scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-27 06:13:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 72

feat(model-prices): add Vertex batch rates for Llama 4 MaaS models (#48085)

Browse source 
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Kerry Lu 2026-10-23 14:47:17 -07:00 • committed by GitHub
parent ada3614eb4
commit 8fa875ff92
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 8 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/model_prices_and_context_window_backup.json
View file

@ -52906,12 +52906,14 @@
},
"vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": {
"input_cost_per_token": 3.5e-07,
"input_cost_per_token_batches": 1.75e-07,
"litellm_provider": "vertex_ai-llama_models",
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 1.15e-06,
"output_cost_per_token_batches": 5.75e-07,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
"supported_modalities": [
"text",
@ -52926,12 +52928,14 @@
},
"vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"litellm_provider": "vertex_ai-llama_models",
"max_input_tokens": 10000000,
"max_output_tokens": 10000000,
"max_tokens": 10000000,
"mode": "chat",
"output_cost_per_token": 7e-07,
"output_cost_per_token_batches": 3.5e-07,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
"supported_modalities": [
"text",

4
model_prices_and_context_window.json
View file

@ -52906,12 +52906,14 @@
},
"vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": {
"input_cost_per_token": 3.5e-07,
"input_cost_per_token_batches": 1.75e-07,
"litellm_provider": "vertex_ai-llama_models",
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 1.15e-06,
"output_cost_per_token_batches": 5.75e-07,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
"supported_modalities": [
"text",
@ -52926,12 +52928,14 @@
},
"vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"litellm_provider": "vertex_ai-llama_models",
"max_input_tokens": 10000000,
"max_output_tokens": 10000000,
"max_tokens": 10000000,
"mode": "chat",
"output_cost_per_token": 7e-07,
"output_cost_per_token_batches": 3.5e-07,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
"supported_modalities": [
"text",