Models / OpenAI/ o4 Mini

o4 Mini

OpenAI · released Apr 16, 2025

Input: text, images and documents. Output: text.InputOutput
Type
Proprietary
Input
$1.10
Output
$4.40
Cached
$0.28

List price · per 1M tokens · OpenAI at 200K context · source ↗

Our take

Written Aug 3, 2026

o4 Mini is a small reasoning-focused model from OpenAI that handles text, images and files in requests of up to 200,000 tokens. It scores well on live coding and math leaderboards, though its results can vary noticeably between runs and it is weaker on creative writing tasks.

Who should pick it

Pick this for coding tasks where its live leaderboard scores are strong, or for math-heavy workflows and long-context work up to 200,000 tokens. Use it when you want OpenAI-native throughput rather than shopping across providers. Skip it if you need creative writing quality to match its coding level, if you want price competition between hosts, or if you need to run the model locally or audit its weights.

The case for it

  • Strong coding performance on live leaderboards, with Arena Coding Elo 1432.4818 and LiveCodeBench reaching 84.5%.
  • Competitive math reasoning, scoring Arena Maths Elo 1415.565.
  • 200,000-token request limit, large enough for substantial documents or codebases.

The case against it

  • Inconsistent coding benchmark results: a 7.1 point gap between its best and repeat LiveCodeBench runs, with the lower score appearing twice.
  • Creative writing lags its other arena categories by 94.5 points — a clear weak spot.
  • No price competition: both tracked offers are identical, so there is no host shopping for a better rate.
00

How good is it?

IntelligencePuzzles, maths, exam questions

2.5 of 5

Arena Text (overall)83rd of 143 · 1390

Arena Hard Prompts 85th of 143Arena Maths 64th of 139

CodingWriting and fixing code on its own

2.5 of 5

Arena Coding86th of 143 · 1432.5

LiveCodeBench 3rd of 14 via Medium

AgenticPlanning, calling tools, staying on task

Scored, not ratedSWE-bench Verified · 25th of 39 · 45via mini-SWE-agent

o4 Mini is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 25th of 39 with 45.

WritingWe do not rate this

Scored, not ratedThe placings are on the right.

Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where o4 Mini placed and give it no mark out of five.

Arena Creative Writing 85th of 143 · 1337.9
Also scored, on boards we give no mark for
Arena Instruction Following 87th of 143

These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.

Every published score for this model8 scoresEvery figure we hold, from 8 boards, with who ran it and a link to the source — including the boards no rating above is built on.
84.5via Mediumindependentsource ↗
1432.5independentsource ↗
1405.6independentsource ↗
1415.6independentsource ↗
45via mini-SWE-agentindependentsource ↗
01

Or rent it from someone else

Cheapest published offer

Why this differs from the header. The strip above quotes OpenAI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.

per 1M tokens
$1.10 in / $4.40 out
Context served
200K
Throughput
Not measured
Current provider offers with price, context and prompt-privacy answers
ProviderIn / out per 1M tokensContextThroughputTrains on promptsLogs promptsZero retention
OpenRouter$1.10 / $4.40200Knot measuredUnknownUnknownUnknown
OpenAI$1.10 / $4.40200K100K out97 tok/sNoYesunknown periodUnknown

Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.

What each host's API supports

From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.

Supported
Not supported
Not published
host gave no parameter list
API features per host
ProviderTool callingJSON outputStrict schema
OpenRouter
OpenAI

Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.

02

Models people weigh against o4 Mini

Other sizes and versionso3 Mini
Succeedso3 Mini

Compare them field by field →

03

When we formed this view

Dates behind this page

Aug 3, 2026BenchmarkScored 84.5 via Medium on LiveCodeBenchleaderboard
Aug 2, 2026BenchmarkScored 1432.5 on Arena Codingleaderboard
Aug 2, 2026BenchmarkScored 1337.9 on Arena Creative Writingleaderboard
Aug 2, 2026BenchmarkScored 1405.6 on Arena Hard Promptsleaderboard
Aug 2, 2026BenchmarkScored 1368.6 on Arena Instruction Followingleaderboard
Aug 2, 2026BenchmarkScored 1415.6 on Arena Mathsleaderboard
Aug 2, 2026BenchmarkScored 1390 on Arena Text (overall)leaderboard
Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Jul 26, 2025BenchmarkScored 45 via mini-SWE-agent on SWE-bench Verifiedleaderboard
Apr 16, 2025Announcedo4 Mini announced by OpenAI

Prices last checked 9d ago

What we do not know about this model yet

  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
  • 1 of 2 listings do not say whether they train on prompts.
04

Licence and identifiers

What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.

Licence

Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.

Identifiers

Modality record
text+image+file->text
Catalogue slug
openai-o4-mini

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us