From 6b036ddcc1c06d8e624f28ed60e3b250199e2f52 Mon Sep 17 00:00:00 2001 From: shrey kharbanda Date: Thu, 24 Sep 2026 04:57:26 +0000 Subject: [PATCH] feat(sail): balanced and flex tier pricing --- ci_cd/generate_model_prices_schema.py | 2 + ...odel_prices_and_context_window_backup.json | 57 +++++++++++++++++++ model_prices_and_context_window.json | 57 +++++++++++++++++++ model_prices_and_context_window.schema.json | 15 +++++ 4 files changed, 131 insertions(+) diff --git a/ci_cd/generate_model_prices_schema.py b/ci_cd/generate_model_prices_schema.py index 8eec07dadda..8d0431e286b 100644 --- a/ci_cd/generate_model_prices_schema.py +++ b/ci_cd/generate_model_prices_schema.py @@ -228,6 +228,8 @@ COST_DESCRIPTIONS: dict[str, str] = { def cost_description(key: str) -> Optional[str]: if key in COST_DESCRIPTIONS: return COST_DESCRIPTIONS[key] + if key.endswith("_balanced"): + return "Balanced service-tier rate for the same-named base field." if key.endswith("_flex"): return "Flex service-tier rate for the same-named base field." if key.endswith("_priority"): diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 742fca4f6d5..214b3f2d350 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -57952,6 +57952,12 @@ "input_cost_per_token": 2.5e-06, "output_cost_per_token": 1.25e-05, "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token_balanced": 2e-06, + "output_cost_per_token_balanced": 1e-05, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_flex": 6.25e-06, + "cache_read_input_token_cost_flex": 1.5e-07, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -57968,6 +57974,12 @@ "input_cost_per_token": 9.8e-07, "output_cost_per_token": 3.08e-06, "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token_balanced": 5e-07, + "output_cost_per_token_balanced": 2.5e-06, + "cache_read_input_token_cost_balanced": 1.2e-07, + "input_cost_per_token_flex": 4e-07, + "output_cost_per_token_flex": 1.8e-06, + "cache_read_input_token_cost_flex": 8e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -57984,6 +57996,12 @@ "input_cost_per_token": 1.1e-07, "output_cost_per_token": 3.5e-07, "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 8e-08, + "output_cost_per_token_balanced": 2.8e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.8e-07, + "cache_read_input_token_cost_flex": 1e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58000,6 +58018,12 @@ "input_cost_per_token": 9.2e-07, "output_cost_per_token": 2.77e-06, "cache_read_input_token_cost": 4e-08, + "input_cost_per_token_balanced": 7.4e-07, + "output_cost_per_token_balanced": 2.22e-06, + "cache_read_input_token_cost_balanced": 3e-08, + "input_cost_per_token_flex": 4.6e-07, + "output_cost_per_token_flex": 1.39e-06, + "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58016,6 +58040,12 @@ "input_cost_per_token": 9e-08, "output_cost_per_token": 1.8e-07, "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 1.4e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 9e-08, + "cache_read_input_token_cost_flex": 1e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58032,6 +58062,12 @@ "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 6e-09, + "input_cost_per_token_balanced": 1.2e-07, + "output_cost_per_token_balanced": 4.8e-07, + "cache_read_input_token_cost_balanced": 5e-09, + "input_cost_per_token_flex": 8e-08, + "output_cost_per_token_flex": 3e-07, + "cache_read_input_token_cost_flex": 4e-09, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58048,6 +58084,12 @@ "input_cost_per_token": 1e-06, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 4.5e-07, + "output_cost_per_token_balanced": 3e-06, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 3.5e-07, + "output_cost_per_token_flex": 2e-06, + "cache_read_input_token_cost_flex": 1e-07, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58088,6 +58130,12 @@ "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 7e-08, + "input_cost_per_token_balanced": 1.1e-07, + "output_cost_per_token_balanced": 3.2e-07, + "cache_read_input_token_cost_balanced": 6e-08, + "input_cost_per_token_flex": 7e-08, + "output_cost_per_token_flex": 2e-07, + "cache_read_input_token_cost_flex": 4e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58105,6 +58153,12 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 2e-06, "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token_balanced": 1e-07, + "output_cost_per_token_balanced": 2e-06, + "cache_read_input_token_cost_balanced": 7e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1e-06, + "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58137,6 +58191,9 @@ "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 4e-07, + "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 742fca4f6d5..214b3f2d350 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -57952,6 +57952,12 @@ "input_cost_per_token": 2.5e-06, "output_cost_per_token": 1.25e-05, "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token_balanced": 2e-06, + "output_cost_per_token_balanced": 1e-05, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_flex": 6.25e-06, + "cache_read_input_token_cost_flex": 1.5e-07, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -57968,6 +57974,12 @@ "input_cost_per_token": 9.8e-07, "output_cost_per_token": 3.08e-06, "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token_balanced": 5e-07, + "output_cost_per_token_balanced": 2.5e-06, + "cache_read_input_token_cost_balanced": 1.2e-07, + "input_cost_per_token_flex": 4e-07, + "output_cost_per_token_flex": 1.8e-06, + "cache_read_input_token_cost_flex": 8e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -57984,6 +57996,12 @@ "input_cost_per_token": 1.1e-07, "output_cost_per_token": 3.5e-07, "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 8e-08, + "output_cost_per_token_balanced": 2.8e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.8e-07, + "cache_read_input_token_cost_flex": 1e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58000,6 +58018,12 @@ "input_cost_per_token": 9.2e-07, "output_cost_per_token": 2.77e-06, "cache_read_input_token_cost": 4e-08, + "input_cost_per_token_balanced": 7.4e-07, + "output_cost_per_token_balanced": 2.22e-06, + "cache_read_input_token_cost_balanced": 3e-08, + "input_cost_per_token_flex": 4.6e-07, + "output_cost_per_token_flex": 1.39e-06, + "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58016,6 +58040,12 @@ "input_cost_per_token": 9e-08, "output_cost_per_token": 1.8e-07, "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 1.4e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 9e-08, + "cache_read_input_token_cost_flex": 1e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58032,6 +58062,12 @@ "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 6e-09, + "input_cost_per_token_balanced": 1.2e-07, + "output_cost_per_token_balanced": 4.8e-07, + "cache_read_input_token_cost_balanced": 5e-09, + "input_cost_per_token_flex": 8e-08, + "output_cost_per_token_flex": 3e-07, + "cache_read_input_token_cost_flex": 4e-09, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58048,6 +58084,12 @@ "input_cost_per_token": 1e-06, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 4.5e-07, + "output_cost_per_token_balanced": 3e-06, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 3.5e-07, + "output_cost_per_token_flex": 2e-06, + "cache_read_input_token_cost_flex": 1e-07, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58088,6 +58130,12 @@ "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 7e-08, + "input_cost_per_token_balanced": 1.1e-07, + "output_cost_per_token_balanced": 3.2e-07, + "cache_read_input_token_cost_balanced": 6e-08, + "input_cost_per_token_flex": 7e-08, + "output_cost_per_token_flex": 2e-07, + "cache_read_input_token_cost_flex": 4e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58105,6 +58153,12 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 2e-06, "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token_balanced": 1e-07, + "output_cost_per_token_balanced": 2e-06, + "cache_read_input_token_cost_balanced": 7e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1e-06, + "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, @@ -58137,6 +58191,9 @@ "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 4e-07, + "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json index 737a9b7fa60..34812b13439 100644 --- a/model_prices_and_context_window.schema.json +++ b/model_prices_and_context_window.schema.json @@ -200,6 +200,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_read_input_token_cost_balanced": { + "type": "number", + "minimum": 0, + "description": "Balanced service-tier rate for the same-named base field." + }, "cache_read_input_token_cost_batches": { "type": "number", "minimum": 0 @@ -376,6 +381,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "input_cost_per_token_balanced": { + "type": "number", + "minimum": 0, + "description": "Balanced service-tier rate for the same-named base field." + }, "input_cost_per_token_batches": { "type": "number", "minimum": 0, @@ -712,6 +722,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "output_cost_per_token_balanced": { + "type": "number", + "minimum": 0, + "description": "Balanced service-tier rate for the same-named base field." + }, "output_cost_per_token_batches": { "type": "number", "minimum": 0,