From 2eeb16266b906494d3a961d0d03da20810b49924 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 24 Sep 2026 04:39:09 -0700 Subject: [PATCH] fix(cost-map): sync vertex-ai rows (gemma 4 maas cache price, chirp_2) (#42942) * fix(cost-map): sync vertex-ai rows (gemma 4 maas cache price, chirp_2) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(vertex-ai): expect chirp_2 as speech-to-text model now that catalog row exists Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: kerry Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../model_prices_and_context_window_backup.json | 15 +++++++++++++++ model_prices_and_context_window.json | 15 +++++++++++++++ .../test_vertex_ai_realtime_transformation.py | 2 +- 3 files changed, 31 insertions(+), 1 deletion(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 54475f38364..298ec16fc55 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -48131,6 +48131,20 @@ "/v1/realtime" ] }, + "vertex_ai/chirp_2": { + "input_cost_per_second": 0.00026667, + "litellm_provider": "vertex_ai", + "metadata": { + "calculation": "$0.016/60 seconds = $0.00026667 per second", + "original_pricing_per_minute": 0.016 + }, + "mode": "audio_transcription", + "source": "https://cloud.google.com/speech-to-text/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions", + "/v1/realtime" + ] + }, "vertex_ai/claude-3-5-haiku": { "deprecation_date": "2026-07-05", "input_cost_per_token": 1e-06, @@ -50155,6 +50169,7 @@ ] }, "vertex_ai/google/gemma-4-26b-a4b-it-maas": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 262144, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 54475f38364..298ec16fc55 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -48131,6 +48131,20 @@ "/v1/realtime" ] }, + "vertex_ai/chirp_2": { + "input_cost_per_second": 0.00026667, + "litellm_provider": "vertex_ai", + "metadata": { + "calculation": "$0.016/60 seconds = $0.00026667 per second", + "original_pricing_per_minute": 0.016 + }, + "mode": "audio_transcription", + "source": "https://cloud.google.com/speech-to-text/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions", + "/v1/realtime" + ] + }, "vertex_ai/claude-3-5-haiku": { "deprecation_date": "2026-07-05", "input_cost_per_token": 1e-06, @@ -50155,6 +50169,7 @@ ] }, "vertex_ai/google/gemma-4-26b-a4b-it-maas": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 262144, diff --git a/tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_transformation.py b/tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_transformation.py index 84c3a4e244a..b50d6e19458 100644 --- a/tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_transformation.py +++ b/tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_transformation.py @@ -115,7 +115,7 @@ def _commands(config: VertexChirpRealtimeConfig, payload: str) -> list[object]: [ ("vertex_ai/chirp_3", True), ("chirp_3", True), - ("chirp_2", False), + ("chirp_2", True), ("gemini-live-2.5-flash", False), ("vertex_ai/gemini-2.0-flash-live-preview-04-09", False), ("vertex_ai/gemini-3.5-transcribe-live-preview", False),