Skip to content

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

fix(vertex-ai): drop flex prices from gemini-nano-banana-2.1 (#47666)

berriai-litellm-provider-info-sync[bot]8e3ce6d110ca
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 15eba7f8af8..b6521557f83 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -75064,12 +75064,10 @@
"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,
@@ -75080,7 +75078,6 @@
"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",
@@ -75113,12 +75110,10 @@
"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,
@@ -75129,7 +75124,6 @@
"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 15eba7f8af8..b6521557f83 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -75064,12 +75064,10 @@
"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,
@@ -75080,7 +75078,6 @@
"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",
@@ -75113,12 +75110,10 @@
"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,
@@ -75129,7 +75124,6 @@
"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",