From 8fa875ff92ccb56424702abe0dd05a4fcdb399d7 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Fri, 23 Oct 2026 14:47:17 -0700 Subject: [PATCH] feat(model-prices): add Vertex batch rates for Llama 4 MaaS models (#48085) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 4 ++++ model_prices_and_context_window.json | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 840576e8225..dd98a273e2d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -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", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 840576e8225..dd98a273e2d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -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",