GPT-4.1 Nano
OpenAI · released Apr 14, 2025
- Type
- Proprietary
- Input
- $0.10
- Output
- $0.40
- Cached
- $0.025
List price · per 1M tokens · OpenAI at 1M context · source ↗
Our take
Written Aug 3, 2026GPT-4.1 Nano is OpenAI's smallest hosted-only model, built for long-context work at entry-level cost. It handles text, images and files across a one-million-token request limit, with a coding score that sits well above its general text rating.
Pick this for low-cost long-context processing with a one-million-token limit, or coding where it scores highest. Use the high-throughput Azure tier when speed matters — nearly six times faster than standard Azure. Skip it if you need strong maths, parameter transparency, or self-hosting.
The case for it
- Extremely long request limit at entry-level pricing — one million tokens, matching far more expensive models.
- Coding performance sits 51.7 points above its overall text score on the independent leaderboard.
- High-throughput Azure tier at 208 tokens per second, nearly six times the standard Azure speed.
- Arena text score moved less than a tenth of a point across three days, showing unusual stability.
The case against it
- Maths is its weakest suit, scoring 48.4 points below hard prompts and 100.1 points below coding on the same leaderboard.
- No published parameter count and no open licence — entirely hosted-only with no transparency on size.
- Throughput is unverified for two of the four tracked offers.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)115th of 143 · 1322.2
CodingWriting and fixing code on its own
Arena Coding108th of 143 · 1373.9
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored GPT-4.1 Nano for this. We would take the rating from Arena Agent (IPS).
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 Nano 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 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.
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
- $0.10 in / $0.40 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.10 / $0.40 | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $0.10 / $0.40 | 1M | 35 tok/s | No | No | Confirmed |
| OpenAI | $0.10 / $0.40 | 1M33K out | 147 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIswedencentral | $0.11 / $0.44 | 1M | 208 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 Nano
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-nano