gpt-4.1

completions

byopenai

gpt-4.1

completions

Published by: openaiProvider:

openai

GPT-4.1 is OpenAI's flagship model for complex tasks. It is well suited for problem solving across domains.

Released

Apr 14, 2025

Knowledge

Jun 1, 2024

License

Proprietary

Context

1047576

Input

$2 / 1M tokens

Output

$8 / 1M tokens

Cached

$0.5 / 1M tokens

Capabilities: tools

Accepts: text, image

Returns: text

Released Apr 14, 2025Knowledge Cutoff: Jun 1, 2024License: Proprietary

Context: 1047576 Input: $2 / 1M tokensOutput: $8 / 1M tokensCached: $0.5 / 1M tokensCapabilities: toolsAccepts: text, imageReturns: text

Access gpt-4.1 through LangDB AI Gateway

Recommended

Integrate with openai's gpt-4.1 and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for gpt-4.1

Overall Performance: 53.3771875 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	43.70	Top 29%	Mathematics
AA Coding Index	41.90	Top 25%	Programming
AAII	43.40	Top 22%	General
AA Math Index	34.70	Top 49%	Mathematics
GPQA	66.45	Top 28%	STEM (Physics, Chemistry, Biology)
HLE	4.60	Top 44%	General Knowledge
LiveCodeBench	45.70	Top 29%	Programming
MATH-500	91.30	Top 27%	Mathematics
MMLU	90.20	Top 4%	General Knowledge
MMLU-Pro	80.60	Top 24%	General Knowledge
MMMU	74.80	Top 27%	General Knowledge
SciCode	38.10	Top 9%	Scientific

MMLU Score: 90.20 - Massive Multitask Language Understanding benchmark

GPQA Score: 66.45 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openai

Model Type: completions

Context Size: 1047576 tokens

Comparing against 345 models in the database

Performance Analytics for gpt-4.1

Usage Statistics (Last 5 Days):

Total Requests: 108 API calls
Average TPS: 1131.19 tokens per second
Average Response Time: 6828.90ms
Average Time to First Token: 736.10ms
Total Cost: $1.09
Average Request Cost: $0.0101

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/14/2025	45	933.20	5664.50ms	567.30ms	$0.33
9/15/2025	54	1309.32	7967.50ms	816.00ms	$0.69
9/16/2025	2	13.42	1117.40ms	1117.40ms	$0.00
9/17/2025	2	269.31	6617.00ms	1282.10ms	$0.01
9/19/2025	5	798.66	7380.60ms	1020.70ms	$0.06

Performance Summary:

Model: gpt-4.1 by openai

Monitoring Period: 9/13/2025 to 9/20/2025

Average Daily Requests: 22

Peak Daily Requests: 54

Statistics

View Full Statistics

Request Volume

Daily API requests

108

Performance (TPS)

Tokens per second

1131.19 tokens/s

Category Scores

vision#8

Benchmark Tests

View Other Benchmarks

AIME

43.7

Mathematics

AA Coding Index

41.9

Programming

AAII

43.4

General

AA Math Index

34.7

Mathematics

GPQA

66.5

STEM (Physics, Chemistry, Biology)

HLE

4.6

General Knowledge

LiveCodeBench

45.7

Programming

MATH-500

91.3

Mathematics

MMLU

90.2

General Knowledge

MMLU-Pro

80.6

General Knowledge

MMMU

74.8

General Knowledge

SciCode

38.1

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU	MMLU-Pro	MMMU	SciCode
Score	43.7	41.9	43.4	34.7	66.5	4.6	45.7	91.3	90.2	80.6	74.8	38.1

Compare with Similar Models

claude-sonnet-4

claude-opus-4

gemini-2.5-pro

gemini-2.5-pro-preview

grok-4

gemini-2.5-flash

Code Examples

Integration samples and API usage

Code Samples for gpt-4.1

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "gpt-4.1",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: gpt-4.1

Provider: openai

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from openai

gpt-4.1-mini

gpt-4.1-nano

gpt-4o-search-preview

o1-mini

gpt-4o

Comments on Issue #519 in microsoft/vscode

5/23/2025

56,793 tokens

Scrape the main text content from https://www.bbc....

5/23/2025

28,713 tokens

gpt-4.1 by openai - AI Model Details, Pricing, and Performance Metrics

gpt-4.1

gpt-4.1

Access gpt-4.1 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

gpt-4.1-mini

gpt-4.1-nano

gpt-4o-search-preview

o1-mini

gpt-4o

gpt-4o-mini

Conversations

Finance Reasoning Team built using Agno

Finance Reasoning Team built using Agno

Travel Planning Agent built with OpenAI Agents SDK

Web Search Agent built wtih Google ADK

Research Agent using Agno AGI

Report Writing Agent built using CrewAI

Dynamic Order Management System using LangGraph

Customer Service Agent built using OpenAI Agents SDK

Travel Planning about Maldives Using Google ADK

Japan Cherry Blossom Travel Plans

Biggest Tech announcement of July 2025

HTML5 Canvas Freehand Drawing + Clear Button

Responsive Two-Column Photo Gallery with Hover Effect

Live Username & Email Validation Form

Responsive Navbar with Hamburger Menu (<600px)

Pure CSS Image Slider with Prev/Next Navigation

pytest tests for palindrome function

A* Pathfinding on Grid in Python

Two Sum Python Function Implementation

Flask To-Do List API Tutorial

Python Pygame Tetris Game Implementation

Closed-Form and Value of Recurrence Sequence

Total Surface Area of Cylinder (78π cm²)

Probability of two face cards drawn from deck

Integer solutions of 3x + 5y = 100

Bob wins exactly when \( n \equiv 0 \) or \( 2 \pmod{5} \); up to 2024 there are \(\boxed{809}\) such values.

Origin and Meaning of "Ride Shotgun"

Synonyms & Nuances of "Gregarious"

Meaning and Use of "Ubiquitous"

Counting overlapping “issi” in sentence

Counting Vowels in "Encyclopedia"

Bridge crossing minimum time and steps (A,B,C,D)

12 Coins Light Fake: 3-Weighing Identification Strategy

Two trains meeting time & location calculation

Ages of Emily & Derek: Algebra Solution

Number of Andrew’s sisters = N

Next.js 14 App with Routing & Server Components

Using TanStack Router with React and context7

Group and Sort Documents in MongoDB Aggregation

FastAPI CRUD API with Auth Using context7

Delete Rows by City Using PostgreSQL Credentials

2025 Renewable Energy Market Size Report (Summary & Drivers)

Most Populous U.S. State & Weather Alerts

Tavily BBC News Scraping MCP

2025 Renewable Energy Market Size Report (Executive Summary, Date, Drivers)

Most Populated U.S. State & Current Weather Alerts

HyperBrowser MCP Scrapping BBC News

Changes in Pull Request #1000 of apache/spark

Comments on Issue #519 in microsoft/vscode

Scrape the main text content from https://www.bbc....