From baa68ebb120187cbcc342d7641f2e0bdd4c31772 Mon Sep 17 00:00:00 2001 From: lmcdonald-godaddy Date: Wed, 13 May 2026 17:42:05 -0700 Subject: [PATCH] fix(pricing): GPT-4o-Transcribe Pricing (#27875) * Update gpt-4o-transcribe price * Update test for gpt-4o-transcribe pricing fix * Update gpt-4o-mini-transcribe price --- .../model_prices_and_context_window_backup.json | 16 ++++++++-------- model_prices_and_context_window.json | 16 ++++++++-------- tests/test_litellm/test_cost_calculator.py | 2 +- 3 files changed, 17 insertions(+), 17 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 61e0dd07968..543172b8381 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3521,7 +3521,7 @@ "supports_tool_choice": true }, "azure/gpt-4o-mini-transcribe": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -3596,7 +3596,7 @@ "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -3608,7 +3608,7 @@ ] }, "azure/gpt-4o-transcribe-diarize": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -8974,7 +8974,7 @@ "supports_vision": true }, "gpt-4o-transcribe-diarize": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -18991,7 +18991,7 @@ "supports_vision": true }, "gpt-4o-mini-transcribe": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -19121,7 +19121,7 @@ "supports_vision": true }, "gpt-4o-transcribe": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -38933,7 +38933,7 @@ ] }, "gpt-4o-mini-transcribe-2025-03-20": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -38945,7 +38945,7 @@ ] }, "gpt-4o-mini-transcribe-2025-12-15": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e62f8686e9d..269e7daecc1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3521,7 +3521,7 @@ "supports_tool_choice": true }, "azure/gpt-4o-mini-transcribe": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -3596,7 +3596,7 @@ "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -3608,7 +3608,7 @@ ] }, "azure/gpt-4o-transcribe-diarize": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -8974,7 +8974,7 @@ "supports_vision": true }, "gpt-4o-transcribe-diarize": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -18996,7 +18996,7 @@ "supports_vision": true }, "gpt-4o-mini-transcribe": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -19126,7 +19126,7 @@ "supports_vision": true }, "gpt-4o-transcribe": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -38938,7 +38938,7 @@ ] }, "gpt-4o-mini-transcribe-2025-03-20": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -38950,7 +38950,7 @@ ] }, "gpt-4o-mini-transcribe-2025-12-15": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py index e53484dd287..d5c1132c5fd 100644 --- a/tests/test_litellm/test_cost_calculator.py +++ b/tests/test_litellm/test_cost_calculator.py @@ -235,7 +235,7 @@ def test_transcription_cost_uses_token_pricing(): call_type="atranscription", ) - expected_cost = (14 * 6e-06) + (45 * 1e-05) + expected_cost = (14 * 2.5e-06) + (45 * 1e-05) assert pytest.approx(cost, rel=1e-6) == expected_cost