From 70643a8b9c3673f4c8dec363087a12adb412e9b6 Mon Sep 17 00:00:00 2001 From: Peter Dave Hello <3691490+PeterDaveHello@users.noreply.github.com> Date: Fri, 12 Dec 2025 04:49:30 +0800 Subject: [PATCH] Add support for OpenAI GPT-5.2 models (#17836) References: - https://openai.com/index/introducing-gpt-5-2/ - https://platform.openai.com/docs/models/gpt-5.2 --- docs/my-website/docs/providers/openai.md | 5 + .../llms/openai/chat/gpt_5_transformation.py | 23 ++- ...odel_prices_and_context_window_backup.json | 170 ++++++++++++++++++ model_prices_and_context_window.json | 170 ++++++++++++++++++ .../llms/openai/test_gpt5_transformation.py | 37 ++++ 5 files changed, 400 insertions(+), 5 deletions(-) diff --git a/docs/my-website/docs/providers/openai.md b/docs/my-website/docs/providers/openai.md index f1f88999d83..b170c6aba22 100644 --- a/docs/my-website/docs/providers/openai.md +++ b/docs/my-website/docs/providers/openai.md @@ -188,6 +188,11 @@ os.environ["OPENAI_BASE_URL"] = "https://your_host/v1" # OPTIONAL | gpt-5-mini-2025-08-07 | `response = completion(model="gpt-5-mini-2025-08-07", messages=messages)` | | gpt-5-nano-2025-08-07 | `response = completion(model="gpt-5-nano-2025-08-07", messages=messages)` | | gpt-5-pro | `response = completion(model="gpt-5-pro", messages=messages)` | +| gpt-5.2 | `response = completion(model="gpt-5.2", messages=messages)` | +| gpt-5.2-2025-12-11 | `response = completion(model="gpt-5.2-2025-12-11", messages=messages)` | +| gpt-5.2-chat-latest | `response = completion(model="gpt-5.2-chat-latest", messages=messages)` | +| gpt-5.2-pro | `response = completion(model="gpt-5.2-pro", messages=messages)` | +| gpt-5.2-pro-2025-12-11 | `response = completion(model="gpt-5.2-pro-2025-12-11", messages=messages)` | | gpt-5.1 | `response = completion(model="gpt-5.1", messages=messages)` | | gpt-5.1-codex | `response = completion(model="gpt-5.1-codex", messages=messages)` | | gpt-5.1-codex-mini | `response = completion(model="gpt-5.1-codex-mini", messages=messages)` | diff --git a/litellm/llms/openai/chat/gpt_5_transformation.py b/litellm/llms/openai/chat/gpt_5_transformation.py index a6d6b164366..1b3abb20d63 100644 --- a/litellm/llms/openai/chat/gpt_5_transformation.py +++ b/litellm/llms/openai/chat/gpt_5_transformation.py @@ -34,12 +34,22 @@ class OpenAIGPT5Config(OpenAIGPTConfig): @classmethod def is_model_gpt_5_1_model(cls, model: str) -> bool: - """Check if the model is a gpt-5.1 variant. + """Check if the model is a gpt-5.1 or gpt-5.2 chat variant. - gpt-5.1 supports temperature when reasoning_effort="none", - unlike gpt-5 which only supports temperature=1. + gpt-5.1/5.2 support temperature when reasoning_effort="none", + unlike base gpt-5 which only supports temperature=1. Excludes + pro variants which keep stricter knobs. """ - return "gpt-5.1" in model + model_name = model.split("/")[-1] + is_gpt_5_1 = model_name.startswith("gpt-5.1") + is_gpt_5_2 = model_name.startswith("gpt-5.2") and "pro" not in model_name + return is_gpt_5_1 or is_gpt_5_2 + + @classmethod + def is_model_gpt_5_2_pro_model(cls, model: str) -> bool: + """Check if the model is the gpt-5.2-pro snapshot/alias.""" + model_name = model.split("/")[-1] + return model_name.startswith("gpt-5.2-pro") def get_supported_openai_params(self, model: str) -> list: from litellm.utils import supports_tool_choice @@ -77,7 +87,10 @@ class OpenAIGPT5Config(OpenAIGPTConfig): or optional_params.get("reasoning_effort") ) if reasoning_effort is not None and reasoning_effort == "xhigh": - if not self.is_model_gpt_5_1_codex_max_model(model): + if not ( + self.is_model_gpt_5_1_codex_max_model(model) + or self.is_model_gpt_5_2_pro_model(model) + ): if litellm.drop_params or drop_params: non_default_params.pop("reasoning_effort", None) else: diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 03b36f09316..5fd7ff4a0cf 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -16300,6 +16300,176 @@ "supports_tool_choice": false, "supports_vision": true }, + "gpt-5.2": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true + }, + "gpt-5.2-2025-12-11": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true + }, + "gpt-5.2-chat-latest": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5.2-pro": { + "input_cost_per_token": 2.1e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.68e-04, + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gpt-5.2-pro-2025-12-11": { + "input_cost_per_token": 2.1e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.68e-04, + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "gpt-5-pro": { "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 03b36f09316..5fd7ff4a0cf 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -16300,6 +16300,176 @@ "supports_tool_choice": false, "supports_vision": true }, + "gpt-5.2": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true + }, + "gpt-5.2-2025-12-11": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true + }, + "gpt-5.2-chat-latest": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5.2-pro": { + "input_cost_per_token": 2.1e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.68e-04, + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gpt-5.2-pro-2025-12-11": { + "input_cost_per_token": 2.1e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.68e-04, + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "gpt-5-pro": { "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, diff --git a/tests/test_litellm/llms/openai/test_gpt5_transformation.py b/tests/test_litellm/llms/openai/test_gpt5_transformation.py index 8b2c7fa27eb..4cb3132f737 100644 --- a/tests/test_litellm/llms/openai/test_gpt5_transformation.py +++ b/tests/test_litellm/llms/openai/test_gpt5_transformation.py @@ -248,6 +248,10 @@ def test_gpt5_1_model_detection(gpt5_config: OpenAIGPT5Config): assert gpt5_config.is_model_gpt_5_1_model("gpt-5.1-codex") assert gpt5_config.is_model_gpt_5_1_model("gpt-5.1-codex-max") assert gpt5_config.is_model_gpt_5_1_model("gpt-5.1-chat") + assert gpt5_config.is_model_gpt_5_1_model("gpt-5.2") + assert gpt5_config.is_model_gpt_5_1_model("gpt-5.2-2025-12-11") + assert gpt5_config.is_model_gpt_5_1_model("gpt-5.2-chat-latest") + assert not gpt5_config.is_model_gpt_5_1_model("gpt-5.2-pro") assert not gpt5_config.is_model_gpt_5_1_model("gpt-5") assert not gpt5_config.is_model_gpt_5_1_model("gpt-5-mini") assert not gpt5_config.is_model_gpt_5_1_model("gpt-5-codex") @@ -267,6 +271,19 @@ def test_gpt5_1_temperature_with_reasoning_effort_none(config: OpenAIConfig): assert params["reasoning_effort"] == "none" +def test_gpt5_2_temperature_with_reasoning_effort_none(config: OpenAIConfig): + """Test that GPT-5.2 aligns with GPT-5.1 temperature rules when effort='none'.""" + for temp in [0.0, 0.3, 0.7, 1.0, 1.5]: + params = config.map_openai_params( + non_default_params={"temperature": temp, "reasoning_effort": "none"}, + optional_params={}, + model="gpt-5.2", + drop_params=False, + ) + assert params["temperature"] == temp + assert params["reasoning_effort"] == "none" + + def test_gpt5_1_temperature_without_reasoning_effort(config: OpenAIConfig): """Test that GPT-5.1 supports any temperature when reasoning_effort is not specified. @@ -359,3 +376,23 @@ def test_gpt5_temperature_still_restricted(config: OpenAIConfig): drop_params=False, ) assert params["temperature"] == 1.0 + + +def test_gpt5_2_pro_allows_reasoning_effort_xhigh(config: OpenAIConfig): + params = config.map_openai_params( + non_default_params={"reasoning_effort": "xhigh"}, + optional_params={}, + model="gpt-5.2-pro", + drop_params=False, + ) + assert params["reasoning_effort"] == "xhigh" + + +def test_gpt5_2_rejects_reasoning_effort_xhigh_for_base_model(config: OpenAIConfig): + with pytest.raises(litellm.utils.UnsupportedParamsError): + config.map_openai_params( + non_default_params={"reasoning_effort": "xhigh"}, + optional_params={}, + model="gpt-5.2", + drop_params=False, + )