GPT-4o-mini (2024-07-18)
OpenAI · released Jul 18, 2024
- Type
- Closed
- Input
- $0.15
- Output
- $0.60
- Cached
- $0.075
List price · per 1M tokens · OpenAI at 128K context · machine-readable source ↗
Our take
Written Sep 30, 2026GPT-4o-mini is a hosted-only model from OpenAI: we list no download for it, so using it means choosing a host. It takes text, images and files in one request, and it is cheap — but every board we hold places it near the bottom of its field, so pick it for cost and convenience rather than answer quality.
Use it for cheap hosted work where the question arrives with a screenshot or a document attached, or for prototyping and high-volume background jobs where the bill matters more than answer quality. Its large request capacity means a long report or a stack of documents need not be split up first, though reliable recall across all of it is unverified in our data. Skip it if the task needs measured coding, maths or instruction-following strength, or if you need a model you can run on your own machine.
The case for it
- Images and files go into the same request as the text, so a screenshot or a document does not have to be described in words first.
- The request capacity leaves room for a long report or a stack of documents beside the question, though room to hold it is not a guarantee of accurate recall.
- Both listed hosts charge the same rate, so the choice between them is not a price decision.
The case against it
- Near the bottom of the Arena Text field, at 139th of 168 as of 25 Sep 2026 — a board that records which answer people preferred rather than whether it was correct.
- Weak on coding by both measures we hold: 144th of 168 on Arena Coding as of 25 Sep 2026, and 15th of 16 on LiveCodeBench as of 28 Sep 2026, which covers set-piece competitive programming problems rather than fixing issues in an existing project.
- Weak on maths and hard prompts, at 142nd of 163 on Arena Maths as of 25 Sep 2026 and 147th of 168 on Arena Hard Prompts as of 25 Sep 2026, both preference boards rather than correctness tests.
How good is it?
A small text model for chat and quick answers, though it trails most models on everyday questions, writing and code.
- getting answers to everyday questionsArena Text (overall) · 139th of 168
- drafts, rewrites and editingArena Creative Writing · 131st of 168
- writing and completing codeArena Coding · 144th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)139th of 168 · 1318
CodingWriting and fixing code on its own
Arena Coding144th of 168 · 1348
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing131st of 168 · 1294
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 model7 scoresEvery figure we hold, from 7 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 2 hours 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 128K of context.
- per 1M tokens
- $0.15 in / $0.60 out
- Context served
- 128K
- Throughput
- ~44 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.15 / $0.60checked 2 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| OpenAIDirect | $0.15 / $0.60checked 2 hours ago | 128K16K max reply | 44 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 GPT-4o-mini (2024-07-18)
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-gpt-4o-mini-2024-07-18