OpenAI: O4 Mini Deep Research

stable

O4 Mini Deep Research is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

o4-mini-deep-researcho-series

Provider Quick start

Context

200K

tokens

Max output

100K

tokens

Input

per 1M

Output

per 1M

Activity

Daily period usage

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

Providers

ProviderContextInput /MOutput /M

OpenAI

200K--

Pricing

No pricing data available.

Performance

Reliability

Compare

Compare usage and performance

Place this model beside up to three other catalog models.

Capabilities

Modalities

Input

Output

Details

Model ID: o4-mini-deep-research
Family: o-series
Status: stable
Knowledge: -
Released: -

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/o4-mini-deep-research",  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

o4-mini-deep-research

Auth env

OPENAI_API_KEY

O4 Mini Deep Research FAQ

What is the context window of O4 Mini Deep Research?

O4 Mini Deep Research accepts up to 200K tokens of context and returns up to 100K output tokens on OpenAI.

What can O4 Mini Deep Research do?

O4 Mini Deep Research supports chat and function calling. It accepts text input.

How do I call O4 Mini Deep Research through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @openai/o4-mini-deep-research. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.