LLM·Dex
Newsletter
ProprietaryOpenAImidtextvision

GPT-4.1

OpenAI's 2025 GPT-4.x refresh, long-context, fast, still widely deployed even after GPT-5.

Updated

Quick facts

Released
Apr 2025
Context
1M tokens
Output / 1M
$8.00 / 1M tokens
License
Proprietary

About GPT-4.1

GPT-4.1 was OpenAI's spring 2025 update to the GPT-4 line, with a 1M-token context window and significantly faster inference than GPT-4o. It remained the recommended pre-GPT-5 default and is still available via the API for migrations and parity testing.

Most production workloads have moved to GPT-5 mini or full, but GPT-4.1 sees continued use in workflows that were specifically tuned to its tokenizer and prompting style.

Benchmarks

Published scores from OpenAI's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval
90.6
Python coding pass@1
MMLU
86.2
Broad academic knowledge
GPQA
,
Graduate-level reasoning
SWE-bench
,
Real software-engineering tasks
  • MMLU86.2
  • HumanEval90.6

Capabilities

Strengths

  • 1M-token context window, strong for long-doc workloads
  • Mature SDK and tooling integrations
  • Reliable JSON-mode and function-calling

Tracked weaknesses

  • Superseded by GPT-5 line for most new workloads
  • Reasoning weaker than current frontier

Pricing

Per-million-token rates as published by OpenAI.

TierPriceNotes
Input$2.00 / 1M tokensTokens you send to the model
Output$8.00 / 1M tokensTokens the model generates
Context1M tokensMax combined input + output

Call GPT-4.1 from your code

Drop-in snippet for the OpenAI SDK. Set your API key in the environment and run.

typescript
import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "gpt-4-1",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

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

Compare GPT-4.1 with…

Frequently asked

  • How much does GPT-4.1 cost per million tokens?
    GPT-4.1 is priced at $2.00 / 1M tokens for input tokens and $8.00 / 1M tokens for output tokens via the official OpenAI API at the time of writing.
  • What is GPT-4.1's context window?
    GPT-4.1 supports a context window of 1M tokens with up to 32.8K output tokens per response.
  • Is GPT-4.1 open source?
    No. GPT-4.1 is a closed-weight model, you can use it via OpenAI's API but the model weights are not publicly downloadable.
  • When was GPT-4.1 released?
    GPT-4.1 was released on Apr 14, 2025 by OpenAI.
  • What is GPT-4.1's knowledge cutoff?
    GPT-4.1's training data has a knowledge cutoff of Jun 2024. For information after that date you'll need a tool-use or web-search wrapper.
Friday digest

Intelligence, distilled weekly.

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.