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 100

fix(cost-map): add vertex cache read, batch and above 200k prices for gemini image preview rows (#42995)

Browse source 
* fix(cost-map): add vertex cache read prices for gemini image preview rows

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(cost-map): add batch cache read and above 200k tiers to vertex gemini image preview rows

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

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 11:08:09 -07:00 • committed by GitHub
parent 0fa1fe2059
commit d3462c65b5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 36 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
litellm/model_prices_and_context_window_backup.json
View file

@ -26312,7 +26312,11 @@
},
"gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_read_input_token_cost_batches": 1e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
@ -26322,6 +26326,7 @@
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
@ -26398,7 +26403,10 @@
},
"gemini-3.1-flash-image-preview": {
"input_cost_per_image": 0.00056,
"cache_read_input_token_cost": 5e-08,
"cache_read_input_token_cost_batches": 2.5e-08,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
@ -26407,6 +26415,7 @@
"output_cost_per_image": 0.0672,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 3e-06,
"output_cost_per_token_batches": 1.5e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
"supported_endpoints": [
"/v1/chat/completions",
@ -49484,7 +49493,11 @@
},
"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_above_200k_tokens": 4e-07,
"cache_read_input_token_cost_batches": 1e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
@ -49494,6 +49507,7 @@
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-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"
@ -49522,7 +49536,10 @@
},
"vertex_ai/gemini-3.1-flash-image-preview": {
"input_cost_per_image": 0.00056,
"cache_read_input_token_cost": 5e-08,
"cache_read_input_token_cost_batches": 2.5e-08,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
@ -49531,6 +49548,7 @@
"output_cost_per_image": 0.0672,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 3e-06,
"output_cost_per_token_batches": 1.5e-06,
"supports_reasoning": false,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
},

18
model_prices_and_context_window.json
View file

@ -26312,7 +26312,11 @@
},
"gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"cache_read_input_token_cost_batches": 1e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
@ -26322,6 +26326,7 @@
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
@ -26398,7 +26403,10 @@
},
"gemini-3.1-flash-image-preview": {
"input_cost_per_image": 0.00056,
"cache_read_input_token_cost": 5e-08,
"cache_read_input_token_cost_batches": 2.5e-08,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
@ -26407,6 +26415,7 @@
"output_cost_per_image": 0.0672,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 3e-06,
"output_cost_per_token_batches": 1.5e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
"supported_endpoints": [
"/v1/chat/completions",
@ -49484,7 +49493,11 @@
},
"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_above_200k_tokens": 4e-07,
"cache_read_input_token_cost_batches": 1e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
@ -49494,6 +49507,7 @@
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_200k_tokens": 1.8e-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"
@ -49522,7 +49536,10 @@
},
"vertex_ai/gemini-3.1-flash-image-preview": {
"input_cost_per_image": 0.00056,
"cache_read_input_token_cost": 5e-08,
"cache_read_input_token_cost_batches": 2.5e-08,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
@ -49531,6 +49548,7 @@
"output_cost_per_image": 0.0672,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 3e-06,
"output_cost_per_token_batches": 1.5e-06,
"supports_reasoning": false,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
},