_cost_per_token_batches": 6e-06,
"supports_reasoning": false,
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"