OpenAI

OpenAI: GPT-4o

stable

GPT-4o is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

gpt-4ogpt-4released May 13, 2024
ProviderQuick start
Context
128K
tokens
Max output
16.4K
tokens
Input
$2.50
per 1M
Output
$10.00
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
Azure OpenAI
Azure OpenAI
128K$2.50$10.00
OpenAI
OpenAI
128K$2.50$10.00
OpenRouter
OpenRouter
128K$2.50$10.00

Pricing

ItemPriceUnit
Input$2.50per 1M tokens
Output$10.00per 1M tokens
Cache read$1.25per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
gpt-4o
Family
gpt-4
Status
stable
Knowledge
-
Released
May 13, 2024
Gateway Config
API
2024-01-01
Auth
OPENAI_API_KEY
Discovery
static
Provider type
static

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@openai/gpt-4o",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.openai.com/v1
Chat completions
https://api.openai.com/v1/chat/completions
Model
gpt-4o
Auth env
OPENAI_API_KEY

GPT-4o FAQ

How much does the GPT-4o API cost?

Through OpenAI, GPT-4o costs $2.50 per 1M input tokens and $10.00 per 1M output tokens.

What is the context window of GPT-4o?

GPT-4o accepts up to 128K tokens of context and returns up to 16.4K output tokens on OpenAI.

Which providers offer GPT-4o?

GPT-4o is available from Azure OpenAI, OpenAI and OpenRouter. Everstack can route between them with automatic fallback when one is unavailable.

What can GPT-4o do?

GPT-4o supports chat, function calling and image input. It accepts text, image and PDF input.

How do I call GPT-4o through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @openai/gpt-4o. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.