GPT-4.1
OpenAI · released Apr 14, 2025
- Type
- Closed
- Input
- $2.00
- Output
- $8.00
- Cached
- $0.50
List price · per 1M tokens · OpenAI at 1M context · machine-readable source ↗
Our take
Written Sep 2, 2026GPT-4.1 is a proprietary multimodal model from OpenAI that handles text, images and files in a single request of up to roughly one million tokens. It offers broad, consistent performance across chat and reasoning tasks, though its coding-automation scores sit below specialist frontier models.
Choose this for long-document analysis where a million-token request limit matters more than raw coding depth, or for general chat and instruction-following workloads that need reliable breadth rather than peak specialism. Use it if you want premium throughput via Azure. Skip it if you need strong autonomous coding, price competition between hosts, or any visibility into model size or efficiency.
The case for it
- Exceptional context length for its tier: roughly four times the previous long-context standard.
- Broad consistency across six arena sub-boards, with no task type falling more than 40 points below its overall score.
- Premium Azure throughput reaches 80 tokens per second, markedly faster than standard Azure or OpenAI's own hosting.
The case against it
- Coding automation lags well behind frontier specialists: under 40% on SWE-bench Verified.
- No price competition at this tier, with uniform rates across three of four tracked offers.
- Parameter count undisclosed, so there is no basis to claim efficiency or size class.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)82nd of 168 · 1415
CodingWriting and fixing code on its own
Arena Coding89th of 168 · 1456
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 31st of 42 with 39.6.
WritingDrafting and rewriting prose
Arena Creative Writing66th of 168 · 1402
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 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.
Where to rent it
Prices checked 4 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
- $2.00 in / $8.00 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 | $2.00 / $8.00checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $2.00 / $8.00checked 4 hours ago | 1M943K max reply | 47 tok/s | No | No | Confirmed |
| OpenAIDirect | $2.00 / $8.00checked 4 hours ago | 1M33K max reply | 41 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIswedencentralThrough OpenRouter | $2.20 / $8.80checked 4 hours ago | 1M943K max reply | 100 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
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