OpenAI

GPT-4o API

GPT-4o ("omni") is OpenAI's flagship multimodal model. Strong text reasoning, native vision, fast inference, and excellent structured output / function calling support. The most widely-supported model in the OpenAI SDK ecosystem.

Input
$2.50
/ 1M tokens
Output
$10.00
/ 1M tokens
Context
128K
tokens
Vision
Yes

Top use cases

  • Multimodal apps (image + text input)
  • Function calling and tool use
  • Structured output / JSON mode
  • General-purpose chat and assistants
  • Drop-in replacement for older GPT-4

Use GPT-4o in 30 seconds

ModelServer is OpenAI-compatible. Point your existing OpenAI SDK at modelserver.dev/v1 and set the model name to gpt-4o.

gpt-4o.py
from openai import OpenAI

client = OpenAI(
    api_key="sk-modelserver-...",
    base_url="https://modelserver.dev/v1",
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "user", "content": "Hello, GPT-4o!"}
    ],
)

print(response.choices[0].message.content)

Frequently asked questions

How much does GPT-4o cost?
GPT-4o is priced at $2.50 per 1M input tokens and $10.00 per 1M output tokens via ModelServer. ModelServer adds a flat 5.5% platform fee on top — no markups on individual tokens, no monthly minimum.
What is the GPT-4o context window?
GPT-4o supports a 128K token context window. You can put roughly 96,000 words in a single prompt.
Is GPT-4o OpenAI-compatible via ModelServer?
Yes. Point your OpenAI SDK base_url to https://modelserver.dev/v1 and set model="gpt-4o". Existing OpenAI-SDK code works without modification.
Who is GPT-4o best for?
Apps already built on the OpenAI SDK that need a strong default.
Does GPT-4o support vision input?
Yes. GPT-4o accepts image inputs alongside text. Pass images as base64 or URL in the OpenAI-compatible message format.

Other OpenAI models

GPT-4o API — Pricing & Access — ModelServer