---
title: "Cheaper alternatives to GPT-4.1 · Undominated.ai"
canonical: https://undominated.ai/alternatives/openai__gpt-4.1/
description: "63 models score at least as high as GPT-4.1 and cost no more on a balanced workload. 9 give up nothing measurable; the other 54 name what they drop. Measured prices and independent scores."
---

# Cheaper alternatives to GPT-4.1 · Undominated.ai

> 63 models score at least as high as GPT-4.1 and cost no more on a balanced workload. 9 give up nothing measurable; the other 54 name what they drop. Measured prices and independent scores.

# Cheaper alternatives to GPT-4.1

OpenAI · LMArena 1382.3 · $3.50/M on a balanced workload · prices as of 2026-08-28

## 9 models are both better and cheaper, giving up nothing.

Of the 133 models carrying both an independent score and a published price at the same delivery mode, **63** score at least as high as GPT-4.1 and cost no more under at least one workload. **62** of them are genuinely cheaper; the rest match the price and win on score alone. **9** match or beat it on every capability we hold — context, maximum output, input modes, tool use and extended reasoning. **54** do not, and every row names what it drops.

Dominance is not a property of a model. It is a property of a model, a capability lens and a workload, and all three are named on every row. Scores are LMArena Elo, used under CC BY 4.0 from the official dataset; prices are blended per million tokens. A higher score is not a drop-in replacement.

This page is built from that comparison and nothing else. When no model is both better and cheaper than GPT-4.1, it is not generated.

## Where it holds

| Workload | GPT-4.1 $/M | Better and cheaper | With a trade |
| --- | --- | --- | --- |
| Balanced | $3.50 | 9 | 54 |
| Summarise | $1.87 | 9 | 54 |
| Chat | $3.95 | 7 | 52 |
| Code gen | $5.48 | 7 | 52 |
| Agentic | $2.01 | 9 | 53 |

Workload mixes are defined on the [methodology page](/methodology/). Cached input is priced at the cached rate, and reasoning tokens at the worse of the reasoning and output rates.

## What you would be replacing

| Intelligence | 1382.3 |
| --- | --- |
| Context window | 1.0M |
| Max output | 33K |
| Input modes | image, text, file |
| Tool use | yes |
| Extended reasoning | no |

A replacement has to clear every line above, not just the score. [Full record for GPT-4.1](/models/openai__gpt-4.1/).

## Better and cheaper, nothing given up 9

Each of these matches or beats GPT-4.1 on context, maximum output, input modes, tool use and reasoning, scores at least as high, and costs no more.

| # | Model | Intelligence | $/M | Holds under |
| --- | --- | --- | --- | --- |
| 1 | Gemini 3.7 Flash Google | 1490.2 +107.9 | $0.750 | Balanced −79% Summarise −81% Chat −78% Code gen −77% Agentic −80% |
| 2 | Gemini 3.5 Flash Google | 1482.6 +100.3 | $3.38 | Balanced −4% Summarise −20% Agentic −9% |
| 3 | Muse Spark 1.1 Meta | 1478.3 +96 | $2.00 | Balanced −43% Summarise −42% Chat −46% Code gen −46% Agentic −48% |
| 4 | Gemini 3.6 Flash Google | 1476.5 +94.2 | $1.50 | Balanced −57% Summarise −62% Chat −56% Code gen −54% Agentic −60% |
| 5 | Gemini 2.5 Pro Google | 1457.3 +75 | $3.44 | Balanced −2% Summarise −27% Agentic −6% |
| 6 | Gemini 3.5 Flash Lite Google | 1436.5 +54.2 | $0.850 | Balanced −76% Summarise −82% Chat −72% Code gen −71% Agentic −77% |
| 7 | GPT-5.6 Luna OpenAI | 1428.5 +46.2 | $0.450 | Balanced −87% Summarise −89% Chat −86% Code gen −86% Agentic −88% |
| 8 | Gemini 2.5 Flash Google | 1417.3 +35 | $0.850 | Balanced −76% Summarise −82% Chat −72% Code gen −71% Agentic −77% |
| 9 | Gemini 3.1 Flash Lite Preview Google | 1414.8 +32.5 | $0.563 | Balanced −84% Summarise −87% Chat −83% Code gen −82% Agentic −85% |

## Cheaper and higher-scoring, but you give something up 54

These score at least as high and cost no more on the two plotted axes, and lose something that is not on them. Read the last column before switching.

| Model | Intelligence | $/M | Holds under | What you give up |
| --- | --- | --- | --- | --- |
| Qwen3.8 Max Qwen | 1481.9 +99.6 | $3.00 | Balanced −14% Summarise −9% Chat −22% Code gen −22% Agentic −22% | 1.0M → 1.0M context no file input |
| GLM 5.3 Z.ai | 1476.9 +94.6 | $2.15 | Balanced −39% Summarise −35% Chat −43% Code gen −43% Agentic −42% | no image, file input |
| MiMo-V2.5-Pro Xiaomi | 1465 +82.7 | $0.544 | Balanced −84% Summarise −82% Chat −88% Code gen −88% Agentic −88% | no image, file input |
| GLM 5.2 Z.ai | 1465.4 +83.1 | $1.83 | Balanced −48% Summarise −44% Chat −51% Code gen −52% Agentic −50% | no image, file input |
| GLM 5.1 Z.ai | 1464.1 +81.8 | $1.94 | Balanced −45% Summarise −41% Chat −49% Code gen −49% Agentic −47% | 1.0M → 205K context no image, file input |
| Qwen3.7 Plus Qwen | 1456.2 +73.9 | $0.560 | Balanced −84% Summarise −84% Chat −84% Code gen −84% Agentic −84% | 1.0M → 1.0M context no file input |
| Kimi K2.6 Moonshot AI | 1455 +72.7 | $1.71 | Balanced −51% Summarise −53% Chat −51% Code gen −50% Agentic −53% | 1.0M → 262K context no file input |
| Grok 4.5 xAI | 1452.3 +70 | $3.00 | Balanced −14% Summarise −8% Chat −22% Code gen −22% Agentic −21% | 1.0M → 500K context |
| Kimi K2.5 Moonshot AI | 1445.2 +62.9 | $0.900 | Balanced −74% Summarise −77% Chat −73% Code gen −73% Agentic −75% | 1.0M → 262K context no file input |
| GLM 5 Z.ai | 1445.2 +62.9 | $0.930 | Balanced −73% Summarise −72% Chat −75% Code gen −75% Agentic −74% | 1.0M → 205K context no image, file input |
| Gemma 4 31B Google | 1441.7 +59.4 | $0.152 | Balanced −96% Summarise −95% Chat −95% Code gen −96% Agentic −95% | 1.0M → 262K context 33K → 16K max output no file input |
| Hy3 Tencent | 1441.2 +58.9 | $0.144 | Balanced −96% Summarise −96% Chat −96% Code gen −96% Agentic −96% | 1.0M → 262K context no image, file input |
| Qwen3.6 Max Preview Qwen | 1446.3 +64 | $2.31 | Balanced −34% Summarise −31% Chat −22% Code gen −25% Agentic −10% | 1.0M → 262K context no image, file input |
| Qwen3.8 27B Qwen | 1440.8 +58.5 | $0.956 | Balanced −73% Summarise −77% Chat −70% Code gen −69% Agentic −73% | 1.0M → 1.0M context no file input |
| GLM 4.6 Z.ai | 1439.8 +57.5 | $0.875 | Balanced −75% Summarise −75% Chat −75% Code gen −75% Agentic −76% | 1.0M → 205K context no image, file input |
| DeepSeek V4 Pro 0423 DeepSeek | 1439.2 +56.9 | $1.09 | Balanced −69% Summarise −63% Chat −75% Code gen −76% Agentic −74% | no image, file input |
| Qwen3.5 397B A17B Qwen | 1438.3 +56 | $0.877 | Balanced −75% Summarise −74% Chat −70% Code gen −72% Agentic −66% | 1.0M → 262K context no file input |
| Grok 4.6 xAI | 1443.7 +61.4 | $3.00 | Balanced −14% Summarise −5% Chat −20% Code gen −22% Agentic −15% | 1.0M → 500K context |
| Qwen3.6 Plus Qwen | 1436.8 +54.5 | $0.731 | Balanced −79% Summarise −78% Chat −75% Code gen −76% Agentic −72% | 1.0M → 1.0M context no file input |
| Inkling Thinking Machines | 1439.2 +56.9 | $1.73 | Balanced −51% Summarise −53% Chat −51% Code gen −50% Agentic −53% | no file input |
| Gemma 4 26B A4B Google | 1434.6 +52.3 | $0.138 | Balanced −96% Summarise −96% Chat −95% Code gen −96% Agentic −94% | 1.0M → 262K context 33K → 16K max output no file input |
| MiniMax M3 MiniMax | 1434.8 +52.5 | $0.525 | Balanced −85% Summarise −85% Chat −85% Code gen −85% Agentic −85% | no file input |
| GLM 4.7 Z.ai | 1435.3 +53 | $0.738 | Balanced −79% Summarise −80% Chat −79% Code gen −78% Agentic −79% | 1.0M → 205K context no image, file input |
| GPT-5.1 OpenAI | 1441.4 +59.1 | $3.44 | Balanced −2% Summarise −27% Agentic −6% | 1.0M → 400K context |
| GLM 5V Turbo Z.ai | 1436.8 +54.5 | $1.90 | Balanced −46% Summarise −43% Chat −49% Code gen −49% Agentic −48% | 1.0M → 203K context no file input |
| DeepSeek V4 Flash 0423 DeepSeek | 1431.6 +49.3 | $0.101 | Balanced −97% Summarise −96% Chat −98% Code gen −98% Agentic −97% | no image, file input |
| MiMo-V2.5 Xiaomi | 1427.3 +45 | $0.175 | Balanced −95% Summarise −94% Chat −96% Code gen −96% Agentic −96% | no file input |
| GLM 4.5 Z.ai | 1429.4 +47.1 | $1.00 | Balanced −71% Summarise −71% Chat −72% Code gen −72% Agentic −73% | 1.0M → 131K context no image, file input |
| R1 0528 DeepSeek | 1427.9 +45.6 | $0.912 | Balanced −74% Summarise −71% Chat −72% Code gen −73% Agentic −67% | 1.0M → 164K context no image, file input |
| DeepSeek V3.2 DeepSeek | 1424.6 +42.3 | $0.290 | Balanced −92% Summarise −88% Chat −93% Code gen −94% Agentic −90% | 1.0M → 164K context no image, file input |
| DeepSeek V3.2 Exp DeepSeek | 1424.4 +42.1 | $0.305 | Balanced −91% Summarise −85% Chat −92% Code gen −94% Agentic −86% | 1.0M → 164K context no image, file input |
| Qwen3 VL 235B A22B Instruct Qwen | 1420.9 +38.6 | $0.632 | Balanced −82% Summarise −86% Chat −78% Code gen −78% Agentic −80% | 1.0M → 262K context no file input |
| Qwen3 235B A22B Instruct 2507 Qwen | 1419.3 +37 | $0.205 | Balanced −94% Summarise −94% Chat −93% Code gen −93% Agentic −92% | 1.0M → 262K context 33K → 16K max output no image, file input |
| DeepSeek V3.1 Terminus DeepSeek | 1419.6 +37.3 | $0.453 | Balanced −87% Summarise −86% Chat −87% Code gen −87% Agentic −85% | 1.0M → 164K context no image, file input |
| Qwen3 Next 80B A3B Instruct Qwen | 1418.6 +36.3 | $0.350 | Balanced −90% Summarise −92% Chat −88% Code gen −87% Agentic −88% | 1.0M → 262K context no image, file input |
| DeepSeek V3.1 DeepSeek | 1419.1 +36.8 | $0.825 | Balanced −76% Summarise −68% Chat −75% Code gen −78% Agentic −64% | 1.0M → 164K context no image, file input |
| Qwen3.5-122B-A10B Qwen | 1417.9 +35.6 | $0.715 | Balanced −80% Summarise −81% Chat −75% Code gen −75% Agentic −73% | 1.0M → 262K context no file input |
| Mistral Medium 3.5 Mistral | 1420.9 +38.6 | $3.00 | Balanced −14% Summarise −4% Chat −1% Code gen −7% | 1.0M → 262K context |
| Qwen3 235B A22B Thinking 2507 Qwen | 1413.8 +31.5 | $0.748 | Balanced −79% Summarise −82% Chat −73% Code gen −73% Agentic −73% | 1.0M → 131K context no image, file input |
| Inkling Small Thinking Machines | 1411.7 +29.4 | $0.637 | Balanced −82% Summarise −79% Chat −84% Code gen −84% Agentic −82% | no file input |
| Qwen3 Max Qwen | 1412.7 +30.4 | $1.56 | Balanced −55% Summarise −60% Chat −53% Code gen −53% Agentic −56% | 1.0M → 262K context no image, file input |
| GPT-5.4 Mini OpenAI | 1412.1 +29.8 | $1.69 | Balanced −52% Summarise −60% Chat −48% Code gen −46% Agentic −55% | 1.0M → 400K context |
| Qwen3.5-27B Qwen | 1407.9 +25.6 | $0.536 | Balanced −85% Summarise −86% Chat −81% Code gen −81% Agentic −80% | 1.0M → 262K context no file input |
| MiniMax M2.7 MiniMax | 1405.3 +23 | $0.525 | Balanced −85% Summarise −85% Chat −85% Code gen −85% Agentic −85% | 1.0M → 205K context no image, file input |
| Step 3.5 Flash StepFun | 1403.8 +21.5 | $0.150 | Balanced −96% Summarise −94% Chat −95% Code gen −96% Agentic −94% | 1.0M → 262K context no image, file input |
| o3 OpenAI | 1409.2 +26.9 | $3.50 | Balanced same price Summarise same price Chat same price Code gen same price Agentic same price | 1.0M → 200K context |
| Qwen3.5-Flash Qwen | 1397.6 +15.3 | $0.114 | Balanced −97% Summarise −96% Chat −96% Code gen −97% Agentic −95% | 1.0M → 1.0M context no file input |
| Qwen3 VL 235B A22B Thinking Qwen | 1400.6 +18.3 | $1.30 | Balanced −63% Summarise −69% Chat −53% Code gen −53% Agentic −53% | 1.0M → 131K context no file input |
| GPT-5 OpenAI | 1405.6 +23.3 | $3.44 | Balanced −2% Summarise −27% Agentic −6% | 1.0M → 400K context |
| Qwen3.5-35B-A3B Qwen | 1395.6 +13.3 | $0.500 | Balanced −86% Summarise −84% Chat −84% Code gen −84% Agentic −80% | 1.0M → 262K context no file input |
| Grok 4.3 xAI | 1397.5 +15.2 | $1.56 | Balanced −55% Summarise −46% Chat −64% Code gen −65% Agentic −60% | 1.0M → 1.0M context |
| Claude Haiku 4.5 Anthropic | 1394.9 +12.6 | $2.00 | Balanced −43% Summarise −50% Chat −41% Code gen −39% Agentic −47% | 1.0M → 200K context |
| Qwen3 30B A3B Instruct 2507 Qwen | 1384.3 tie | $0.084 | Balanced −98% Summarise −97% Chat −97% Code gen −98% Agentic −97% | 1.0M → 262K context 33K → 32K max output no image, file input |
| GLM 4.5 Air Z.ai | 1382.8 tie | $0.310 | Balanced −91% Summarise −93% Chat −90% Code gen −90% Agentic −91% | 1.0M → 131K context no image, file input |

## What this compares, and what it leaves out

 - Quality is LMArena Elo, used under CC BY 4.0 from the official dataset. The 95% confidence interval on a difference between two scores is about ±10.68 points, so a gap smaller than that is marked *tie* rather than an improvement — see [significance bands](/significance/).
 - 188 further models at this delivery mode carry a price but no independent score. They are absent from the comparison in both directions — unrated is not a zero, and an unmeasured model is neither an alternative nor a worse buy.
 - Retired models are never offered as an alternative, and a model only competes against its own delivery mode: batch trades latency for price, so it is not a like-for-like swap.
 - Nothing here measures latency, throughput, rate limits or how a model behaves on your prompts. Two models with the same index score are not interchangeable.
 - The models that nothing beats on both axes are on the [value frontier](/frontier/), and every other model something cheaper beats is [listed here](/alternatives/).