diff --git a/docs/my-website/blog/gpt_5_4/index.md b/docs/my-website/blog/gpt_5_4/index.md new file mode 100644 index 00000000000..b4e68096c04 --- /dev/null +++ b/docs/my-website/blog/gpt_5_4/index.md @@ -0,0 +1,96 @@ +--- +slug: gpt_5_4 +title: "GPT-5.4 Model Support" +date: 2026-03-05T10:00:00 +authors: + - name: Sameer Kankute + title: SWE @ LiteLLM (LLM Translation) + url: https://www.linkedin.com/in/sameer-kankute/ + image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg + - name: Krrish Dholakia + title: "CEO, LiteLLM" + url: https://www.linkedin.com/in/krish-d/ + image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg + - name: Ishaan Jaff + title: "CTO, LiteLLM" + url: https://www.linkedin.com/in/reffajnaahsi/ + image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg +description: "GPT-5.4 model support in LiteLLM" +tags: [openai, gpt-5.4, completion] +hide_table_of_contents: false +--- + +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +LiteLLM now supports fully GPT-5.4! + +## Docker Image + +```bash +docker pull ghcr.io/berriai/litellm:v1.81.14-stable.gpt-4o +``` + +## Usage + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: gpt-5.4 + litellm_params: + model: openai/gpt-5.4 + api_key: os.environ/OPENAI_API_KEY +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e OPENAI_API_KEY=$OPENAI_API_KEY \ + -v $(pwd)/config.yaml:/app/config.yaml \ + ghcr.io/berriai/litellm:v1.81.14-stable.gpt-4o \ + --config /app/config.yaml +``` + +**3. Test it** + +```bash +curl -X POST "http://0.0.0.0:4000/chat/completions" \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $LITELLM_KEY" \ + -d '{ + "model": "gpt-5.4", + "messages": [ + {"role": "user", "content": "Write a Python function to check if a number is prime."} + ] + }' +``` + + + + +```python +from litellm import completion + +response = completion( + model="openai/gpt-5.4", + messages=[ + {"role": "user", "content": "Write a Python function to check if a number is prime."} + ], +) + +print(response.choices[0].message.content) +``` + + + + +## Notes + +- Use `/responses` for better model performance. +- GPT-5.4 supports reasoning, function calling, vision, and tool-use — see the [OpenAI provider docs](../../docs/providers/openai) for advanced usage. diff --git a/litellm/llms/azure/chat/gpt_5_transformation.py b/litellm/llms/azure/chat/gpt_5_transformation.py index eeb55911ecf..a70e008d66b 100644 --- a/litellm/llms/azure/chat/gpt_5_transformation.py +++ b/litellm/llms/azure/chat/gpt_5_transformation.py @@ -28,8 +28,8 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config): def get_supported_openai_params(self, model: str) -> List[str]: """Get supported parameters for Azure OpenAI GPT-5 models. - Azure OpenAI GPT-5.2 models support logprobs, unlike OpenAI's GPT-5. - This overrides the parent class to add logprobs support back for gpt-5.2. + Azure OpenAI GPT-5.2/5.4 models support logprobs, unlike OpenAI's GPT-5. + This overrides the parent class to add logprobs support back for gpt-5.2+. Reference: - Tested with Azure OpenAI GPT-5.2 (api-version: 2025-01-01-preview) @@ -43,8 +43,12 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config): if "tool_choice" not in params: params.append("tool_choice") - # Only gpt-5.2 has been verified to support logprobs on Azure - if self.is_model_gpt_5_2_model(model): + # Only gpt-5.2+ has been verified to support logprobs on Azure. + # The base OpenAI class includes logprobs for gpt-5.1+, but Azure + # hasn't verified support for gpt-5.1, so remove them unless gpt-5.2/5.4+. + if self.is_model_gpt_5_1_model(model) and not self.is_model_gpt_5_2_model(model): + params = [p for p in params if p not in ["logprobs", "top_logprobs"]] + elif self.is_model_gpt_5_2_model(model): azure_supported_params = ["logprobs", "top_logprobs"] params.extend(azure_supported_params) @@ -63,7 +67,7 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config): or optional_params.get("reasoning_effort") ) - # gpt-5.1 supports reasoning_effort='none', but other gpt-5 models don't + # gpt-5.1/5.2/5.4 support reasoning_effort='none', but other gpt-5 models don't # See: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning is_gpt_5_1 = self.is_model_gpt_5_1_model(model) @@ -97,7 +101,7 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config): drop_params=drop_params, ) - # Only drop reasoning_effort='none' for non-gpt-5.1 models + # Only drop reasoning_effort='none' for non-gpt-5.1/5.2/5.4 models if result.get("reasoning_effort") == "none" and not is_gpt_5_1: result.pop("reasoning_effort") diff --git a/litellm/llms/openai/chat/gpt_5_transformation.py b/litellm/llms/openai/chat/gpt_5_transformation.py index 05c003c8b7a..23342550e17 100644 --- a/litellm/llms/openai/chat/gpt_5_transformation.py +++ b/litellm/llms/openai/chat/gpt_5_transformation.py @@ -36,16 +36,26 @@ class OpenAIGPT5Config(OpenAIGPTConfig): @classmethod def is_model_gpt_5_1_model(cls, model: str) -> bool: - """Check if the model is a gpt-5.1 or gpt-5.2 chat variant. + """Check if the model is a gpt-5.1, gpt-5.2, or gpt-5.4 chat variant. - gpt-5.1/5.2 support temperature when reasoning_effort="none", + gpt-5.1/5.2/5.4 support temperature when reasoning_effort="none", unlike base gpt-5 which only supports temperature=1. Excludes - pro variants which keep stricter knobs. + pro variants which keep stricter knobs and chat-only variants + which only support temperature=1. """ 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 + is_gpt_5_2 = ( + model_name.startswith("gpt-5.2") + and "pro" not in model_name + and not model_name.startswith("gpt-5.2-chat") + ) + is_gpt_5_4 = ( + model_name.startswith("gpt-5.4") + and "pro" not in model_name + and not model_name.startswith("gpt-5.4-chat") + ) + return is_gpt_5_1 or is_gpt_5_2 or is_gpt_5_4 @classmethod def is_model_gpt_5_2_pro_model(cls, model: str) -> bool: @@ -57,7 +67,7 @@ class OpenAIGPT5Config(OpenAIGPTConfig): def is_model_gpt_5_2_model(cls, model: str) -> bool: """Check if the model is a gpt-5.2 variant (including pro).""" model_name = model.split("/")[-1] - return model_name.startswith("gpt-5.2") + return model_name.startswith("gpt-5.2") or model_name.startswith("gpt-5.4") def get_supported_openai_params(self, model: str) -> list: from litellm.utils import supports_tool_choice @@ -69,14 +79,19 @@ class OpenAIGPT5Config(OpenAIGPTConfig): base_gpt_series_params.remove("tool_choice") non_supported_params = [ - "logprobs", - "top_p", "presence_penalty", "frequency_penalty", - "top_logprobs", "stop", + "logit_bias", + "modalities", + "prediction", + "audio", + "web_search_options", ] + # gpt-5.1/5.2/5.4 support logprobs, top_p, top_logprobs when reasoning_effort="none" + if not self.is_model_gpt_5_1_model(model): + non_supported_params.extend(["logprobs", "top_p", "top_logprobs"]) return [ param for param in base_gpt_series_params @@ -104,7 +119,7 @@ class OpenAIGPT5Config(OpenAIGPTConfig): else: raise litellm.utils.UnsupportedParamsError( message=( - "reasoning_effort='xhigh' is only supported for gpt-5.1-codex-max and gpt-5.2 models." + "reasoning_effort='xhigh' is only supported for gpt-5.1-codex-max, gpt-5.2, and gpt-5.4+ models." ), status_code=400, ) @@ -118,6 +133,25 @@ class OpenAIGPT5Config(OpenAIGPTConfig): "max_tokens" ) + # gpt-5.1/5.2/5.4 support logprobs, top_p, top_logprobs only when reasoning_effort="none" + if self.is_model_gpt_5_1_model(model): + sampling_params = ["logprobs", "top_logprobs", "top_p"] + has_sampling = any(p in non_default_params for p in sampling_params) + if has_sampling and reasoning_effort not in (None, "none"): + if litellm.drop_params or drop_params: + for p in sampling_params: + non_default_params.pop(p, None) + else: + raise litellm.utils.UnsupportedParamsError( + message=( + "gpt-5.1/5.2/5.4 only support logprobs, top_p, top_logprobs when " + "reasoning_effort='none'. Current reasoning_effort='{}'. " + "To drop unsupported params set `litellm.drop_params = True`" + ).format(reasoning_effort), + status_code=400, + ) + + if "temperature" in non_default_params: temperature_value: Optional[float] = non_default_params.pop("temperature") if temperature_value is not None: diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e54eaf89d72..98083676dfc 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -20336,6 +20336,43 @@ "supports_vision": true, "supports_web_search": true }, + "gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_priority": 5e-07, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_priority": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 3e-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-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 e54eaf89d72..98083676dfc 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -20336,6 +20336,43 @@ "supports_vision": true, "supports_web_search": true }, + "gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_priority": 5e-07, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_priority": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 3e-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-pro": { "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06,