From 01cec8f9381e2afb4f0c957de84d93e2777fa435 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Wed, 14 Oct 2026 16:47:00 -0700 Subject: [PATCH] fix(vertex-ai): add flex prices to gemini-nano-banana-2.1 (#46512) Price-Sync: litellm-providers Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Co-authored-by: Kerry Lu --- litellm/model_prices_and_context_window_backup.json | 6 ++++++ model_prices_and_context_window.json | 6 ++++++ 2 files changed, 12 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 9011e4511d7..04f391d4d20 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -72571,10 +72571,12 @@ "gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_image": 0.00168, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, @@ -72585,6 +72587,7 @@ "output_cost_per_image_token": 3e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -72617,10 +72620,12 @@ "vertex_ai/gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_image": 0.00168, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, @@ -72631,6 +72636,7 @@ "output_cost_per_image_token": 3e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9011e4511d7..04f391d4d20 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -72571,10 +72571,12 @@ "gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_image": 0.00168, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, @@ -72585,6 +72587,7 @@ "output_cost_per_image_token": 3e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -72617,10 +72620,12 @@ "vertex_ai/gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_image": 0.00168, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, @@ -72631,6 +72636,7 @@ "output_cost_per_image_token": 3e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",