Using GPT-5.1 on OpenAI API

Implementation guide · GPT-5.1 · OpenAI

Serverless

OpenAI API exposes GPT-5.1 through model ID gpt-5.1. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-04. Next refresh: weekly.

Quick Start

1
Create an account at OpenAI API and generate an API key.
2
Use the OpenAI API SDK or REST API to call gpt-5.1 — see the documentation for request format.
3
You'll be billed $1.25/1M input, $10.00/1M output tokens. See full pricing.

API Portal Documentation Pricing Model Card

Code Examples

Install

pip install openai

API key

OPENAI_API_KEY

Model ID

gpt-5.1

Use the model slug directly, e.g. "gpt-4o" or "gpt-4.1-mini".

import os
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
    model="gpt-5.1",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on OpenAI API

Type	Price (per 1M)
Input tokens	$1.25
Output tokens	$10.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured Outputs

About GPT-5.1

OpenAI's GPT-5.1 is the main thinking model in the GPT-5.1 family, released November 13, 2025 via API (ChatGPT rollout began November 12, 2025). Features adaptive reasoning that dynamically adjusts thinking time by task complexity, with a reasoning_effort parameter supporting none/low/medium/high settings. Deprecated in ChatGPT as of March 11, 2026 in favor of newer models.

Full model details →

Model Specs

Released2025-11-13

Context262k

OpenAI

San Francisco, California, United States