Last refreshed 2026-06-13. Next refresh: weekly.
Why use GPT-5.4 on OpenAI API?
OpenAI API offers GPT-5.4 with pay-as-you-go pricing at $2.50/1M input tokens. OpenAI is a leading AI research and deployment company dedicated to developing safe and beneficial artificial general intelligence (AGI) for humanity.
Compare GPT-5.4 across 4 providers to find the best fit for your use caseInput / 1M
$2.50
Output / 1M
$15.00
Cache
read $0.25
Batch
-50% · in $1.25 / out $7.50
Setup recipe
Python + curlInstall
pip install openaiAuth
export OPENAI_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY from env
response = client.chat.completions.create(Model ID
gpt-5.4Request example
import os
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
model="gpt-5.4",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use the model slug directly, e.g. "gpt-4o" or "gpt-4.1-mini".
- The examples expect OPENAI_API_KEY; rename it only if your application config maps the new variable.
Compare GPT-5.4 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenAI API | $2.50 | $15.00 |
| OpenRouter | $2.50 | $15.00 |
| Vercel AI Gateway | $2.50 | $15.00 |
| AWS Bedrock | $2.75 | $16.50 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $2.50 |
| Output tokens | $15.00 |
Capabilities
VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt CachingBatch API
About GPT-5.4
GPT-5.4 is OpenAI's flagship frontier reasoning model, released March 5, 2026. It incorporates advances from GPT-5.3-Codex for coding and agentic workflows, and adds 'Thinking' mode with editable reasoning plans. Key capabilities include computer use (navigating interfaces via Playwright), image understanding and generation integration, full-stack web app generation, tool calling, and deep research. Knowledge cutoff is August 31, 2025. Model ID: gpt-5.4.
Get Started
Model Specs
Released2026-03-05
Context1.05m
ArchitectureDecoder Only
Knowledge cutoff2025-08