From d2bae98d97c6b9905bdebd96fde8b3d34176b857 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Fri, 13 Nov 2026 23:18:03 +0000 Subject: [PATCH] fix(model-prices): drop Flex prices from Vertex AI Gemini 4 Argon and Hydrogen (#51735) * fix(model-prices): drop Flex prices from Vertex AI Gemini 4 Argon and Hydrogen * test(cost-calc): stop comparing Flex prices between Vertex AI and Gemini API Gemini 4 Argon Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: kerry --- litellm/model_prices_and_context_window_backup.json | 9 --------- model_prices_and_context_window.json | 9 --------- .../llm_cost_calc/test_llm_cost_calc_utils.py | 3 --- 3 files changed, 21 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 08b7f4700ca..9c0c65406b1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -79427,7 +79427,6 @@ "vertex_ai/gemini-4-argon": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, "cache_read_input_token_cost_priority": 1.8e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 2e-06, @@ -79435,7 +79434,6 @@ "input_cost_per_audio_token_priority": 3.6e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, - "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, @@ -79444,7 +79442,6 @@ "output_cost_per_reasoning_token": 1e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, @@ -79487,7 +79484,6 @@ "vertex_ai/gemini-4-argon-cyber-permissive": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, - "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 4e-06, @@ -79495,7 +79491,6 @@ "input_cost_per_audio_token_priority": 7.2e-06, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, - "input_cost_per_token_flex": 2e-06, "input_cost_per_token_priority": 7.2e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, @@ -79504,7 +79499,6 @@ "output_cost_per_reasoning_token": 2e-05, "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, - "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 3.6e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, @@ -101738,7 +101732,6 @@ "vertex_ai/gemini-4-hydrogen": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, - "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.35e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1.5e-06, @@ -101746,7 +101739,6 @@ "input_cost_per_audio_token_priority": 2.7e-06, "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", "max_input_tokens": 1048576, @@ -101755,7 +101747,6 @@ "output_cost_per_reasoning_token": 7.5e-06, "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, "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 08b7f4700ca..9c0c65406b1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -79427,7 +79427,6 @@ "vertex_ai/gemini-4-argon": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, "cache_read_input_token_cost_priority": 1.8e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 2e-06, @@ -79435,7 +79434,6 @@ "input_cost_per_audio_token_priority": 3.6e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, - "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, @@ -79444,7 +79442,6 @@ "output_cost_per_reasoning_token": 1e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, @@ -79487,7 +79484,6 @@ "vertex_ai/gemini-4-argon-cyber-permissive": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, - "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 4e-06, @@ -79495,7 +79491,6 @@ "input_cost_per_audio_token_priority": 7.2e-06, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, - "input_cost_per_token_flex": 2e-06, "input_cost_per_token_priority": 7.2e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, @@ -79504,7 +79499,6 @@ "output_cost_per_reasoning_token": 2e-05, "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, - "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 3.6e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, @@ -101738,7 +101732,6 @@ "vertex_ai/gemini-4-hydrogen": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, - "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.35e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1.5e-06, @@ -101746,7 +101739,6 @@ "input_cost_per_audio_token_priority": 2.7e-06, "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", "max_input_tokens": 1048576, @@ -101755,7 +101747,6 @@ "output_cost_per_reasoning_token": 7.5e-06, "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, "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 6612d28c43b..eadff039d81 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -4627,16 +4627,13 @@ def test_token_type_cost_breakdown_bills_cache_tokens_at_the_provider_speed_mult GEMINI_4_ARGON_TOKEN_PRICE_KEYS: Final = ( "input_cost_per_token", "input_cost_per_token_batches", - "input_cost_per_token_flex", "input_cost_per_token_priority", "output_cost_per_token", "output_cost_per_token_batches", - "output_cost_per_token_flex", "output_cost_per_token_priority", "output_cost_per_reasoning_token", "cache_read_input_token_cost", "cache_read_input_token_cost_batches", - "cache_read_input_token_cost_flex", "cache_read_input_token_cost_priority", )