See how ChatGPT, Perplexity and Google AI Overviews describe you today
Free AI Visibility AuditGPT-4.1 Nano is the smallest and fastest model in OpenAI's GPT-4.1 series, built for tasks where latency and cost matter more than depth of reasoning. It accepts text, images and files, and carries the same million-token-class context as the larger GPT-4.1 models.
OpenAIVerified 24/09/2026Released 14/04/202501 / decision
Each figure sits next to the middle of the field, so it can be read as dear or cheap, wide or narrow, rather than floating on its own. Compared against the 126 models we track, not against an absolute standard.
Capability
Not measured
No published benchmark scores yet
Input / 1M tokens
$0.10
field median $0.30
Output / 1M tokens
$0.40
field median $1.25
Context
1,048K
field median 524K
02 / overview
Four questions, answered separately, because somebody arrives at one of them rather than at the top of the page.
The job it was built for, and the job it is not for.
GPT-4.1 Nano is a small, low-latency general model from OpenAI, positioned as the cheapest entry in the GPT-4.1 line. It is built for high-volume work that has to return quickly: classification, extraction, routing, tagging, first-pass summarisation over long documents. It is not the model to reach for when a task needs sustained reasoning or careful long-form writing, which is what its larger siblings are for.
Where it sits in its line, and when a sibling is the better pick.
GPT-4.1 Nano was first seen in April 2025, arriving alongside the rest of the GPT-4.1 family as its speed-and-cost tier. It is the right pick when you are running the same prompt thousands of times a day and the per-call bill is the constraint, or when a user is waiting on the response. It is the wrong pick for anything where an error is expensive to catch later, where a mid-tier or frontier model earns its higher cost.
The API, the apps it powers, and what its limits let you do.
GPT-4.1 Nano is reached through the OpenAI API and is generally used as a component inside someone else's product rather than something a person talks to directly. The very large context window means you can pass whole documents, transcripts or file attachments in one call and have the model pull structure out of them, and the image and file inputs let it handle scanned pages and uploads rather than clean text alone. Output length is capped well below the input capacity, which suits the extract-and-summarise shape of work it is meant for.
What changes because this exists, or why it does not.
A very cheap model with a very long context changes which tasks are worth automating at all. Work that was previously done with brittle rules or keyword matching, because running a language model over every record was too slow or too expensive, becomes straightforward to run at volume. Nothing here is a capability leap, the point is that the economics let you apply it everywhere rather than selectively.
Follows GPT-4.1 Mini. Superseded by GPT-5. See the whole line.
03 / evidence
Split by category, so a strong number never hides a thin evidence base. Verified means we read it on the benchmark's own published results; a provider's claim about its own model is shown and labelled rather than dropped.
No published benchmark scores for this model yet.
We publish a score only where we can link the result to where it was published. Until a benchmark result for this model exists in a source we read, this section stays empty rather than being filled with a provider's marketing figure.
How we decide what counts as evidence04 / ledger
Every published row, grouped by category, each compared with the best published score on the same benchmark. 'Is 64% good' is a question nobody can answer; '26 points behind the leader' is one anybody can.
Nothing in the ledger yet.
Each row here carries a score, the benchmark it came from, what the leading model scored on the same test, and a link to the published result. Rows appear as results are published and read.
How we decide what counts as evidence05 / capability
Where this model is strong, and against how many peers. Ranks are against models with evidence in that category, not against everything we track: ranking against models nobody tested would rank who published, not who is better.
No category scores to shape yet.
A category score is the weighted mean of the benchmarks published for it. With no published rows there is nothing to average, and an empty chart drawn at zero would say something false.
How we decide what counts as evidence06 / cost
List API rates as last read from the provider, with the source on every row, plus every change we have recorded since we started tracking it.
| Charge | Price | Unit | Read on | Source |
|---|---|---|---|---|
| Input | $0.10 | per 1M tokens | 2026-09-24 | Check |
| Output | $0.40 | per 1M tokens | 2026-09-24 | Check |
GPT-4.1 Nano is the cheapest model in the GPT-4.1 family and sits at the low end of the wider market, with output charged at a small multiple of input. At this level, cost stops being the thing that decides your architecture, and the real question becomes whether the smallest model is accurate enough for the job.
| Workload | Input / month | Output / month | Cost |
|---|---|---|---|
| A small product team | 20M tokens | 5M tokens | $4.00 |
| A busy support assistant | 200M tokens | 40M tokens | $36.00 |
| A document pipeline | 1000M tokens | 100M tokens | $140.00 |
List API rates, no caching and no batch discount, which both providers offer and which change the answer a great deal. Treat these as the ceiling, not the bill.
07 / specs
As listed by the provider's own catalogue and re-read every few hours. Anything absent is absent there too.
| Context window | 1,047,576 tokens |
|---|---|
| Maximum output | 32,768 tokens |
| Modalities | image, text, file |
| Released | 14/04/2025 |
| Status | Current |
| Catalogue identifier | openai/gpt-4.1-nano |
08 / lineage
What this model replaced, what replaced it, and what else its provider has in the field.
Also from OpenAI
09 / line
Every model in this family in release order, so a page from eight months ago says in one glance that two newer ones exist.
Came before
← GPT-4.1 MiniCame after
GPT-5 →Ordered by release date and worked out from the naming, so a new member slots in as soon as its page exists. A retired model keeps its page and its place in the line.
10 / notes
What this model changes for a brand trying to be cited in AI answers, and every change we have logged since it launched.
What it changes for you
Models like GPT-4.1 Nano are often the ones doing the retrieval, filtering and summarising steps behind an AI answer, even when a larger model writes the final text. That means your content is frequently being judged first by a small, fast model skimming for relevance, so clear structure, plain claims and self-contained pages matter more than elegant prose. If a page needs careful reading to work out what your product does, it can be dropped before the bigger model ever sees it.
Buyers rarely meet GPT-4.1 Nano by name. They meet it through the OpenAI API, inside SaaS products that use it for background classification, search ranking, tagging and document processing, where it does its work without appearing in the interface.
Nothing published here yet. Changes appear within hours of a provider announcing them.
11 / questions
The things people ask about this model, answered from what is on this page rather than from anywhere else.
Models change what gets cited. We measure whether AI answers name your brand or your competitors across every assistant, and show you what to change.