Add day 0 support for gpt-5.4 #22916
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change | ||||||
|---|---|---|---|---|---|---|---|---|
| @@ -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 | ||||||||
| ``` | ||||||||
|
|
||||||||
|
Comment on lines
+31
to
+33
Contributor
There was a problem hiding this comment. Docker image tag references wrong model The Docker image pulled and run in the usage example is tagged
Suggested change
|
||||||||
| ## Usage | ||||||||
|
|
||||||||
| <Tabs> | ||||||||
| <TabItem value="proxy" label="LiteLLM Proxy"> | ||||||||
|
|
||||||||
| **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."} | ||||||||
| ] | ||||||||
| }' | ||||||||
| ``` | ||||||||
|
|
||||||||
| </TabItem> | ||||||||
| <TabItem value="sdk" label="LiteLLM SDK"> | ||||||||
|
|
||||||||
| ```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) | ||||||||
| ``` | ||||||||
|
|
||||||||
| </TabItem> | ||||||||
| </Tabs> | ||||||||
|
|
||||||||
| ## 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. | ||||||||
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -48,11 +48,11 @@ def is_model_gpt_5_1_codex_max_model(cls, model: str) -> bool: | |
|
|
||
| @classmethod | ||
| def is_model_gpt_5_1_model(cls, model: str) -> bool: | ||
| """Check if the model is a gpt-5.1, gpt-5.2, or gpt-5.4 chat variant. | ||
|
|
||
| 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 and chat-only variants | ||
| which only support temperature=1. | ||
| """ | ||
| model_name = model.split("/")[-1] | ||
|
|
@@ -62,7 +62,12 @@ def is_model_gpt_5_1_model(cls, model: str) -> bool: | |
| 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 | ||
|
Comment on lines
+65
to
+70
Contributor
There was a problem hiding this comment. Hardcoded model name violates no-hardcoding rule The custom rule for this repository explicitly prohibits hardcoding model-specific flags directly in transformation code. Instead, capabilities should be read from
The same hardcoded pattern also exists in Context Used: Rule from
Comment on lines
+65
to
+70
Contributor
There was a problem hiding this comment. Hardcoded model-specific flag violates the no-hardcoding rule. Custom rule [2605a1b1] explicitly requires putting model capabilities in If Context Used: Rule from |
||
|
|
||
| @classmethod | ||
| def is_model_gpt_5_2_pro_model(cls, model: str) -> bool: | ||
|
|
@@ -74,7 +79,7 @@ def is_model_gpt_5_2_pro_model(cls, model: str) -> bool: | |
| 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") or model_name.startswith("gpt-5.4") | ||
|
Comment on lines
79
to
+82
Contributor
There was a problem hiding this comment.
The method is named return model_name.startswith("gpt-5.2") or model_name.startswith("gpt-5.4")This is semantically wrong and will be a source of confusion for future contributors who call If
Comment on lines
79
to
+82
Contributor
There was a problem hiding this comment. Method name return model_name.startswith("gpt-5.2") or model_name.startswith("gpt-5.4")This misleads future contributors who expect the method to only match gpt-5.2 variants. Downstream callers in Consider either introducing a separate |
||
|
|
||
| def get_supported_openai_params(self, model: str) -> list: | ||
| if self.is_model_gpt_5_search_model(model): | ||
|
|
@@ -113,7 +118,7 @@ def get_supported_openai_params(self, model: str) -> list: | |
| "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"]) | ||
|
|
||
|
|
@@ -156,7 +161,7 @@ def map_openai_params( | |
| else: | ||
| raise litellm.utils.UnsupportedParamsError( | ||
| message=( | ||
| "reasoning_effort='xhigh' is only supported for gpt-5.1-codex-max, gpt-5.2, and gpt-5.4+ models." | ||
| ), | ||
| status_code=400, | ||
| ) | ||
|
|
@@ -170,7 +175,7 @@ def map_openai_params( | |
| "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) | ||
|
|
@@ -181,7 +186,7 @@ def map_openai_params( | |
| 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), | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Docker image tag references GPT-4o instead of GPT-5.4. The tag
v1.81.14-stable.gpt-4oexplicitly names gpt-4o, which conflicts with this blog post documenting gpt-5.4 support. Update to a release tag that actually contains gpt-5.4 support, or use a generic/latest tag if the appropriate release doesn't exist yet.