o3 Mini
OpenAI · released Jan 31, 2025
- Type
- Proprietary
- Input
- $1.10
- Output
- $4.40
- Cached
- $0.55
List price · per 1M tokens · OpenAI at 200K context · source ↗
Our take
Written Aug 3, 2026o3 Mini is a compact reasoning model from OpenAI that handles text and file inputs up to 200,000 tokens. It is a coding and maths specialist with strong arena ratings in those areas, though its creative writing score lags well behind.
Pick this for coding tasks where its highest arena rating is sufficient and you want OpenAI-hosted throughput, or for long-context document analysis within the OpenAI ecosystem. Use it if you need reasoning capability below flagship pricing with consistent rates across both tracked providers. Skip it if you need open weights, if creative writing quality matters as much as coding, or if you want to self-host rather than use a hosted-only model.
The case for it
- Highest arena coding rating of its six category scores, at 1415.9 Elo.
- 200,000-token request limit, large for its price tier.
- Identical pricing across both tracked providers, so there is no arbitrage hunt.
The case against it
- LiveCodeBench scores swing by 7.1 percentage points across three runs in two days, so the best figure may not be representative.
- Creative writing arena score is 114.8 points below its coding score, a notable gap within the same model.
- Throughput is only verified for OpenAI direct; the second provider does not disclose it.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)101st of 143 · 1347.8
CodingWriting and fixing code on its own
Arena Coding95th of 143 · 1415.9
AgenticPlanning, calling tools, staying on task
o3 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 26th of 39 with 42.4.
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 o3 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 | 84 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 o3 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+file->text
- Catalogue slug
- openai-o3-mini