Skip to main content

text model comparison

GPT-4.1 vs GPT-4.1 nano

GPT-4.1 and GPT-4.1 nano are both current text models, from OpenAI. GPT-4.1 nano is 95% cheaper per 1M input tokens than GPT-4.1, $0.10 vs $2. On Arena Text, GPT-4.1 scores 1415 Elo and GPT-4.1 nano 1322 Elo (Arena, measured October 28, 2026). Both accept 1,047,576 tokens of context.

Higher Arena Text
GPT-4.11415 Elo against 1322 Elo
Lower price per 1M input tokens
GPT-4.1 nano$0.10 against $2

Data verified November 3, 2026 · Dataset 2026-11-06

Share this

Side by side

GPT-4.1 and GPT-4.1 nano, line by line

Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.

FactGPT-4.1GPT-4.1 nano
Price
Price per 1M input tokens$2$0.10 (better)
Price per 1M output tokens$8$0.40 (better)
Independent benchmarks
Arena Text1415 Elo (#45 of 52) (better)1322 Elo (#52 of 52)
GPQA Diamond66.9% (#39 of 41) (better)48.9% (#41 of 41)
SimpleQA Verified31.1% (#33 of 38) (better)6% (#38 of 38)
FrontierMath Tiers 1-3 (v2)6% (#41 of 41)Not measured
Specs
ProviderOpenAIOpenAI
Release dateApril 14, 2025April 14, 2025
AccessAPI onlyAPI only
Context window1,047,576 tokens1,047,576 tokens
Max output32,768 tokens32,768 tokens
Inputtext, imagetext, image
Outputtexttext

Scores:Arena · 2026-11-03Epoch AI · 2026-11-03

Open both in the interactive comparison

Charts

Against every current text model

Where GPT-4.1 and GPT-4.1 nano land among the current models of their task, on every independent benchmark, on price and on context.

Where each stands

On Arena Text, GPT-4.1 ranks #45 and GPT-4.1 nano #52 of 52 current models. Each bar is the share of current models it beats: on score, price and context.

GPT-4.1 and GPT-4.1 nano among the current text models, one row per benchmark, price and context window.

Independent benchmarks

Arena Text

GPT-4.1:#45of 52

1,415 Elo · ahead of 14%

GPT-4.1 nano:#52of 52

1,322 Elo · ahead of 0%

GPQA Diamond

GPT-4.1:#39of 41

66.9% · ahead of 5%

GPT-4.1 nano:#41of 41

48.9% · ahead of 0%

FrontierMath Tiers 1-3 (v2)

GPT-4.1:#41of 41

6% · ahead of 0%

GPT-4.1 nano: Not scored

SimpleQA Verified

GPT-4.1:#33of 38

31.1% · ahead of 14%

GPT-4.1 nano:#38of 38

6% · ahead of 0%

Price and context

Price per 1M input tokens

GPT-4.1:#31of 58

$2 · cheaper than 26%

GPT-4.1 nano:#1of 58

$0.10 · cheaper than 96%

Price per 1M output tokens

GPT-4.1:#35of 58

$8 · cheaper than 40%

GPT-4.1 nano:#2of 58

$0.40 · cheaper than 98%

Context window

GPT-4.1:#24of 67

1.05M tokens · longer than 62%

GPT-4.1 nano:#24of 67

1.05M tokens · longer than 62%

Quality against price

Arena Text · measured October 28, 2026

GPT-4.1 scores 1,415 at $3.50; GPT-4.1 nano scores 1,322 at $0.175 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.

Quality against priceArena Text score against price for 44 text models, GPT-4.1 and GPT-4.1 nano marked.1,2501,3001,3501,4001,4501,5001,550$0.30$1$3$10MOST ATTRACTIVE QUADRANTMedian price $3Median 1,476Blended price per 1M tokens (3 input : 1 output), log scaleArena Text (Elo)GPT-4.1GPT-4.1 nano
Quality against price: the data
Arena Text score against price for 44 text models, GPT-4.1 and GPT-4.1 nano marked.
ModelProviderBlended price per 1M tokensArena Text (Elo)
Gemini 4 CarbonGoogle$41,528
Gemini 4 ArgonGoogle$41,520
Claude Opus 5.5Anthropic$81,509
Muse WonderMeta$81,507
Claude Fable 5Anthropic$201,504
Claude Fable 5.1Anthropic$201,504
Gemini 3.8 FlashGoogle$1.501,496
Muse Spark 1.3Meta$21,495
Claude Opus 5Anthropic$101,492
Kimi K3Moonshot Kimi$61,488
GPT-5.6 SolOpenAI$81,485
Gemini 3.6 FlashGoogle$31,483
GPT-5.5OpenAI$111,482
Claude Opus 4.8Anthropic$101,482
Qwen3.8-MaxAlibaba Qwen$31,482
GPT-6.1 SolOpenAI$41,481
GLM-5.3Z.ai$2.151,481
MiMo-V2.6-ProXiaomi MiMo$0.541,480
Claude Sonnet 5.5Anthropic$41,477
GLM-5.3-FlashZ.ai$0.241,477
GPT-6 AstraOpenAI$201,476
DeepSeek-V4.1-FlashDeepSeek$0.521,476
GPT-5.4OpenAI$5.631,475
Gemini 3 Flash PreviewGoogle$1.131,473
Grok 4.20xAI$1.561,472
GPT-5.6 TerraOpenAI$4.501,467
Grok 4.5xAI$31,465
DeepSeek-V4-ProDeepSeek$1.981,465
Claude Sonnet 5Anthropic$41,462
GPT-6 SolOpenAI$41,458
Gemini 3.5 Flash-LiteGoogle$0.851,456
Grok 4.6xAI$31,455
GPT-5.6 LunaOpenAI$0.451,453
MiMo-V2.6-FlashXiaomi MiMo$0.181,448
Step 5 PreviewStepFun$1.431,448
Grok 4.3xAI$1.561,442
GPT-6 LunaOpenAI$0.201,441
Grok 4.7xAI$31,441
Mistral Large 4Mistral AI$1.051,432
Claude Haiku 5.5Anthropic$0.201,425
GPT-4.1OpenAI$3.501,415
Solar Pro 4Upstage$0.521,388
GPT-4.1 miniOpenAI$0.701,383
GPT-4.1 nanoOpenAI$0.181,322

Cost

What each costs

Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.

The same work, priced

For 10M input and 2M output tokens, GPT-4.1 costs 20 times as much as GPT-4.1 nano, at each provider's listed rates.

What GPT-4.1 and GPT-4.1 nano cost for the same work, at the rates each provider lists.
  • 10M input and 2M output tokens

    GPT-4.1 costs 20× as much

    GPT-4.1
    $36
    GPT-4.1 nano
    $1.80
  • The same, with 9M of the input tokens cached

    GPT-4.1 costs 20× as much

    GPT-4.1
    $22.50
    GPT-4.1 nano
    $1.13
Workload or rateGPT-4.1GPT-4.1 nano
Example workloads
10M input and 2M output tokens$36$1.80 (better)
The same, with 9M of the input tokens cached$22.50$1.13 (better)
Other listed rates
1M input tokens, cached$0.50$0.025 (better)

Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.

Launch price $100, regular price $150

Book the cost audit

Verdict

When to choose each

GPT-4.1

Where it leads

  • Higher Arena Text score, 1415 Elo vs 1322 Elo
  • Higher GPQA Diamond score, 66.9% vs 48.9%
  • Higher SimpleQA Verified score, 31.1% vs 6%

Best for

  • Long-context API trials using text and image inputs

Watch out for

  • Not in the pinned LiveBench snapshot; its independent scores here come from Epoch AI's own GPQA Diamond, FrontierMath and SimpleQA Verified runs

GPT-4.1 nano

Where it leads

  • Lower input and output prices, $0.10 and $0.40 vs $2 and $8 per 1M tokens
  • Cheaper cached input, $0.025 vs $0.50 per 1M tokens

Best for

  • High-volume API screening at low published token prices

Watch out for

  • Not in the pinned LiveBench snapshot; its independent scores here come from Epoch AI's own GPQA Diamond, FrontierMath and SimpleQA Verified runs

From benchmark to production

Building on GPT-4.1 or GPT-4.1 nano?

Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.

AI Model Cost AuditLaunch price $100, regular price $150What the audit includes

FAQ

GPT-4.1 vs GPT-4.1 nano FAQ

Which is cheaper, GPT-4.1 or GPT-4.1 nano?

GPT-4.1 nano is 95% cheaper per 1M input tokens than GPT-4.1, $0.10 vs $2. For 10M input and 2M output tokens, GPT-4.1 costs $36 and GPT-4.1 nano $1.80 at standard rates.

Which is cheaper with prompt caching, GPT-4.1 or GPT-4.1 nano?

GPT-4.1 charges $0.50 per 1M cached input tokens, 75% below its standard input rate, and GPT-4.1 nano $0.025, 75% below. With 9M of 10M input tokens cached and 2M output tokens, GPT-4.1 costs $22.50 and GPT-4.1 nano $1.13.

Which scores higher on independent benchmarks, GPT-4.1 or GPT-4.1 nano?

GPT-4.1 leads on Arena Text, 1415 Elo to 1322 Elo; GPT-4.1 leads on GPQA Diamond, 66.9% to 48.9%; GPT-4.1 leads on SimpleQA Verified, 31.1% to 6%. Scores are independent evaluations, not either vendor's launch figures.

Which has the larger context window, GPT-4.1 or GPT-4.1 nano?

Both accept 1,047,576 tokens of context. Both return up to 32,768 tokens per response.

Production evaluation

Choosing between GPT-4.1 and GPT-4.1 nano?

Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • A head-to-head evaluation on your real workload
  • Routing between models by cost and difficulty