GPT-4.1 Nano
OpenAI · released Apr 14, 2025
- Type
- Closed
- Input
- $0.10
- Output
- $0.40
- Cached
- $0.025
List price · per 1M tokens · OpenAI at 1M context · machine-readable source ↗
Our take
Written Sep 3, 2026GPT-4.1 Nano is OpenAI's smallest proprietary model, built for long-context tasks at minimal cost. It handles text, images and files across a one-million-token request limit, with its best measured performance in coding.
Pick this for low-cost long-context work where a one-million-token request limit matters more than peak quality. Use it for latency-sensitive applications on the fastest Azure endpoint, or for budget image and file understanding. Skip it if you need open weights, fine-tuning access, or strong maths and creative writing scores.
The case for it
- One-million-token request limit, unusually long for its price tier.
- Lowest published price in its own offer set.
- Strongest measured performance is in coding, well above its overall text score.
- Fastest throughput on one Azure endpoint, more than double the OpenAI endpoint.
The case against it
- Maths is its weakest measured category, nearly 50 points below its overall text score.
- Creative writing and instruction following lag even further behind its coding peak.
- Proprietary weights with no disclosed licence and no fine-tuning access.
How good is it?
A small text model for light chat and simple coding help, though it trails most models on everyday questions and code.
- getting answers to everyday questionsArena Text (overall) · 136th of 168
- writing and completing codeArena Coding · 130th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)136th of 168 · 1322
CodingWriting and fixing code on its own
Arena Coding130th of 168 · 1373
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing125th of 168 · 1307
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 model6 scoresEvery figure we hold, from 6 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 1M of context.
- per 1M tokens
- $0.10 in / $0.40 out
- Context served
- 1M
- Throughput
- ~41 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.10 / $0.40checked 2 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $0.10 / $0.40checked 2 hours ago | 1M943K max reply | 32 tok/s | No | No | Confirmed |
| OpenAIDirect | $0.10 / $0.40checked 2 hours ago | 1M33K max reply | 41 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIswedencentralThrough OpenRouter | $0.11 / $0.44checked 2 hours ago | 1M943K max reply | 38 tok/s | No | No | Confirmed |
OpenRouter
Microsoft Azure AIAcross the 4 listings we hold: 3 say they do not train on prompts, 0 say they do and 1 does not say. 2 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 | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
| Microsoft Azure AIswedencentralThrough OpenRouter | ✓ | ✓ | ✓ |
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 Nano
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 4 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-4-1-nano