GPT-5.1
OpenAI · released Nov 13, 2025
- Type
- Proprietary
- Input
- $0.63
- Output
- $5.00
- Cached
- $0.063
List price · per 1M tokens · OpenAI at 400K context · source ↗
Our take
Written Aug 2, 2026GPT-5.1 is OpenAI's flagship reasoning model that can handle up to 400,000 tokens in a single request and accepts text, images and files. It leads on several independent leaderboards we track, with its strongest showing in coding, and is available only through hosted APIs with tiered throughput options.
Pick this for long-document analysis or high-stakes coding where its leaderboard scores are strongest. Use it when guaranteed throughput matters, as Azure offers more than double the speed of the entry tier. Skip it if you need local hardware, face tight output budgets, or mainly do web development coding.
The case for it
- Broad leaderboard strength with its highest single score in coding, 36 points above its overall text score.
- Exceptionally long request limit at 400,000 tokens.
- Tiered pricing allows a cost-throughput tradeoff, with one Azure option delivering more than double the speed of the entry tier.
The case against it
- Web development coding lags its general coding score by roughly a hundred points or more.
- Output costs eight times the input rate across every tier, which punishes generation-heavy workloads.
- Proprietary weights with no disclosed licence; you cannot download or self-host it.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)46th of 143 · 1438.7
Also on this board: 1454.6 via High (Aug 2, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding54th of 143 · 1474.3
Also on this board: 1490.7 via High (Aug 2, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
GPT-5.1 is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 15th of 39 with 66.
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-5.1 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 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.
Or rent it from someone else
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 400K of context.
- per 1M tokens
- $0.63 in / $5.00 out
- Context served
- 400K
- Throughput
- ~31 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIdefault tier | $0.63 / $5.00 | 400K | 31 tok/s | No | Yesunknown period | Unknown |
| OpenRouter | $1.25 / $10.00 | 400K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $1.25 / $10.00 | 400K | 90 tok/s | No | No | Confirmed |
| OpenAI | $1.25 / $10.00 | 128K16K out | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIswedencentral | $1.38 / $11.00 | 400K | 59 tok/s | No | No | Confirmed |
OpenRouter
Microsoft Azure AIAcross the 5 listings we hold: 3 say they do not train on prompts, 0 say they do and 2 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 |
|---|---|---|---|
| OpenAIdefault | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AI | ✓ | ✓ | ✓ |
| OpenAI | |||
| Microsoft Azure AIswedencentral | ✓ | ✓ | ✓ |
Tool calling: 4 of 5 listings say yes, 1 publishes no parameter list. JSON output: 4 of 5 listings say yes, 1 publishes no parameter list. Strict schema: 4 of 5 listings say yes, 1 publishes no parameter list.
Models people weigh against GPT-5.1
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 1 of 5 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 5 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-5-1