From f1b781d06b6155df7c8979110ddc45938c3b81fb Mon Sep 17 00:00:00 2001 From: lihugang <94808542+lihugang@users.noreply.github.com> Date: Fri, 31 Jul 2026 04:08:01 +0800 Subject: [PATCH] fix(pricing): adjust gpt-5.6-terra and gpt-5.6-luna prices according to OpenAI's latest article (#35258) Adjust the price of gpt-5.6-terra to 80% of its original rate (2/12), and gpt-5.6-luna to 20% of its original rate (0.2/1.2). References: https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/ https://developers.openai.com/api/docs/pricing --- ...odel_prices_and_context_window_backup.json | 72 +++++++++---------- model_prices_and_context_window.json | 72 +++++++++---------- .../llm_cost_calc/test_llm_cost_calc_utils.py | 4 +- .../test_gpt_5_6_model_metadata.py | 15 ++-- 4 files changed, 85 insertions(+), 78 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index cc418c9c428..a431c4b29fc 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -23782,29 +23782,29 @@ "supports_xhigh_reasoning_effort": true }, "gpt-5.6-terra": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_272k_tokens": 6.25e-06, - "cache_creation_input_token_cost_flex": 1.5625e-06, - "cache_creation_input_token_cost_priority": 6.25e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "cache_read_input_token_cost_flex": 1.25e-07, - "cache_read_input_token_cost_priority": 5e-07, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_above_272k_tokens": 5e-06, - "input_cost_per_token_batches": 1.25e-06, - "input_cost_per_token_flex": 1.25e-06, - "input_cost_per_token_priority": 5e-06, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "output_cost_per_token_batches": 7.5e-06, - "output_cost_per_token_flex": 7.5e-06, - "output_cost_per_token_priority": 3e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.4e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ @@ -23835,29 +23835,29 @@ "supports_xhigh_reasoning_effort": true }, "gpt-5.6-luna": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_creation_input_token_cost_flex": 6.25e-07, - "cache_creation_input_token_cost_priority": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "cache_read_input_token_cost_flex": 5e-08, - "cache_read_input_token_cost_priority": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "input_cost_per_token_batches": 5e-07, - "input_cost_per_token_flex": 5e-07, - "input_cost_per_token_priority": 2e-06, + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_flex": 1.25e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_flex": 1e-08, + "cache_read_input_token_cost_priority": 4e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "output_cost_per_token_batches": 3e-06, - "output_cost_per_token_flex": 3e-06, - "output_cost_per_token_priority": 1.2e-05, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.4e-06, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index c4628fecdb8..184bc69c9e8 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -23857,29 +23857,29 @@ "supports_xhigh_reasoning_effort": true }, "gpt-5.6-terra": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_272k_tokens": 6.25e-06, - "cache_creation_input_token_cost_flex": 1.5625e-06, - "cache_creation_input_token_cost_priority": 6.25e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "cache_read_input_token_cost_flex": 1.25e-07, - "cache_read_input_token_cost_priority": 5e-07, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_above_272k_tokens": 5e-06, - "input_cost_per_token_batches": 1.25e-06, - "input_cost_per_token_flex": 1.25e-06, - "input_cost_per_token_priority": 5e-06, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "output_cost_per_token_batches": 7.5e-06, - "output_cost_per_token_flex": 7.5e-06, - "output_cost_per_token_priority": 3e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.4e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ @@ -23910,29 +23910,29 @@ "supports_xhigh_reasoning_effort": true }, "gpt-5.6-luna": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_creation_input_token_cost_flex": 6.25e-07, - "cache_creation_input_token_cost_priority": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "cache_read_input_token_cost_flex": 5e-08, - "cache_read_input_token_cost_priority": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "input_cost_per_token_batches": 5e-07, - "input_cost_per_token_flex": 5e-07, - "input_cost_per_token_priority": 2e-06, + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_flex": 1.25e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_flex": 1e-08, + "cache_read_input_token_cost_priority": 4e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "output_cost_per_token_batches": 3e-06, - "output_cost_per_token_flex": 3e-06, - "output_cost_per_token_priority": 1.2e-05, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.4e-06, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index d282e656ce8..1ad271900f6 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -611,8 +611,8 @@ def test_generic_cost_per_token_gpt55_pro(): [ ("gpt-5.6", 5e-6, 3e-5, 5e-7, 6.25e-6), ("gpt-5.6-sol", 5e-6, 3e-5, 5e-7, 6.25e-6), - ("gpt-5.6-terra", 2.5e-6, 1.5e-5, 2.5e-7, 3.125e-6), - ("gpt-5.6-luna", 1e-6, 6e-6, 1e-7, 1.25e-6), + ("gpt-5.6-terra", 2e-6, 1.2e-5, 2e-7, 2.5e-6), + ("gpt-5.6-luna", 2e-7, 1.2e-6, 2e-8, 2.5e-7), ], ) def test_generic_cost_per_token_gpt56( diff --git a/tests/test_litellm/test_gpt_5_6_model_metadata.py b/tests/test_litellm/test_gpt_5_6_model_metadata.py index 5a7b621d521..b17ef32a1dc 100644 --- a/tests/test_litellm/test_gpt_5_6_model_metadata.py +++ b/tests/test_litellm/test_gpt_5_6_model_metadata.py @@ -7,7 +7,14 @@ from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider GPT_5_6_MODELS = ("gpt-5.6", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna") -STANDARD_PRICING = { +OPENAI_STANDARD_PRICING = { + "gpt-5.6": (5e-06, 3e-05, 5e-07, 6.25e-06), + "gpt-5.6-sol": (5e-06, 3e-05, 5e-07, 6.25e-06), + "gpt-5.6-terra": (2e-06, 1.2e-05, 2e-07, 2.5e-06), + "gpt-5.6-luna": (2e-07, 1.2e-06, 2e-08, 2.5e-07), +} + +AZURE_STANDARD_PRICING = { "gpt-5.6": (5e-06, 3e-05, 5e-07, 6.25e-06), "gpt-5.6-sol": (5e-06, 3e-05, 5e-07, 6.25e-06), "gpt-5.6-terra": (2.5e-06, 1.5e-05, 2.5e-07, 3.125e-06), @@ -27,7 +34,7 @@ def test_openai_gpt_5_6_model_info(model): assert info["litellm_provider"] == "openai" assert info["mode"] == "chat" - input_cost, output_cost, cache_read_cost, cache_write_cost = STANDARD_PRICING[model] + input_cost, output_cost, cache_read_cost, cache_write_cost = OPENAI_STANDARD_PRICING[model] assert info["input_cost_per_token"] == input_cost assert info["output_cost_per_token"] == output_cost assert info["cache_read_input_token_cost"] == cache_read_cost @@ -95,7 +102,7 @@ def test_azure_gpt_5_6_global_model_info(model): assert info["litellm_provider"] == "azure" assert info["mode"] == "chat" - input_cost, output_cost, cache_read_cost, _ = STANDARD_PRICING[_tier_key(model)] + input_cost, output_cost, cache_read_cost, _ = AZURE_STANDARD_PRICING[_tier_key(model)] assert info["input_cost_per_token"] == input_cost assert info["output_cost_per_token"] == output_cost assert info["cache_read_input_token_cost"] == cache_read_cost @@ -124,7 +131,7 @@ def test_azure_gpt_5_6_regional_model_info(model): assert info["litellm_provider"] == "azure" assert info["mode"] == "chat" - input_cost, output_cost, cache_read_cost, _ = STANDARD_PRICING[_tier_key(model)] + input_cost, output_cost, cache_read_cost, _ = AZURE_STANDARD_PRICING[_tier_key(model)] assert info["input_cost_per_token"] == pytest.approx(input_cost * 1.1) assert info["output_cost_per_token"] == pytest.approx(output_cost * 1.1)