How much does GPT-4.1 cost?

GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens on standard pricing; other tiers (Standard, Batch, Fast (Priority)) are also available. A workload of 20M input and 5M output tokens a month is about $80.

What is the context length of GPT-4.1?

GPT-4.1 accepts up to 1,047,576 tokens (1M) of input and can return up to 32,768 tokens in one response.

Does GPT-4.1 support tool calling and structured outputs?

Yes, GPT-4.1 supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Deterministic seed, Prompt caching.

What inputs and outputs does GPT-4.1 support?

GPT-4.1 accepts Image, Text, PDF as input and produces Text as output.

Which providers serve GPT-4.1?

GPT-4.1 is available from 3 API providers: Azure, OpenAI, Azure. Prices can differ by provider.

When was GPT-4.1 released?

GPT-4.1 was released by OpenAI in 2025-04.

GPT-4.1

gpt-4.1

API Provider site

Non-reasoning GPT-4.1 with a 1M-token context window, strong at instruction following and coding. Built by OpenAI.

Prices updated recently

Input price

$2.00

per 1M tokens · Standard

Output price

$8.00

per 1M tokens · Standard

Input limit

tokens

Output limit

33K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF

Compare

GPT-4.1 price history

12 price records since 4/1/2026 · 10 changes

GPT-4.1 cost calculator

Input20M tokens

Output5M tokens

$80/month

Standard pricing

Overview

What is GPT-4.1?

GPT-4.1 is a text & reasoning and code & slms and vision model from OpenAI. Non-reasoning GPT-4.1 with a 1M-token context window, strong at instruction following and coding. Its 1M context window and $2.00 input price make it a candidate for quality-focused production applications.

Code generationAgent workflowsImage understandingDocument analysis

Benchmarks

GPT-4.1 benchmarks & speed

How GPT-4.1 scores on standardized evaluations, and where it lands among every model we track.

12.7

Intelligence Index

Better than 32% of 153 models

166tok/s

Output speed

Better than 81% of 119 models

1029

DesignArena Elo

Better than 11% of 81 models

Reasoning

GPQA Diamond

66.6%

Graduate-level scientific reasoning · top 74%

HLE

4.2%

Humanity's Last Exam · top 88%

Latency & design

Time to first token: 0.83s
DesignArena win rate: 50.9%
Design battles judged: 1,747

Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.

Rates

GPT-4.1 pricing

Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

Input · Standard

$2.00

Per 1M tokens

Cached input · Standard

$0.50

Per 1M tokens

Capabilities

GPT-4.1 Tools

Tools available when using GPT-4.1 through supported provider APIs.

Function calling

Supported

Structured outputs

Supported

JSON mode

Supported

Reasoning

Not supported

Built-in web search

Not supported

Log probabilities

Not supported

Deterministic seed

Supported

Parallel tool calls

Not supported

Prompt caching

Supported

Where to run it

GPT-4.1 API providers

3 providers serve GPT-4.1. Prices are per 1M tokens; uptime is the last 24 hours.

Provider	Input	Output	Cached	Context	Uptime
Azure	$2.00	$8.00	$0.50	1M	99.91%
OpenAI	$2.00	$8.00	$0.50	1M	99.9%
Azure	$2.20	$8.80	$0.55	1M	100%

Azure

Input: $2.00
Output: $8.00
Cached: $0.50
Context: 1M
Uptime: 99.91%

OpenAI

Input: $2.00
Output: $8.00
Cached: $0.50
Context: 1M
Uptime: 99.9%

Azure

Input: $2.20
Output: $8.80
Cached: $0.55
Context: 1M
Uptime: 100%

Strengths and limitations

Strengths

Measured results (AA Intelligence 12.7 · DesignArena Elo 1029 · Arena Elo 1200 · MMLU-Pro 73.6%) position it for demanding production work.
1M context supports large documents, repositories and extended conversations.
Supports text & reasoning and code & slms and vision workloads in one model.

Limitations

Generated tokens cost 4× more than input tokens, which matters for verbose responses.
Large context capacity does not guarantee consistent retrieval across the entire prompt.
Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

Same provider

More models from OpenAI

View provider →

GPT-3.5 Turbo

OpenAI

16K

$0.50 in · $1.50 out

View model

GPT-3.5 Turbo (older v0613)

OpenAI

$1.00 in · $2.00 out

View model

GPT-3.5 Turbo 16k

OpenAI

16K

$3.00 in · $4.00 out

View model

GPT-3.5 Turbo Instruct

OpenAI

$1.50 in · $2.00 out

View model

Peer set

Alternatives to GPT-4.1

GPT-4o

OpenAI

128K

$2.50 in · $10 out

Compare side-by-side

Claude Sonnet 4

Anthropic

200K

$3.00 in · $15 out

Compare side-by-side

Gemini 2.5 Pro

Google

$1.25 in · $10 out

Compare side-by-side

Frequently asked questions about GPT-4.1

GPT-4.1 is a text & reasoning and code & slms and vision model from OpenAI. Non-reasoning GPT-4.1 with a 1M-token context window, strong at instruction following and coding.