GPT-5.1-Codex
OpenAI · released Nov 13, 2025
- Type
- Proprietary
- Input
- $1.25
- Output
- $10.00
- Cached
- Not published
List price · per 1M tokens · OpenAI at 400K context · source ↗
Our take
Written Aug 3, 2026GPT-5.1-Codex is a proprietary coding specialist from OpenAI that can handle up to 400,000 tokens in a single request. It holds a narrow but consistent top-tier ranking on web development benchmarks, though its measured capabilities are limited to just two coding tests.
Pick this for long-context code review or repository analysis at 400K tokens, or web development where its Arena Code ranking matters. Use Azure if 67 tokens per second meets latency needs. Skip it if you need general reasoning, maths, or multilingual coding scores; inspectable weights; or if only the premium tier is available.
The case for it
- Extremely long context for code workflows, at 400,000 tokens.
- Consistent top-tier web development ranking, holding within 0.17 points across seven evaluations.
- Verified software engineering capability with a 66% score on SWE-bench Verified.
The case against it
- Narrow benchmark coverage for a flagship coding model: only two benchmarks on record, with no general reasoning, mathematics, or multilingual coding scores.
- Premium pricing on one tier with no measured throughput advantage on most channels; only Azure offers a measured speed figure at the standard rate.
- Proprietary weights with no licence disclosed, so the model cannot be inspected or self-hosted.
How good is it?
IntelligencePuzzles, maths, exam questions
Nobody we watch has scored GPT-5.1-Codex for this. We would take the rating from Arena Text (overall).
CodingWriting and fixing code on its own
GPT-5.1-Codex is not on Arena Coding, which is where the rating would come from, so there is no rating here. It is on Arena Code (WebDev), in 58th of 74 with 1336.1.
AgenticPlanning, calling tools, staying on task
GPT-5.1-Codex 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
Nobody we watch has scored this model for writing. 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.
Every published score for this model2 scoresEvery figure we hold, from 2 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
- $1.25 in / $10.00 out
- Context served
- 400K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $1.25 / $10.00 | 400K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $1.25 / $10.00 | 400K | 32 tok/s | No | No | Confirmed |
| OpenAI | $1.25 / $10.00 | 400K | not measured | No | Yesunknown period | Unknown |
| OpenAIpriority tier | $2.50 / $20.00 | 400K | not measured | No | Yesunknown period | Unknown |
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. 1 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 | |||
| OpenAIpriority |
Tool calling: 2 of 4 listings say yes, 2 publish no parameter list. JSON output: 2 of 4 listings say yes, 2 publish no parameter list. Strict schema: 2 of 4 listings say yes, 2 publish no parameter list.
Models people weigh against GPT-5.1-Codex
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 2 of 4 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.
- 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->text
- Catalogue slug
- openai-gpt-5-1-codex