GPT-5.1
OpenAI · released Nov 13, 2025
- Type
- Closed
- Input
- $1.25
- Output
- $10.00
- Cached
- $0.13
List price · per 1M tokens · OpenAI at 128K context · machine-readable source ↗
Our take
Written Sep 30, 2026GPT-5.1 is a hosted-only model from OpenAI: we list no download for it, so using it means choosing a host. Its measured quality is middling rather than leading, but the same model is available at rates that differ by a factor of four, so where you reach it matters more than which model it is.
Reach for it when you want a strong general chat model and the Arena preference boards are the kind of evidence you trust, or when long documents would otherwise have to be split up before you can ask about them. Compare the listed offers before you commit, because the same model is priced very differently across them. Skip it if you need to run the model on your own hardware, or if web-app building is the job.
The case for it
- 66% of real GitHub issues resolved end-to-end on SWE-bench Verified via mini-SWE-agent, 15th of 42 as of 19 Feb 2026 — a result for the model inside that harness, not for the model on its own.
- Request capacity is large enough that long documents need not be split up before you ask about them, though reliable recall across the whole of it is unverified in our data.
- Text, image and file input with written output, so a screenshot or a document can go in with the question.
The case against it
- 62nd of 168 on Arena Text (overall) and 76th of 95 on Arena Code (WebDev) as of 25 Sep 2026 — the first is a human-preference score, not a correctness measure, and the second is a small field where it lands near the bottom.
- We list no download for it, so using it means choosing a host.
- The same model costs four times as much depending on where you reach it, with no measured difference between the offers in our data to justify the gap.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)62nd of 168 · 1438
Also on this board: 1456 (Sep 25, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding72nd of 168 · 1476
Also on this board: 1492 (Sep 25, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 15th of 42 with 66.
WritingDrafting and rewriting prose
Arena Creative Writing58th of 168 · 1408
Arena Creative Writing is the only board that has scored it for this.
Also on this board: 1428 (Sep 25, 2026). Read the pair, not the higher one.
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 model8 scoresEvery figure we hold, from 8 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.
Microsoft Azure AI, through OpenRouter
Why this differs from the header. The strip above quotes OpenAI's own list price; this is the cheapest live offer, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $1.25 in / $10.00 out
- Context served
- 400K
- Throughput
- ~52 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIflex tierThrough OpenRouter | $0.63 / $5.00checked 4 hours ago | 400K128K max reply | 26 tok/s | No | Yesunknown period | Unknown |
| OpenRouterOpenRouter's own listing | $1.25 / $10.00checked 4 hours ago | 400K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $1.25 / $10.00checked 4 hours ago | 400K128K max reply | 52 tok/s | No | No | Confirmed |
| OpenAIDirect | $1.25 / $10.00checked 4 hours ago | 128K16K max reply | 44 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIswedencentralThrough OpenRouter | $1.38 / $11.00checked 4 hours ago | 400K128K max reply | 78 tok/s | No | No | Confirmed |
| OpenAIfast tierThrough OpenRouter | $2.50 / $20.00checked 4 hours ago | 400K128K max reply | 133 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 6 listings we hold: 5 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 |
|---|---|---|---|
| OpenAIflexThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
| Microsoft Azure AIswedencentralThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIfastThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 6 of 6 listings say yes. JSON output: 6 of 6 listings say yes. Strict schema: 6 of 6 listings say yes.
Models people weigh against GPT-5.1
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 6 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-5-1