GPT-5.1-Codex

Approved Data Classifications

Description

GPT‑5.1 Codex is a specialized version of OpenAI’s GPT‑5.1 family tuned for agentic coding and software engineering tasks, designed to work within tools like IDEs, terminals, and CLI environments with a 400K token context window and multimodal input support (e.g., code plus screenshots) for UI and development workflows. On developer‑focused benchmarks, GPT‑5.1‑Codex achieves around ~73.7 % on SWE‑Bench Verified and roughly 52.8 % on Terminal‑Bench 2.0 in its standard configuration. Compared with general GPT‑5.1 coding results, Codex focuses on sustained coding workflows and tighter integration with developer tooling rather than broad general reasoning improvements.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
gpt-5.1-codex	October 2023	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-codex",
    "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-codex", # 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-codex",
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