GPT: gpt-5.4-pro
gpt-5.4-pro
Version of GPT-5.4 that produces smarter and more precise responses.
text → image → text
Modalities
In / Out Price
40% offfrom$18/ 1M
$30 Official price
from$108/ 1M
$180 Official price
1.05M
Context
Mar 5, 2026
Released
Providers
This model is hosted by one provider. Requests are forwarded to it directly, with no routing decisions to make.
Call this model in three steps.
1
Get your API key
Create a key and set your API key and base URL as environment variables.
Create API KeyEnvironment
export UNIROUTER_API_KEY="<YOUR_API_KEY>"
export UNIROUTER_BASE_URL="https://api.tokatlas.com/v1"2
Choose a request format
Choose the format supported by your selected route.
3
Make your first request
Model ID: gpt-5.4-pro
from openai import OpenAI
client = OpenAI(
base_url="https://api.tokatlas.com/v1",
api_key="<YOUR_API_KEY>",
)
response = client.chat.completions.create(**{
"model": "gpt-5.4-pro",
"messages": [
{
"role": "user",
"content": "Explain quantum entanglement."
}
],
"temperature": 0.7
})
print(response)Endpoint
Creates a model response for the given chat conversation.
- POST
- https://api.tokatlas.com/v1/chat/completions
- Authorization
- Bearer $UNIROUTER_API_KEY
- Content-Type
- application/json