GPT-5.1, the OpenAI model in numbers

Overview

GPT-5.1 is a language model from OpenAI, released on November 13, 2025. That makes it 11 months old as of October 22, 2026. It is a closed model: you access it through an API, from OpenAI or one of the 31 providers listed on models.dev. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money.

We file it under mid-range models (34 models in this category on the site).

How much does GPT-5.1 cost?

GPT-5.1 costs $1.25 per million input tokens and $10 per million output tokens (median of 31 providers, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.045; a thousand of those tasks, $45.

That is 2.3 times the median output price of mid-range models ($4.38).

To estimate your own budget, use the agent cost calculator.

What do independent benchmarks say?

According to results published by Epoch AI (checked on October 22, 2026), GPT-5.1 has a capability index of 75.8 out of 100, computed on 4 benchmarks from our basket.

It is not among the top 30 of the weekly ranking.

• GPQA Diamond (PhD-level science questions): 87.6% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 88.6% — the best tracked model, GPT-5.5 Pro, reaches 100%
• SWE-bench Verified (fixing real software bugs): 68% — the best tracked model, Claude Opus 4.7, reaches 83.5%
• Terminal-Bench (agent tasks in a terminal): 47.6% — the best tracked model, GPT-5.5, reaches 84.7%

Technical specifications

Its context window reaches 272,000 tokens, roughly 408 pages of text at 500 words per page: enough for a long report or several contracts at once. A single answer can run to 8,192 tokens.

It accepts as input: text and image. Its knowledge stops at September 30, 2024: beyond that, it needs web search or your documents.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

Who is it for?

Given its category, GPT-5.1 is mainly aimed at a balance between quality and cost, for everyday uses that do not justify a frontier model.

Its Terminal-Bench result (47.6%, above the median of tracked models) makes it a serious candidate for coding agents.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

What could replace it?

In the same category, the models closest to GPT-5.1 are:

• Gemini 3.5 Flash (Google DeepMind, index 76)
• GPT-5 (OpenAI, index 75.3)
• Claude Opus 4.6 (Anthropic, index 76.7)
• Grok 4.3 (xAI, index 76.8)