OpenAI (Text Completion)

LiteLLM supports OpenAI text completion models

note

OpenAI's model pages list the legacy Completions endpoint as not supported for current models. gpt-5.4, gpt-5.4-mini and gpt-5.4-nano still answer there as of October 2026, while gpt-5.5 and later answer 404. These are chat models, so the endpoint continues your prompt as plain text instead of replying to it, and the text can include the model's internal formatting tokens. LiteLLM does not track spend on this route yet. For chat-style answers and spend tracking, use the openai/ prefix, which also serves /completions requests.

Required API Keys

import os 
os.environ["OPENAI_API_KEY"] = "your-api-key"

Usage

import os 
from litellm import completion

os.environ["OPENAI_API_KEY"] = "your-api-key"

# openai call
response = completion(
    model = "text-completion-openai/gpt-5.4-mini", 
    messages=[{ "content": "Hello, how are you?","role": "user"}]
)

Usage - LiteLLM Proxy Server

Here's how to call OpenAI models with the LiteLLM Proxy Server

1. Save key in your environment

export OPENAI_API_KEY=""

2. Start the proxy

config.yaml
config.yaml - proxy all OpenAI models
CLI

model_list:
  - model_name: gpt-6-luna
    litellm_params:
      model: openai/gpt-6-luna                          # The `openai/` prefix will call openai.chat.completions.create
      api_key: os.environ/OPENAI_API_KEY
  - model_name: gpt-5.4-mini-completions
    litellm_params:
      model: text-completion-openai/gpt-5.4-mini # The `text-completion-openai/` prefix will call openai.completions.create
      api_key: os.environ/OPENAI_API_KEY

Use this to add all openai models with one API Key. WARNING: This will not do any load balancing This means requests to gpt-6.1-sol, gpt-6-luna will all go through this route

model_list:
  - model_name: "*"             # all requests where model not in your config go to this deployment
    litellm_params:
      model: openai/*           # set `openai/` to use the openai route
      api_key: os.environ/OPENAI_API_KEY

$ litellm --model text-completion-openai/gpt-5.4-mini

# Server running on http://0.0.0.0:4000

3. Test it

Curl Request
OpenAI v1.0.0+
Langchain

curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
      "model": "gpt-5.4-mini-completions",
      "messages": [
        {
          "role": "user",
          "content": "what llm are you"
        }
      ]
    }
'

import openai
client = openai.OpenAI(
    api_key="anything",
    base_url="http://0.0.0.0:4000"
)

# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="gpt-5.4-mini-completions", messages = [
    {
        "role": "user",
        "content": "this is a test request, write a short poem"
    }
])

print(response)

from langchain_openai import OpenAI

llm = OpenAI(
    base_url="http://0.0.0.0:4000", # set base_url to the LiteLLM Proxy
    api_key="anything",
    model="gpt-5.4-mini-completions",
    temperature=0.1
)

response = llm.invoke("test from litellm. tell me why it's amazing in 1 sentence")

print(response)