o4 Mini High
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 2, 2026o4 Mini High is a hosted-only reasoning model from OpenAI that handles text, images and files up to 200,000 tokens in a single request. It scores well on coding benchmarks and is priced identically whether you access it directly or through a router, though benchmark coverage beyond coding is thin.
Choose this for coding tasks where LiveCodeBench 87.3 is the relevant quality signal, or for long-document and codebase work that needs up to 200,000 tokens in one go. Use it when OpenAI's measured throughput of about 107 tokens per second meets your latency needs. Skip it if you need verified chat quality scores, general reasoning benchmarks, or transparency about model size and architecture.
The case for it
- Strong measured coding performance at LiveCodeBench 87.3.
- Very large request limit for its price tier: 200,000 tokens.
- Same pricing on direct and router access, with no routing premium.
The case against it
- Throughput data is thin: only one measured figure, and router speed is unverified in our data.
- No published parameter count or architecture details.
- Benchmark coverage is narrow: only one coding score, with no chat Elo, general reasoning, or multimodal scores available.
How good is it?
IntelligencePuzzles, maths, exam questions
Nobody we watch has scored o4 Mini High for this. We would take the rating from Arena Text (overall).
CodingWriting and fixing code on its own
o4 Mini High is not on Arena Coding, which is where the rating would come from, so there is no rating here. It is on LiveCodeBench, in 1st of 14 with 87.3.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored o4 Mini High for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Nobody we watch has scored this model for writing. 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.
Every published score for this model1 scoreEvery figure we hold, from 1 board, 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 | 200K | 125 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 High
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-high