GPT-4.1 Mini
OpenAI · released Apr 14, 2025
- Type
- Proprietary
- Input
- $0.40
- Output
- $1.60
- Cached
- $0.10
List price · per 1M tokens · OpenAI at 1M context · source ↗
Our take
Written Aug 2, 2026GPT-4.1 Mini is OpenAI's compact hosted-only model with a one-million-token request limit and measured coding strength. It accepts text, images and files, and is positioned as a long-context workhorse within the OpenAI ecosystem.
Choose this for coding tasks where its Arena leaderboard score is strongest, or for processing very long documents within the OpenAI ecosystem. It is the fastest on OpenAI's own API among the tracked hosts. Skip it if you need strong creative-writing scores, want to self-host, or need price competition between providers.
The case for it
- One-million-token request limit, unusually long for its price tier.
- Coding is its standout skill on the Arena leaderboard, scoring 50.7 points above its own overall average.
- Fastest throughput on the first-party API at 35 tokens per second, double the Azure standard rate.
The case against it
- Creative writing is its weakest measured category, 84.2 points below its coding score.
- No real price competition: every tracked offer is identical or more expensive, with slower throughput on the pricier option.
- Hosted only with undisclosed size; no parameters published and no licence available for download.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)87th of 143 · 1383
CodingWriting and fixing code on its own
Arena Coding84th of 143 · 1433.6
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
GPT-4.1 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 34th of 39 with 23.9.
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 GPT-4.1 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 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.
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
- $0.40 in / $1.60 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.40 / $1.60 | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $0.40 / $1.60 | 1M | 13 tok/s | No | No | Confirmed |
| OpenAI | $0.40 / $1.60 | 1M33K out | 32 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIswedencentral | $0.44 / $1.76 | 1M | 10 tok/s | No | No | Confirmed |
Microsoft Azure AIAcross the 4 listings we hold: 3 say they do not train on prompts, 0 say they do and 1 do not say. 2 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 | ✓ | ✓ | ✓ |
| Microsoft Azure AI | ✓ | ✓ | ✓ |
| OpenAI | ✓ | ✓ | ✓ |
| Microsoft Azure AIswedencentral | ✓ | ✓ | ✓ |
Tool calling: 4 of 4 listings say yes. JSON output: 4 of 4 listings say yes. Strict schema: 4 of 4 listings say yes.
Models people weigh against GPT-4.1 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 4 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-gpt-4-1-mini