o3-mini

Name: o3-mini
Brand: OpenAI
SKU: o3-mini
Price: 1.32 USD
Availability: InStock

Text & chatDeprecatedAvailable

by OpenAIo3-mini

OpenAI's reasoning model optimized for STEM tasks, coding, and math. Uses chain-of-thought reasoning.

Try it Get API key Compare

Price · 1M in / out: $1.32 / $5.28
Context: 200,000 tokens
Max. output: 100,000 tokens
Input → output: Text → Text
Developer: OpenAI
Updated: September 23, 2026

The provider is phasing this model out.

Playground

Try o3-mini

Chat

$1.32/1M in

Send a message. The answer arrives in full once the model is done (no streaming).

System prompt

Max. answer length (tokens)

⌘/Ctrl + Enter

This run

at most $0.0055 · 0.55 credits reserved

Billed by the tokens actually used; the unused part of the reservation is refunded.

New here?

10 free credits ($0.10) when you sign up with Google

Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits. Enough for 18 runs of this model.

About o3-mini

TL;DRAs of September 23, 2026

o3-mini is a model by OpenAI in the Text & chat category. On Railwail, o3-mini costs $1.32 per 1M input tokens and $5.28 per 1M output tokens. The context window holds 200,000 tokens, and one response can be up to 100,000 tokens long.

Background

About OpenAI

Founded 2015 · San Francisco, USA

OpenAI was founded in 2015 as a non-profit lab by Sam Altman, Elon Musk, Greg Brockman, Ilya Sutskever, Wojciech Zaremba and John Schulman, transitioning to a capped-profit structure in 2019 to raise capital from Microsoft (now over $13B invested). OpenAI's research output includes the GPT series (GPT-1 in 2018 through GPT-4 in 2023), the InstructGPT/RLHF paper (2022), the GPT-4o System Card (2024) and the o-series reasoning papers. The o-series began with o1-preview in September 2024 and o1 in December 2024, introducing test-time compute scaling via long internal chains-of-thought trained with reinforcement learning. o3 and o3-mini followed in January-February 2025, with o3-mini specifically launched on 31 January 2025 as a fast, cost-efficient reasoning model available to free, Plus and Team ChatGPT users. The o-series has been described by OpenAI as the first models to solve previously-unsolved Frontier Math benchmark problems. Sam Altman remains CEO and the company's 2025 valuation exceeded $300 billion.

Visit OpenAI

Architecture

Decoder-only Transformer (reasoning model with test-time chain-of-thought)

o3-mini is the small reasoning model in the o-series, released by OpenAI on 31 January 2025. Like its o1 and o3 siblings it is a decoder-only Transformer trained to produce long internal chains-of-thought during inference, then return a concise final answer to the user. Reinforcement learning was the core training technique: the model is rewarded for correct answers on verifiable tasks (math, code, scientific problems) and learns to allocate test-time compute by generating longer or shorter reasoning traces as needed. o3-mini supports three reasoning effort settings ('low', 'medium', 'high') that developers can choose to trade latency for accuracy. The training corpus and base pretraining are not disclosed in detail but build on OpenAI's frontier pretraining stack. o3-mini is the first o-series model to support function calling, Structured Outputs with strict JSON schemas, streaming and developer messages from day one, making it deployable in production agentic stacks. On benchmarks the medium-effort setting matched o1's performance at significantly lower cost; the high-effort setting outperformed o1 on AIME math, GPQA Diamond and Codeforces. Vision input is not supported (use o1 or GPT-4o for multimodal). The model retains OpenAI's deliberative alignment training, in which the safety policy itself is reasoned about explicitly during inference.

Parameters: Undisclosed (estimated tens of billions of active parameters)
Context: 200,000 tokens

Capabilities

Three reasoning effort modes: low, medium, high
Strong math performance: o3-mini-high matches or beats o1 on AIME and GPQA
Competitive Codeforces ratings on coding contests
200K context window with 100K max output
Function calling and parallel tool calls
Structured Outputs with strict JSON schemas
Streaming and developer-message support
Lower latency than o1 at equal accuracy
Available in ChatGPT Free, Plus, Team and API
Deliberative alignment: reasons about safety policy at inference time
Best for: math, coding contests, scientific reasoning, multi-step tool agents.

Training & license

Pretrained on OpenAI's standard multi-trillion-token corpus (composition undisclosed). Post-training relies heavily on reinforcement learning against verifiable rewards on math, code and scientific problem datasets, plus deliberative alignment training where the model is taught to reason about OpenAI's safety policy.

License: Proprietary commercial license via OpenAI API, Azure OpenAI Service and ChatGPT. Commercial use permitted.

Safety testing: Evaluated under OpenAI's Preparedness Framework. Deliberative alignment training reduces compliance with jailbreaks; external red-teamers covered persuasion, cyber and CBRN risks.

Known limitations

No vision or audio input
Long internal chains-of-thought add latency at high effort
Hidden reasoning tokens count against pricing
Knowledge cutoff October 2023 from base pretraining
Not always cheaper than GPT-4o for short answer tasks

Research papers

Pricing

Prices in US dollars. Usage is charged from prepaid credits.

Input	$1.32 / 1M tokens
Output	$5.28 / 1M tokens

Billed by the tokens each request actually uses.
1 credit = $0.01

Cost calculator

Price calculator

Input tokens

/ req.

Output tokens

/ req.

Requests

Total

$0.40

40 credits

Per request

$0.004 · 0.4 credits

Each request is rounded up to 0.01 credits.

API

Call o3-mini with your Railwail API key. Use this model ID in the request:

o3-miniAPI documentation Get an API key

curl https://railwail.com/api/v1/chat/completions \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "o3-mini",
    "messages": [
      {
        "role": "user",
        "content": "Explain what a vector database is in two sentences."
      }
    ],
    "max_tokens": 1024
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RAILWAIL_API_KEY"],
    base_url="https://railwail.com/api/v1",
)

completion = client.chat.completions.create(
    model="o3-mini",
    messages=[
        {
            "role": "user",
            "content": "Explain what a vector database is in two sentences.",
        },
    ],
    max_tokens=1024,
)

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

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RAILWAIL_API_KEY,
  baseURL: "https://railwail.com/api/v1",
});

const completion = await client.chat.completions.create({
  model: "o3-mini",
  messages: [
    {
      role: "user",
      content: "Explain what a vector database is in two sentences."
    }
  ],
  max_tokens: 1024
});

console.log(completion.choices[0].message.content);

// npm install railwail
import railwail from "railwail";

const rw = railwail(process.env.RAILWAIL_API_KEY);

const res = await rw.chat("o3-mini", [
  { role: "user", content: "Explain what a vector database is in two sentences." },
], { max_tokens: 1024 });

console.log(res.choices[0].message.content);

Set your key as RAILWAIL_API_KEYCreate API key

Specifications

Model ID: o3-mini
Developer: OpenAI
Category: Text & chat
Input: Text
Output: Text
Context window: 200,000 tokens
Max. output: 100,000 tokens
Billing: By usage (tokens or GPU time)
Lifecycle: Deprecated
Model size: Undisclosed (estimated tens of billions of active parameters)
License: Proprietary commercial license via OpenAI API, Azure OpenAI Service and ChatGPT. Commercial use permitted.
Catalog entry updated: September 23, 2026

Example prompts

Examples from the Railwail catalog. They were not generated live on this page.

Math Problem
Prove that the square root of 2 is irrational
Show example answer
Assume for contradiction that sqrt(2) is rational, meaning sqrt(2) = p/q where p and q are integers with no common factors. Squaring both sides gives 2 = p²/q², so p² = 2q². This means p² is even, which implies p is even—write p = 2k. Substituting gives 4k² = 2q², so q² = 2k², meaning q is also even. But if both p and q are even, they share a common factor of 2, contradicting our assumption. Therefore sqrt(2) must be irrational.
Logic Puzzle
Three boxes are labeled 'Apples', 'Oranges', and 'Mixed'. All labels are wrong. You can pick one fruit from one box. How do you determine the correct labels?
Show example answer
Pick a fruit from the box labeled 'Mixed'. Since all labels are wrong, this box contains only one type of fruit—either all apples or all oranges. Say you draw an apple: the 'Mixed' box is actually the Apples box. Now consider the remaining two boxes labeled 'Apples' and 'Oranges'. The box labeled 'Apples' cannot be apples (wrong label) and cannot be mixed (we found that), so it must be Oranges. The box labeled 'Oranges' is therefore the Mixed box. One draw is all you need.

Use cases

What it is used for

Math olympiad and STEM problem solving
Competitive programming assistants
Scientific paper review
Backend reasoning step in agent stacks
Code review and bug hunting
Logic and rule-based systems

Related guides

Best Large Language Models

All models in Text & chat

Frequently asked questions

What is o3-mini?

o3-mini is a model by OpenAI in the Text & chat category. On Railwail you can call it with an API key through the Railwail API.

How much does o3-mini cost on Railwail?

On Railwail, o3-mini costs $1.32 per 1M input tokens and $5.28 per 1M output tokens. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals $0.01.

What is the context window of o3-mini?

The context window of o3-mini holds 200,000 tokens. One response can be up to 100,000 tokens long.

How fast is o3-mini?

There are not enough measured runs of o3-mini on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is o3-mini better than Claude Fable 5.1?

That depends on the task. o3-mini (OpenAI) and Claude Fable 5.1 (Anthropic) are both models in the Text & chat category. The comparison page shows their prices and specifications side by side.

Compare o3-mini and Claude Fable 5.1

How do I use o3-mini through the API?

Create a Railwail API key and send your request with the model ID o3-mini. Code examples for curl, Python and JavaScript are in the API section of this page.

Comparable models

All in this category

Claude Fable 5.1Anthropic
Anthropic's model for the most demanding reasoning and long-horizon agentic work. 1M-token context window, up to 128K output tokens, adaptive thinking that is always on.
$12.00/1M in
809 % more expensive per unit
Compare o3-mini vs. Claude Fable 5.1
Claude Opus 4.8Anthropic
The most capable model of Anthropic's Opus 4 series. State of the art on long-horizon agentic work, coding and knowledge tasks, with a 1M-token context window at standard pricing.
$6.00/1M in
355 % more expensive per unit
Compare o3-mini vs. Claude Opus 4.8
Claude Opus 5.5Anthropic
Anthropic's current Opus model for long-running agentic coding and knowledge work. 1M-token context window, up to 128K output tokens, adaptive thinking that is always on.
$4.80/1M in
264 % more expensive per unit
Compare o3-mini vs. Claude Opus 5.5

Use o3-mini via the API

One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.

Get API key Browse all models