OpenAI o4-mini Model

OpenAI retired o4-mini from its API on October 23, 2026. This record preserves historical model details; the former API identity is unavailable, and OpenAI recommends GPT-5.6 Terra as a migration target.

OpenAI recommended migration target
A different model requiring its own input, output, price and behavior checks.

Platform: Replicate

Reasoning ModelMultimodal AITool IntegrationConversational Agent

4.3k runs

Retired direct OpenAI API model; historical prices are not established by the reviewed sources. Previous aggregator quotes are unverified.

Commercial

🚀Function Overview

o4-mini is a historical model retired from OpenAI’s API on October 23, 2026. A migration suggestion is not an automatic runtime replacement.

Key Features

OpenAI shutdown date: October 23, 2026; exact alias/snapshot scope in the official deprecations table.
Historical specifications and sample syntax below do not prove current endpoint or gateway access.
Examples are historical illustrations; GetLLMs did not execute requests or verify historical sample outputs.
Optimized for math, code, and visual reasoning
Agentic tool use (browsing, Python, image generation)
Improved instruction following and conversational abilities
Low-latency performance for high-throughput tasks
Historical hardware and aggregator prices have not been verified against an archived provider contract; no current direct OpenAI price is implied.

Use Cases

•Real-time assistant applications
•Structured reasoning with tool use (web/Python)
•Document analysis and visual interpretation
•High-throughput workflows with tight latency requirements

⚙️Input Parameters

prompt

string

The prompt to send to the model. Do not use if using messages.

system_prompt

string

System prompt to set the assistant's behavior

image_input

array

List of images to send to the model

reasoning_effort

string

Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

max_completion_tokens

integer

Maximum number of completion tokens to generate

💡Usage Examples

Example 1

Input Parameters

{
  "prompt": "What is the theme of the Iliad?",
  "system_prompt": "You only speak in mathematical terms.",
  "reasoning_effort": "high",
  "max_completion_tokens": 4096
}

Output Results

Let us encode the main theme in purely mathematical terms. 1. Basic objects • Let t ∈ [0,T] be “narrative time.” • Let R(t) ∈ ℝ₊ be Achilles’ wrath‐intensity at time t. • Let D(t) ∈ ℝ₊ be the cumulative death‐count (“destruction”) up to time t. • Let H(t) ∈ ℝ₊ be Achilles’ honor (kleos) at time t. • Let F be a fixed vector of “fate‐parameters” determined by the gods (constant w.r.t. t). 2. Governing relations (i) dD/dt = α·R(t) + β·G(t) – here G(t) models discrete divine interventions; α,β>0. (ii) dH/dt = γ·R(t) – δ·D(t) – honor rises with wrath but is eroded by mounting destruction; γ,δ>0. (iii) R(0)=R₀>0, H(0)=H₀≥0, D(0)=0, F fixed. 3. Central result (thematic “theorem”) Under these conditions the solution satisfies ∂D/∂R > 0 for all t>0, i.e. D(t) is a strictly increasing function of R(t). 4. Interpretation The epic thus examines the map R(·) ↦ D(·) under the boundary/fate constraints F. Its “theme” is exactly that Achilles’ wrath R inexorably drives up the human cost D, despite any gains in honor H, all within a framework of immutable divine fate F.

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: Not specified
Run Count: 4.3k
Commercial Use: Supported
Pricing: Retired direct OpenAI API model; historical prices are not established by the reviewed sources. Previous aggregator quotes are unverified.
Platform: Replicate

OpenAI o4-mini Model

🚀Function Overview

Key Features

Use Cases

⚙️Input Parameters

prompt

system_prompt

image_input

reasoning_effort

max_completion_tokens

💡Usage Examples

Example 1

Input Parameters

Output Results

Quick Actions

Technical Specifications

Sources

Related Keywords

Related Models