# GPT-5.1

> OpenAI's warmer, more conversational GPT-5 update — adds adaptive reasoning that spends fewer tokens on easy tasks, a no-reasoning mode, and shell + apply_patch coding tools.

- Maker: OpenAI
- Line: GPT (Flagship / Thinking)
- Canonical page: https://ai-tldr.dev/models/gpt-5-1/
- Updated: 2026-06-18

## In short

GPT-5.1 is OpenAI's flagship large language model in the GPT-5 (Flagship / Thinking) line, released on November 12, 2025 in ChatGPT and rolled out to the API for developers on November 13. It has a 400K-token context window and costs $1.25 per million input tokens and $10.00 per million output tokens. You can use it through OpenAI API and OpenRouter.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 400K (max output 128K) | [1] |
| Input price | $1.25 / 1M tokens (cached $0.125 / 1M tokens) | [2] |
| Output price | $10.00 / 1M tokens | [2] |
| Licence | Proprietary · API only | [1] |
| Released | 12 November 2025 | [3] |
| Parameters | Undisclosed | [1] |
| Knowledge cutoff | September 30, 2024 | [1] |

## Sources

1. [GPT-5.1 Instant and Thinking System Card Addendum — OpenAI](https://openai.com/index/gpt-5-system-card-addendum-gpt-5-1/)
2. [GPT-5.1 model reference — OpenAI API docs](https://developers.openai.com/api/docs/models/gpt-5.1)
3. [Introducing GPT-5.1 for developers — OpenAI](https://openai.com/index/gpt-5-1-for-developers/)

## Overview

GPT-5.1 is OpenAI's flagship large language model in the GPT-5 (Flagship / Thinking) line, released on November 12, 2025 in ChatGPT and rolled out to the API for developers on November 13. It ships as two models: GPT-5.1 Instant — a warmer, more conversational default tuned for everyday chat and quick coding — and GPT-5.1 Thinking, a reasoning model aimed at harder, multi-step problems. It positions itself as a smarter, friendlier successor to GPT-5 rather than a clean-sheet model.

Its headline change is adaptive reasoning: GPT-5.1 decides how much time to spend thinking based on how hard the task looks, spending fewer tokens on straightforward prompts and more on complex ones. OpenAI reports it runs roughly 2-3x faster than GPT-5 on simple tasks while using far fewer tokens, and it adds a new 'none' reasoning-effort option that makes the model respond like a non-reasoning model for latency-sensitive use. ChatGPT also gained eight selectable personality presets and a warmer default tone.

For developers, GPT-5.1 carries a 400,000-token context window, up to 128,000 output tokens, a September 30, 2024 knowledge cutoff, and text-plus-image (vision) input. The API release adds two new built-in tools — apply_patch for structured, reliable code edits and a shell tool for proposing shell commands a developer runs — plus extended prompt caching that retains prompts for up to 24 hours. It is priced at $1.25 per million input tokens and $10 per million output tokens, with cached input at $0.125 per million.

## Benchmarks

- SWE-bench Verified — real-world software engineering: 76.3% ([source](https://medium.com/@leucopsis/how-gpt-5-2-compares-to-gpt-5-1-54e580307ecb))
- GPQA Diamond — PhD-level science reasoning: 88.1% ([source](https://www.aifire.co/p/gpt-5-2-review-benchmarks-vs-gemini-3-0-claude-4-5))
- AIME 2025 — competition math: 94% ([source](https://medium.com/@leucopsis/how-gpt-5-2-compares-to-gpt-5-1-54e580307ecb))
- SWE-bench Pro — harder multi-file engineering: 50.8% ([source](https://www.aifire.co/p/gpt-5-2-review-benchmarks-vs-gemini-3-0-claude-4-5))
- Artificial Analysis Intelligence Index (GPT-5.1 high): 39 ([source](https://artificialanalysis.ai/models/gpt-5-1))

## Pricing

- Input: $1.25 / 1M tokens per 1M tokens
- Cached input: $0.125 / 1M tokens per 1M tokens
- Output: $10.00 / 1M tokens per 1M tokens

Standard API pricing for the gpt-5.1 model. Cached input is a 90% discount on input; extended prompt caching retains prompts for up to 24 hours. Reasoning tokens in Thinking mode are billed as output tokens.

Source: https://developers.openai.com/api/docs/models/gpt-5.1

## Strengths

- Adaptive reasoning that spends fewer thinking tokens on easy prompts and more on hard ones — roughly 2-3x faster than GPT-5 on simple tasks at lower token cost
- Two complementary variants from one line: GPT-5.1 Instant (warm, fast, default) and GPT-5.1 Thinking (deeper reasoning for complex problems)
- A 'none' reasoning-effort setting that turns off thinking entirely for latency-sensitive, interactive use
- Strong coding and agentic results — 76.3% on SWE-bench Verified — plus new apply_patch and shell tools that tighten the edit-and-run loop
- Frontier science reasoning: 88.1% on GPQA Diamond and 94.0% on AIME 2025
- Large 400K-token context window with up to 24-hour extended prompt caching for cheaper, faster follow-ups
- Vision input (text + images) for screenshots, charts, diagrams, and document pages
- Warmer, more steerable ChatGPT personality with eight selectable presets

## Best for

- Everyday conversational assistance and writing where a warmer, faster default tone matters
- Agentic coding workflows that edit files (apply_patch) and propose shell commands for a developer to run
- Complex reasoning, math, and science tasks routed to GPT-5.1 Thinking
- Latency-sensitive interactive apps using Instant with reasoning_effort set to 'none'
- Long-document and large-codebase analysis within the 400K-token context window
- Vision-assisted steps that read screenshots, charts, scanned pages, and diagrams
- Cost-sensitive high-volume API workloads that benefit from adaptive token spend and 24-hour prompt caching

## How to access

- [OpenAI API](https://developers.openai.com/api/docs/models/gpt-5.1) — model id `gpt-5.1 / gpt-5.1-chat-latest`
- [OpenRouter](https://openrouter.ai/openai/gpt-5.1) — model id `openai/gpt-5.1`

## GPT (Flagship / Thinking) versions

- [GPT-5.5](https://ai-tldr.dev/models/gpt-5-5/) (23 April 2026)
- [GPT-5.4](https://ai-tldr.dev/models/gpt-5-4/) (5 March 2026)
- [GPT-5.2](https://ai-tldr.dev/models/gpt-5-2/) (11 December 2025)
- GPT-5.1 (12 November 2025) — this page
- [GPT-5](https://ai-tldr.dev/models/gpt-5/) (7 August 2025)
- [GPT-4o](https://ai-tldr.dev/models/gpt-4o/) (13 May 2024)

## FAQ

### What is GPT-5.1?

GPT-5.1 is OpenAI's flagship large language model, released November 12, 2025 (and to developers on November 13). It comes in two variants — GPT-5.1 Instant, a warmer and faster default, and GPT-5.1 Thinking, a reasoning model for complex tasks — and its main new feature is adaptive reasoning that scales how much the model thinks with the difficulty of the task.

### How is GPT-5.1 different from GPT-5?

GPT-5.1 has a warmer, more conversational default tone, eight selectable personality presets in ChatGPT, and adaptive reasoning that makes it roughly 2-3x faster than GPT-5 on simple tasks while using fewer tokens. It also adds a 'none' reasoning-effort option, new apply_patch and shell tools for coding, and extended prompt caching of up to 24 hours.

### How much does GPT-5.1 cost?

Per OpenAI's API pricing, GPT-5.1 is $1.25 per million input tokens and $10.00 per million output tokens, with cached input at $0.125 per million (a 90% discount). Reasoning tokens used by GPT-5.1 Thinking are billed as output tokens.

### What is GPT-5.1's context window and knowledge cutoff?

GPT-5.1 has a 400,000-token context window with up to 128,000 output tokens, a knowledge cutoff of September 30, 2024, and accepts text plus image (vision) input. Audio input is not supported.

## Links

- [Introducing GPT-5.1 for developers — OpenAI](https://openai.com/index/gpt-5-1-for-developers/)
- [GPT-5.1: A smarter, more conversational ChatGPT — OpenAI](https://openai.com/index/gpt-5-1/)
- [GPT-5.1 model reference — OpenAI API docs](https://developers.openai.com/api/docs/models/gpt-5.1)
- [GPT-5.1 Instant and Thinking System Card Addendum — OpenAI](https://openai.com/index/gpt-5-system-card-addendum-gpt-5-1/)
- [OpenAI — official site](https://openai.com)
- [GPT-5.1 on OpenRouter — pricing & context](https://openrouter.ai/openai/gpt-5.1)
- [GPT-5.1 — Artificial Analysis (Intelligence Index, specs)](https://artificialanalysis.ai/models/gpt-5-1)
- [Introducing GPT-5.1 for developers — Simon Willison](https://simonwillison.net/2025/Nov/13/gpt-51/)
- [GPT-5.1 benchmark comparison — Medium (leucopsis)](https://medium.com/@leucopsis/how-gpt-5-2-compares-to-gpt-5-1-54e580307ecb)
- [GPT-5.1 benchmarks — AI Fire review](https://www.aifire.co/p/gpt-5-2-review-benchmarks-vs-gemini-3-0-claude-4-5)
- [GPT-5.1 — Wikipedia](https://en.wikipedia.org/wiki/GPT-5.1)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/gpt-5-1/