From 53ce41625fdd64afd26a70b77179018a0760bccc Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 29 Oct 2026 18:30:38 -0700 Subject: [PATCH] chore(databricks): retirement dates for DeepSeek V4 Flash (0731), V4 Pro (0813) and Inkling (#49124) * chore(databricks): retirement dates for DeepSeek V4 Pro (0813) and Inkling * chore(databricks): retirement dates for DeepSeek V4 Flash (0731), V4 Pro (0813) and Inkling --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 43 ++++++++++--------- model_prices_and_context_window.json | 43 ++++++++++--------- 2 files changed, 46 insertions(+), 40 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 82b1ad9bc5d..72509bd3c69 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -21435,7 +21435,7 @@ "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, "deprecation_date": "2026-10-09", - "input_cost_per_token": 2.9999900000000002e-06, + "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, @@ -21444,7 +21444,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, "output_dbu_cost_per_token": 0.000214286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", @@ -21557,6 +21557,7 @@ "databricks/databricks-deepseek-v4-flash-0731": { "cache_creation_input_token_cost": 1.4e-07, "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-11-05", "input_cost_per_token": 1.4e-07, "input_dbu_cost_per_token": 2e-06, "litellm_provider": "databricks", @@ -21569,7 +21570,7 @@ "mode": "chat", "output_cost_per_token": 2.8e-07, "output_dbu_cost_per_token": 4e-06, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text" ], @@ -21590,6 +21591,7 @@ "databricks/databricks-deepseek-v4-pro-0813": { "cache_creation_input_token_cost": 1.31999e-06, "cache_read_input_token_cost": 1.3202e-07, + "deprecation_date": "2026-10-30", "input_cost_per_token": 1.31999e-06, "input_dbu_cost_per_token": 1.8857e-05, "litellm_provider": "databricks", @@ -21601,7 +21603,7 @@ "mode": "chat", "output_cost_per_token": 3.95997e-06, "output_dbu_cost_per_token": 5.6571e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text" ], @@ -21788,7 +21790,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, "output_cost_per_token_above_200k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", @@ -22047,7 +22049,7 @@ "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 128000, @@ -22170,7 +22172,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, + "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -22193,7 +22195,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, + "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -22264,7 +22266,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", @@ -22539,7 +22541,7 @@ "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, "cache_read_input_token_cost": 2.499e-08, - "input_cost_per_token": 2.4997000000000006e-07, + "input_cost_per_token": 2.4997e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", "max_input_tokens": 272000, @@ -22548,7 +22550,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.9999700000000004e-06, + "output_cost_per_token": 1.99997e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -22571,7 +22573,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 3.9998000000000007e-07, + "output_cost_per_token": 3.9998e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -22581,7 +22583,7 @@ "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 131072, @@ -22606,7 +22608,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 3.0001999999999996e-07, + "output_cost_per_token": 3.0002e-07, "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, @@ -22639,7 +22641,7 @@ "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, - "input_cost_per_token": 1.2999000000000001e-07, + "input_cost_per_token": 1.2999e-07, "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", "max_input_tokens": 8192, @@ -22655,6 +22657,7 @@ "databricks/databricks-inkling": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.7003e-07, + "deprecation_date": "2026-10-30", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -22665,7 +22668,7 @@ "mode": "chat", "output_cost_per_token": 4.04999e-06, "output_dbu_cost_per_token": 5.7857e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image" @@ -22730,7 +22733,7 @@ "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, + "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true @@ -22738,7 +22741,7 @@ "databricks/databricks-meta-llama-3-1-8b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 200000, @@ -22747,7 +22750,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 4.5003000000000007e-07, + "output_cost_per_token": 4.5003e-07, "output_dbu_cost_per_token": 6.429000000000001e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, @@ -22763,7 +22766,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, + "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 82b1ad9bc5d..72509bd3c69 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -21435,7 +21435,7 @@ "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, "deprecation_date": "2026-10-09", - "input_cost_per_token": 2.9999900000000002e-06, + "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, @@ -21444,7 +21444,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, "output_dbu_cost_per_token": 0.000214286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", @@ -21557,6 +21557,7 @@ "databricks/databricks-deepseek-v4-flash-0731": { "cache_creation_input_token_cost": 1.4e-07, "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-11-05", "input_cost_per_token": 1.4e-07, "input_dbu_cost_per_token": 2e-06, "litellm_provider": "databricks", @@ -21569,7 +21570,7 @@ "mode": "chat", "output_cost_per_token": 2.8e-07, "output_dbu_cost_per_token": 4e-06, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text" ], @@ -21590,6 +21591,7 @@ "databricks/databricks-deepseek-v4-pro-0813": { "cache_creation_input_token_cost": 1.31999e-06, "cache_read_input_token_cost": 1.3202e-07, + "deprecation_date": "2026-10-30", "input_cost_per_token": 1.31999e-06, "input_dbu_cost_per_token": 1.8857e-05, "litellm_provider": "databricks", @@ -21601,7 +21603,7 @@ "mode": "chat", "output_cost_per_token": 3.95997e-06, "output_dbu_cost_per_token": 5.6571e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text" ], @@ -21788,7 +21790,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, "output_cost_per_token_above_200k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", @@ -22047,7 +22049,7 @@ "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 128000, @@ -22170,7 +22172,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, + "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -22193,7 +22195,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, + "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -22264,7 +22266,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", @@ -22539,7 +22541,7 @@ "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, "cache_read_input_token_cost": 2.499e-08, - "input_cost_per_token": 2.4997000000000006e-07, + "input_cost_per_token": 2.4997e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", "max_input_tokens": 272000, @@ -22548,7 +22550,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.9999700000000004e-06, + "output_cost_per_token": 1.99997e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -22571,7 +22573,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 3.9998000000000007e-07, + "output_cost_per_token": 3.9998e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -22581,7 +22583,7 @@ "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 131072, @@ -22606,7 +22608,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 3.0001999999999996e-07, + "output_cost_per_token": 3.0002e-07, "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, @@ -22639,7 +22641,7 @@ "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, - "input_cost_per_token": 1.2999000000000001e-07, + "input_cost_per_token": 1.2999e-07, "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", "max_input_tokens": 8192, @@ -22655,6 +22657,7 @@ "databricks/databricks-inkling": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.7003e-07, + "deprecation_date": "2026-10-30", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -22665,7 +22668,7 @@ "mode": "chat", "output_cost_per_token": 4.04999e-06, "output_dbu_cost_per_token": 5.7857e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image" @@ -22730,7 +22733,7 @@ "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, + "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true @@ -22738,7 +22741,7 @@ "databricks/databricks-meta-llama-3-1-8b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 200000, @@ -22747,7 +22750,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 4.5003000000000007e-07, + "output_cost_per_token": 4.5003e-07, "output_dbu_cost_per_token": 6.429000000000001e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, @@ -22763,7 +22766,7 @@ "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, + "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true