o3
OpenAI · released Apr 16, 2025
- Type
- Closed
- Input
- $2.00
- Output
- $8.00
- Cached
- $0.50
List price · per 1M tokens · OpenAI at 200K context · machine-readable source ↗
Our take
Written Sep 30, 2026o3 is a hosted-only model with no download, so using it means picking a host. It is strong on set-piece competitive programming and takes long documents in one request, but the human preference boards place it mid-field.
Reach for it on set-piece competitive programming problems, where it scores 84.7% on LiveCodeBench High, or on long-document work where the 200,000-token request capacity means you need not split files first. It also takes images and files alongside the text. Skip it if you need fixes landed in an existing codebase without review, or if you need a model you can run yourself.
The case for it
- 84.7% pass on LiveCodeBench High, which covers set-piece algorithmic exercises rather than fixing issues in an existing project.
- A 200,000-token request capacity means long documents need not be split up first, though reliable recall across all of it is unverified in our data.
- Text, image and file input with written output, so a screenshot or document does not have to be described in words first.
The case against it
- Mid-field on the human preference boards: 70th of 168 on Arena Text (overall) as of 25 Sep 2026, and 84th of 168 on Arena Creative Writing as of 25 Sep 2026 — these record which answer people preferred, not whether it was correct.
- 58.4% of real GitHub issues resolved end-to-end on SWE-bench Verified via mini-SWE-agent, 24th of 42 as of 19 Feb 2026 — a result for the model inside that scaffold, not on its own.
- We list no download for it, so using it means choosing a host, and both listed hosts charge the same rate.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)70th of 168 · 1432
CodingWriting and fixing code on its own
Arena Coding83rd of 168 · 1460
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 24th of 42 with 58.4.
WritingDrafting and rewriting prose
Arena Creative Writing84th of 168 · 1383
Arena Creative Writing is the only board that has scored it for this.
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.
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.
Where to rent it
Prices checked between 59 min and 1 hour ago — each listing carries its own date.
OpenAI, direct
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts OpenAI on 200K of context.
- per 1M tokens
- $2.00 in / $8.00 out
- Context served
- 200K
- Throughput
- ~71 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.00 / $8.00checked 1 hour ago | 200K | not measured | Unknown | Unknown | Unknown |
| OpenAIDirect | $2.00 / $8.00checked 59 min ago | 200K100K max reply | 71 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
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
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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 does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
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
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- openai-o3