GPT-4.1 API

Try this model

GPT-4.1 is OpenAI's large-context language model with up to 1M token input and improved instruction following.

Modalities: Text, ImageText
In / Out price: $2/$8per 1M
Context window: 1.05M tokens
Released: Apr 14, 2025

GPT-4.1 overview

GPT-4.1 by OpenAI

GPT-4.1 advanced coding-focused AI with million-token context and superior instruction following.

GPT-4.1 specs

Model ID: openai/gpt-4.1-2025-04-14
Developer: OpenAI
Context window: 1,047,576 tokens
Max output: 32,768 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

GPT-4.1 Description

GPT-4.1 is OpenAI's advanced large language model designed with significant improvements in coding capabilities, instruction following, and long context processing. The model represents a substantial step forward from GPT-4o, offering enhanced performance while maintaining a lower cost profile than GPT-4.5. GPT-4.1 excels particularly in software engineering tasks, with optimizations for real-world developer use cases including frontend coding, cleaner code editing, and precise instruction adherence.

Context Window and Token Capacity

GPT-4.1 processes input contexts of up to 1,047,576 tokens (approximately 750,000 words). The model generates outputs of up to 32,768 tokens in a single response.

All training data for GPT-4.1 extends to May 31, 2024, which serves as its knowledge cutoff date.

Performance Benchmarks

SWE-bench Verified: 52-54.6% (21.4% improvement over GPT-4o)
Instruction Following (IFEval): 87.4% (6.4% improvement over GPT-4o)
Long Context Reasoning (OpenAI-MRCR): 84% accuracy with 8,000 tokens, degrading to 50% with 1 million tokens
Graph Reasoning (Graphwalks): 61.7% (19.7% improvement over GPT-4o)
Multi-challenge Benchmark: 38.3% (10.5% improvement over GPT-4o)

Programming and Software Development

GPT-4.1 delivers enhanced frontend coding with significantly fewer unnecessary edits. The model provides improved code refactoring and debugging capabilities for complex software projects. It follows programming best practices with superior accuracy compared to previous models. GPT-4.1 generates optimized diffs through extensive training on recommended formats. The system supports advanced agentic development workflows for autonomous coding tasks. It achieves state-of-the-art performance across standard coding benchmarks, particularly in practical software engineering tasks.

Long Context Processing

GPT-4.1 processes and reasons over documents containing up to 1 million tokens with maintained coherence. The model effectively retrieves specific information from large corpuses even when relevant data is deeply embedded. It analyzes entire codebases at once, maintaining context across multiple files and functions. GPT-4.1 handles multi-document analysis with improved accuracy for complex research and legal applications. The system is optimized for XML-style delimiters that enhance structure and information retention in long-context inputs.

Instruction Following

GPT-4.1 adheres precisely to explicit formatting instructions with higher consistency than previous models. The system handles negative instructions (what not to do) with improved accuracy and reliability. It performs multi-step ordered instructions with enhanced sequential understanding and context retention. GPT-4.1 executes ranking and sorting tasks with greater accuracy based on specified criteria. The model interprets prompts more literally, which provides greater control but requires more explicit instructions from users.

Use cases

AI pair programming and software development assistance
Technical documentation generation and automated report writing
Multimodal content creation and analysis
Complex customer support and conversational AI
Research applications requiring advanced reasoning and long-context understanding

Capabilities

Function calling
Streaming
Structured outputs
Reasoning

GPT-4.1 benchmarks by Artificial Analysis

See how GPT-4.1 compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#37 / 219185Output tokens / second Latency#37 / 2160.85Seconds to first token Humanity's Last Exam#386 / 4584.2%Score GPQA Diamond#241 / 43966.6%Score

Speed

Output tokens / second

Benchmark results

Compare 17 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

GPT-4.1 API pricing

GPT-4.1 pricing in US dollars
Usage	Price	Unit
Input	$2	1M tokens
Output	$8	1M tokens
Cached input	$0.5	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

GPT-4.1 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
GPT-4.1	$2	$8
GPT-6 Luna	$0.1	$0.5
GPT-6.1 Terra	$1	$5
GPT-6.1 Sol	$2	$10
GPT-6.1 Terra Pro	$2.12	$10.58

How to use the GPT-4.1 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-4.1-2025-04-14",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "openai/gpt-4.1-2025-04-14",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "openai/gpt-4.1-2025-04-14",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

GPT-4.1 FAQ

What is the context window of GPT-4.1?

GPT-4.1 has a 1,047,576 tokens context window and can return up to 32,768 tokens.

What inputs and outputs does GPT-4.1 support?

GPT-4.1 takes image, text as input and returns text.

What is the model ID for GPT-4.1?

Use openai/gpt-4.1-2025-04-14 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was GPT-4.1 released?

GPT-4.1 became available on August 7, 2025.

How much does GPT-4.1 cost?

GPT-4.1 costs $2 input and $8 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does GPT-4.1 support streaming?

Yes, GPT-4.1 can stream responses as they are generated.

Can GPT-4.1 read images?

Yes, GPT-4.1 accepts image input alongside text.

Who created GPT-4.1?

GPT-4.1 was built by OpenAI.

Start building with GPT-4.1

Get API key

GPT-4.1 API

openai/gpt-4.1-2025-04-14

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-4.1-2025-04-14",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "openai/gpt-4.1-2025-04-14",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "openai/gpt-4.1-2025-04-14",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

GPT-4.1 API

GPT-4.1 overview

GPT-4.1 by OpenAI

GPT-4.1 specs

GPT-4.1 Description

Context Window and Token Capacity

Performance Benchmarks

Programming and Software Development

Long Context Processing

Instruction Following

Use cases

Capabilities

GPT-4.1 benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

GPT-4.1 API pricing

GPT-4.1 vs other models: token prices

How to use the GPT-4.1 API

Build with your agent

1Get your API key

2Make your first request

Related articles

GPT-4.1 FAQ

Start building with GPT-4.1

GPT-4.1 API

Build with your agent

1Get your API key

2Make your first request

GPT-4.1 API

GPT-4.1 overview

GPT-4.1 by OpenAI

GPT-4.1 specs

GPT-4.1 Description

Context Window and Token Capacity

Performance Benchmarks

Programming and Software Development

Long Context Processing

Instruction Following

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

GPT-4.1 API pricing

GPT-4.1 vs other models: token prices

How to use the GPT-4.1 API

Build with your agent

1Get your API key

2Make your first request

Models similar to GPT-4.1

GPT-6.1 Terra

GPT-6.1 Terra Pro

GPT-6.1 Sol

Claude Sonnet 5.5

Claude Sonnet 5

Gemini 3.1 Pro

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

GPT-4.1 FAQ

Start building with GPT-4.1