---
title: "Compare alternatives to GPT-4.1 Nano · Undominated.ai"
canonical: https://undominated.ai/alternatives/openai__gpt-4.1-nano/
description: "17 alternatives score at least as high as GPT-4.1 Nano and cost no more under at least one listed workload. 0 preserve recorded capabilities; 17 have named trade-offs."
---

# Compare alternatives to GPT-4.1 Nano · Undominated.ai

> 17 alternatives score at least as high as GPT-4.1 Nano and cost no more under at least one listed workload. 0 preserve recorded capabilities; 17 have named trade-offs.

# Alternatives to GPT-4.1 Nano

OpenAI · LMArena 1284.8 · $0.175/M on a balanced workload · prices as of 2026-10-06

 [Compare models](https://undominated.ai/compare/) Comparison context

Choose up to three standard models in Compare.

Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls.

## Every higher-scoring or cheaper alternative has a recorded capability loss.

Of the 144 models carrying both an independent score and a published price at the same delivery mode, **17** score at least as high as GPT-4.1 Nano and cost no more under at least one listed workload, with at least one of those dimensions improved. **17** have a recorded capability loss, named on every row.

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 only while a candidate improves score or price without worsening the other under a listed workload. When that comparison no longer holds, it is not generated.

## Where it holds

| Workload | GPT-4.1 Nano $/M | Recorded capabilities preserved | Recorded capability losses |
| --- | --- | --- | --- |
| Balanced | $0.175 | 0 | 16 |
| Summarise | $0.094 | 0 | 13 |
| Chat | $0.198 | 0 | 16 |
| Code gen | $0.274 | 0 | 16 |
| Agentic | $0.100 | 0 | 13 |

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 | 1284.8 |
| --- | --- |
| Context window | 1M |
| Max output | 32K |
| Input modes | image, text, file |
| Tool use | yes |
| Extended reasoning | no |

Preserving recorded capabilities requires matching or beating these fields. [Full record for GPT-4.1 Nano](/models/openai__gpt-4.1-nano/), or [check GPT-4.1 Nano against the whole catalogue](/check/openai__gpt-4.1-nano/).

## Alternatives with recorded capability losses 17

These improve score or price without worsening the other under the listed workloads, but reduce at least one recorded capability. Read the last column before switching.

| Model | Intelligence | $/M | Holds under | Recorded capability loss |
| --- | --- | --- | --- | --- |
| [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) Xiaomi | 1456.4 +171.6 | $0.175 | Balanced same price Chat −22% Code gen −22% Agentic −21% | no file input |
| [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) Google | 1433.9 +149.1 | $0.127 | Balanced −28% Summarise −26% Chat −24% Code gen −25% Agentic −20% | 1M → 262K context no file input |
| [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) DeepSeek | 1432.1 +147.3 | $0.113 | Balanced −36% Summarise −21% Chat −47% Code gen −50% Agentic −40% | no image, file input |
| [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) Xiaomi | 1427.5 +142.7 | $0.175 | Balanced same price Chat −22% Code gen −22% Agentic −21% | no file input |
| [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) StepFun | 1403 +118.2 | $0.150 | Balanced −14% Chat −9% Code gen −20% | 1M → 262K context no image, file input |
| [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) Qwen | 1397 +112.2 | $0.114 | Balanced −35% Summarise −20% Chat −28% Code gen −34% Agentic −6% | 1M → 1M context no file input |
| [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) Qwen | 1384.1 +99.3 | $0.143 | Balanced −19% Chat −12% Code gen −21% | 1M → 262K context no image, file input |
| [gpt-oss-120b](/models/openai__gpt-oss-120b/) OpenAI | 1365.4 +80.6 | $0.065 | Balanced −63% Summarise −60% Chat −56% Code gen −58% Agentic −49% | 1M → 131K context no image, file input |
| [Gemma 3 27B](/models/google__gemma-3-27b-it/) Google | 1357.8 +73 | $0.100 | Balanced −43% Summarise −10% Chat −43% Code gen −53% Agentic −8% | 1M → 131K context no file input |
| [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) Z.ai | 1350.9 +66.1 | $0.145 | Balanced −17% Summarise −33% Chat −8% Code gen −5% Agentic −19% | 1M → 200K context no image, file input |
| [Qwen3 32B](/models/qwen__qwen3-32b/) Qwen | 1340.1 +55.3 | $0.130 | Balanced −26% Summarise −4% Chat −19% Code gen −27% | 1M → 131K context 33K → 16K max output no image, file input |
| [Gemma 3 12B](/models/google__gemma-3-12b-it/) Google | 1334.2 +49.4 | $0.075 | Balanced −57% Summarise −41% Chat −54% Code gen −60% Agentic −35% | 1M → 131K context 33K → 16K max output no file input |
| [GPT-5 Nano](/models/openai__gpt-5-nano/) OpenAI | 1320 +35.2 | $0.138 | Balanced −21% Summarise −42% Chat −11% Code gen −6% Agentic −25% | 1M → 400K context |
| [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) IBM | 1317.8 +33 | $0.108 | Balanced −39% Summarise −39% Chat −38% Code gen −38% Agentic −39% | 1M → 131K context no image, file input |
| [Gemma 3 4B](/models/google__gemma-3-4b-it/) Google | 1290.8 tie | $0.063 | Balanced −64% Summarise −44% Chat −65% Code gen −71% Agentic −43% | 1M → 131K context 33K → 16K max output no file input no tool use |
| [gpt-oss-20b](/models/openai__gpt-oss-20b/) OpenAI | 1287.7 tie | $0.036 | Balanced −79% Summarise −80% Chat −78% Code gen −78% Agentic −77% | 1M → 131K context no image, file input |
| [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) DeepSeek | 1462.5 +177.7 | $0.067 summarise | Summarise −29% | no 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 ±10.47 points, so a gap smaller than that is marked *tie* rather than an improvement — see [significance bands](/significance/).
 - 204 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.
 - Models with no higher-scoring or cheaper alternative that is no worse on the other axis are on the [value frontier](/frontier/). Models with such an alternative are [listed here](/alternatives/).

## Continue your investigation

 - [Check requirements](/check/)
- [Compare exact differences](/compare/)
- [Set a quality floor](/cheapest-at/)
- [Inspect tier boundaries](/cliffs/)