OpenAI: o3 Mini

o3 Mini is OpenAI's compact reasoning model, released 2025-01, built for cost-efficient STEM work in science, mathematics, and coding. It offers adjustable reasoning effort levels and supports function calling and structured outputs. With medium effort it matches the larger o1 on AIME and GPQA while reducing major errors by 39%.

Modalities
inTextinFileoutText
Price / 1M−70%
$0.33 / $1.32$1.10 / $4.40
Context
200K
Knowledge cutoff
2023-10-31

Capabilities

ReasoningTool useLong contextPrompt cachingStructured output

Channels

Same weights on every channel. Requests route to the cheapest healthy one; the channel used is printed on each billing line.

Provider
Discount
Input /M
Output /M
Cache Read /M
Cache Create 5m /M
Cache Create 1h /M
Codexcheap
−70%
$0.33
$1.32
$0.17
Defaultstable
−30%
$0.77
$3.08
$0.39

Cost Calculator

Pick a channel and a usage scenario, then drag to your workload — each scenario assumes a different prompt-cache hit rate.

Channel
Scenario
Unit $0.33 / $1.32 /1MDaily chat: 40% cache hit assumed · cache read $0.17 /1M
List price $295.68On MirAPI$88.70/ moYou save $206.98Create an API key

Showcase

Three fixed prompts, identical for every chat model. Outputs are archived verbatim — copy the prompt to reproduce.

Task prompt · identical for all models
Build a single-file HTML page using three.js from a CDN: a low-poly planet with a tilted ring of ~200 orbiting particles, a soft key light plus rim light, slow auto-rotation, and drag-to-orbit controls. No build tools — one file only.
Archived output
Archive not published yet

Every model will run this exact prompt; the output lands here verbatim, with tokens and per-run cost.

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="openai/o3-mini",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire o3 Mini into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free