GPT-5.1

Approved Data Classifications

Description

GPT‑5.1 is OpenAI’s mid‑cycle refinement of the GPT‑5 series, released in late 2025 with a focus on improved efficiency, adaptive reasoning, and practical coding performance rather than a major architectural overhaul. It introduces adaptive reasoning that dynamically adjusts how much “thinking” the model does based on task complexity—spending fewer tokens and responding faster on easy tasks while persisting longer on harder ones—which leads to noticeably speedier responses and lower token costs on typical workloads. GPT‑5.1 also adds new developer‑oriented tools like apply_patch and a shell command tool to improve coding workflows and increased steerability in outputs. Benchmarks from both OpenAI and independent sources show that GPT‑5.1 scores around 76.3% on SWE‑bench Verified coding tasks (an improvement over GPT‑5’s ~72.8%) and ~94% on the AIME 2025 math benchmark, with strong visual reasoning results (e.g., ~85.4% on MMMU). It generally maintains or slightly improves performance on reasoning and math benchmarks versus GPT‑5 while being 2–3× faster on straightforward tasks and more token‑efficient.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
gpt-5.1	August 2025	Image, Text, Audio, Video	Text	400,000	$1.25/1M input $10.00/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
    "model": "gpt-5.1",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
}'

python

from openai import OpenAI
  client = OpenAI(
      api_key="your_api_key",
      base_url="https://api.ai.it.ufl.edu/v1"
  )

  response = client.chat.completions.create(
      model="gpt-5.1", # model to send to the proxy
      messages = [
          { role: "system", content: "You are a helpful assistant." },
          {
              "role": "user",
              "content": "Write a haiku about an Alligator."
          }
      ]
  )

  print(response.choices[0].message)

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
apiKey: 'your_api_key',
baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.chat.completions.create({
model: "gpt-5.1",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{
role: "user",
content: "Write a haiku about an Alligator.",
},
],
});

print(completion.choices[0].message)

---

References

1. OpenAI https://openai.com/
2. LLM Stats https://llm-stats.com
3. Artificial Analysis https://artificialanalysis.ai