o4 Mini
OpenAI · released Apr 16, 2025
- 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, 2026o4 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.
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.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)83rd of 143 · 1390
CodingWriting and fixing code on its own
Arena Coding86th of 143 · 1432.5
AgenticPlanning, calling tools, staying on task
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
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.
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.
Or rent it from someone else
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
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $1.10 / $4.40 | 200K | not measured | Unknown | Unknown | Unknown |
| OpenAI | $1.10 / $4.40 | 200K100K out | 97 tok/s | No | Yesunknown period | Unknown |
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
| Provider | Tool calling | JSON output | Strict 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.
Models people weigh against o4 Mini
When we formed this view
Dates behind this page
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.
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