GPT-4.1
OpenAI · released Apr 14, 2025
- Type
- Proprietary
- Input
- $2.00
- Output
- $8.00
- Cached
- $0.50
List price · per 1M tokens · OpenAI at 1M context · source ↗
Our take
Written Aug 3, 2026GPT-4.1 is a proprietary multimodal model from OpenAI that can handle up to one million tokens in a single request and accepts text, images and files. Its measured coding skill is the strongest of its Arena categories, while its maths score trails well behind.
Pick this for long-document analysis at one million tokens, coding workloads where its measured skill is highest, or multimodal inputs that need text output. Use the standard Azure tier for throughput rather than the premium one. Skip it if you need downloadable weights, a permissive licence, or strong measured maths performance.
The case for it
- Exceptionally long request limit at 1,047,576 tokens.
- Coding is the standout skill: its Arena Coding score is 82.7 points above its own Maths score.
- Stable leaderboard scores, with under 0.1 drift across two evaluation dates in every category.
- Predictable pricing across platforms, with only a modest premium on one of four tracked offers.
The case against it
- Maths is the weakest Arena category, 82.7 points below its own Coding score.
- Azure throughput varies sharply by tier: the standard tier is more than three times faster than the premium tier for a modestly higher rate.
- Proprietary weights with no disclosed licence; you cannot download or self-host it.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)66th of 143 · 1413.8
CodingWriting and fixing code on its own
Arena Coding70th of 143 · 1456
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
GPT-4.1 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 28th of 39 with 39.6.
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 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
- $2.00 in / $8.00 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $2.00 / $8.00 | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $2.00 / $8.00 | 1M | 77 tok/s | No | No | Confirmed |
| OpenAI | $2.00 / $8.00 | 1M33K out | 59 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIswedencentral | $2.20 / $8.80 | 1M | 15 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
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