---
title: "Cheaper alternatives to GPT-4o (2024-08-06) · Undominated.ai"
canonical: https://undominated.ai/alternatives/openai__gpt-4o-2024-08-06/
description: "103 models score at least as high as GPT-4o (2024-08-06) and cost no more on a balanced workload. 33 give up nothing measurable; the other 70 name what they drop. Measured prices and independent scores."
---

# Cheaper alternatives to GPT-4o (2024-08-06) · Undominated.ai

> 103 models score at least as high as GPT-4o (2024-08-06) and cost no more on a balanced workload. 33 give up nothing measurable; the other 70 name what they drop. Measured prices and independent scores.

# Cheaper alternatives to GPT-4o (2024-08-06)

OpenAI · LMArena 1282.7 · $4.38/M on a balanced workload · prices as of 2026-08-28

## 33 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, **103** score at least as high as GPT-4o (2024-08-06) and cost no more under at least one workload. **33** match or beat it on every capability we hold — context, maximum output, input modes, tool use and extended reasoning. **70** 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-4o (2024-08-06), it is not generated.

## Where it holds

| Workload | GPT-4o (2024-08-06) $/M | Better and cheaper | With a trade |
| --- | --- | --- | --- |
| Balanced | $4.38 | 29 | 70 |
| Summarise | $2.52 | 33 | 70 |
| Chat | $5.13 | 29 | 70 |
| Code gen | $6.90 | 29 | 70 |
| Agentic | $2.88 | 32 | 70 |

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 | 1282.7 |
| --- | --- |
| Context window | 128K |
| Max output | 16K |
| Input modes | text, image, file |
| Tool use | yes |
| Extended reasoning | no |

A replacement has to clear every line above, not just the score. [Full record for GPT-4o (2024-08-06)](/models/openai__gpt-4o-2024-08-06/).

## Better and cheaper, nothing given up 33

Each of these matches or beats GPT-4o (2024-08-06) 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 +207.5 | $0.750 | Balanced −83% Summarise −86% Chat −83% Code gen −82% Agentic −86% |
| 2 | Gemini 3.5 Flash Google | 1482.6 +199.9 | $3.38 | Balanced −23% Summarise −41% Chat −20% Code gen −15% Agentic −37% |
| 3 | Muse Spark 1.1 Meta | 1478.3 +195.6 | $2.00 | Balanced −54% Summarise −57% Chat −59% Code gen −57% Agentic −64% |
| 4 | Gemini 3.6 Flash Google | 1476.5 +193.8 | $1.50 | Balanced −66% Summarise −72% Chat −66% Code gen −64% Agentic −72% |
| 5 | Gemini 2.5 Pro Google | 1457.3 +174.6 | $3.44 | Balanced −21% Summarise −46% Chat −14% Code gen −7% Agentic −34% |
| 6 | Grok 4.5 xAI | 1452.3 +169.6 | $3.00 | Balanced −31% Summarise −32% Chat −40% Code gen −38% Agentic −45% |
| 7 | GPT-5.6 Sol OpenAI | 1454.2 +171.5 | $4.00 | Balanced −9% Summarise −25% Chat −9% Code gen −4% Agentic −26% |
| 8 | Grok 4.6 xAI | 1443.7 +161 | $3.00 | Balanced −31% Summarise −30% Chat −39% Code gen −38% Agentic −41% |
| 9 | Gemini 3.5 Flash Lite Google | 1436.5 +153.8 | $0.850 | Balanced −81% Summarise −87% Chat −79% Code gen −77% Agentic −84% |
| 10 | GPT-5.1 OpenAI | 1441.4 +158.7 | $3.44 | Balanced −21% Summarise −46% Chat −14% Code gen −7% Agentic −34% |
| 11 | Claude Sonnet 5 Anthropic | 1442.3 +159.6 | $4.00 | Balanced −9% Summarise −25% Chat −9% Code gen −4% Agentic −26% |
| 12 | GPT-5.6 Luna OpenAI | 1428.5 +145.8 | $0.450 | Balanced −90% Summarise −92% Chat −89% Code gen −89% Agentic −92% |
| 13 | Gemini 2.5 Flash Google | 1417.3 +134.6 | $0.850 | Balanced −81% Summarise −87% Chat −79% Code gen −77% Agentic −84% |
| 14 | Mistral Medium 3.5 Mistral | 1420.9 +138.2 | $3.00 | Balanced −31% Summarise −29% Chat −24% Code gen −26% Agentic −17% |
| 15 | Gemini 3.1 Flash Lite Preview Google | 1414.8 +132.1 | $0.563 | Balanced −87% Summarise −90% Chat −87% Code gen −86% Agentic −89% |
| 16 | GPT-5.4 Mini OpenAI | 1412.1 +129.4 | $1.69 | Balanced −61% Summarise −70% Chat −60% Code gen −57% Agentic −68% |
| 17 | o3 OpenAI | 1409.2 +126.5 | $3.50 | Balanced −20% Summarise −26% Chat −23% Code gen −21% Agentic −30% |
| 18 | GPT-5 OpenAI | 1405.6 +122.9 | $3.44 | Balanced −21% Summarise −46% Chat −14% Code gen −7% Agentic −34% |
| 19 | Grok 4.3 xAI | 1397.5 +114.8 | $1.56 | Balanced −64% Summarise −60% Chat −72% Code gen −72% Agentic −72% |
| 20 | Claude Haiku 4.5 Anthropic | 1394.9 +112.2 | $2.00 | Balanced −54% Summarise −63% Chat −55% Code gen −52% Agentic −63% |
| 21 | GPT-4.1 OpenAI | 1382.3 +99.6 | $3.50 | Balanced −20% Summarise −26% Chat −23% Code gen −21% Agentic −30% |
| 22 | GPT-5 Mini OpenAI | 1373.4 +90.7 | $0.688 | Balanced −84% Summarise −89% Chat −83% Code gen −81% Agentic −87% |
| 23 | GPT-5.4 Nano OpenAI | 1372.8 +90.1 | $0.463 | Balanced −89% Summarise −92% Chat −89% Code gen −88% Agentic −91% |
| 24 | Nova 2 Lite Amazon | 1362.2 +79.5 | $0.850 | Balanced −81% Summarise −84% Chat −77% Code gen −77% Agentic −78% |
| 25 | o4 Mini OpenAI | 1352.5 +69.8 | $1.93 | Balanced −56% Summarise −59% Chat −58% Code gen −56% Agentic −62% |
| 26 | GPT-4.1 Mini OpenAI | 1340.5 +57.8 | $0.700 | Balanced −84% Summarise −85% Chat −85% Code gen −84% Agentic −86% |
| 27 | GPT-5 Nano OpenAI | 1320.3 +37.6 | $0.138 | Balanced −97% Summarise −98% Chat −97% Code gen −96% Agentic −97% |
| 28 | GPT-4o-mini (2024-07-18) OpenAI | 1286.6 tie | $0.263 | Balanced −94% Summarise −94% Chat −94% Code gen −94% Agentic −94% |
| 29 | GPT-4.1 Nano OpenAI | 1284.8 tie | $0.175 | Balanced −96% Summarise −96% Chat −96% Code gen −96% Agentic −97% |
| 30 | Gemini 3.1 Pro Preview Google | 1479.5 +196.8 | $1.99 summarise | Summarise −21% Agentic −16% |
| 31 | GPT-5.4 OpenAI | 1469.6 +186.9 | $2.48 summarise | Summarise −1% |
| 32 | GPT-5.6 Terra OpenAI | 1446 +163.3 | $1.99 summarise | Summarise −21% Agentic −16% |
| 33 | GPT-5.2 OpenAI | 1416.5 +133.8 | $1.91 summarise | Summarise −24% Agentic −8% |

## Cheaper and higher-scoring, but you give something up 70

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 +199.2 | $3.00 | Balanced −31% Summarise −32% Chat −40% Code gen −38% Agentic −46% | no file input |
| GLM 5.3 Z.ai | 1476.9 +194.2 | $2.15 | Balanced −51% Summarise −51% Chat −56% Code gen −55% Agentic −59% | no image, file input |
| MiMo-V2.5-Pro Xiaomi | 1465 +182.3 | $0.544 | Balanced −88% Summarise −87% Chat −91% Code gen −90% Agentic −92% | no image, file input |
| GLM 5.2 Z.ai | 1465.4 +182.7 | $1.83 | Balanced −58% Summarise −59% Chat −63% Code gen −62% Agentic −65% | no image, file input |
| GLM 5.1 Z.ai | 1464.1 +181.4 | $1.94 | Balanced −56% Summarise −56% Chat −60% Code gen −59% Agentic −63% | no image, file input |
| Qwen3.7 Plus Qwen | 1456.2 +173.5 | $0.560 | Balanced −87% Summarise −88% Chat −88% Code gen −87% Agentic −89% | no file input |
| Kimi K2.6 Moonshot AI | 1455 +172.3 | $1.71 | Balanced −61% Summarise −65% Chat −62% Code gen −61% Agentic −67% | no file input |
| Kimi K2.5 Moonshot AI | 1445.2 +162.5 | $0.900 | Balanced −79% Summarise −83% Chat −79% Code gen −78% Agentic −83% | no file input |
| GLM 5 Z.ai | 1445.2 +162.5 | $0.930 | Balanced −79% Summarise −79% Chat −81% Code gen −80% Agentic −82% | no image, file input |
| Gemma 4 31B Google | 1441.7 +159 | $0.152 | Balanced −97% Summarise −96% Chat −97% Code gen −97% Agentic −96% | no file input |
| Qwen3.6 Max Preview Qwen | 1446.3 +163.6 | $2.31 | Balanced −47% Summarise −49% Chat −40% Code gen −40% Agentic −38% | no image, file input |
| Hy3 Tencent | 1441.2 +158.5 | $0.144 | Balanced −97% Summarise −97% Chat −97% Code gen −97% Agentic −97% | no image, file input |
| Qwen3.8 27B Qwen | 1440.8 +158.1 | $0.956 | Balanced −78% Summarise −83% Chat −77% Code gen −76% Agentic −81% | no file input |
| GLM 4.6 Z.ai | 1439.8 +157.1 | $0.875 | Balanced −80% Summarise −82% Chat −81% Code gen −80% Agentic −83% | no image, file input |
| DeepSeek V4 Pro 0423 DeepSeek | 1439.2 +156.5 | $1.09 | Balanced −75% Summarise −73% Chat −81% Code gen −81% Agentic −82% | no image, file input |
| Qwen3.5 397B A17B Qwen | 1438.3 +155.6 | $0.877 | Balanced −80% Summarise −81% Chat −77% Code gen −77% Agentic −76% | no file input |
| Inkling Thinking Machines | 1439.2 +156.5 | $1.73 | Balanced −61% Summarise −65% Chat −62% Code gen −60% Agentic −67% | no file input |
| Qwen3.6 Plus Qwen | 1436.8 +154.1 | $0.731 | Balanced −83% Summarise −84% Chat −81% Code gen −81% Agentic −80% | no file input |
| Gemma 4 26B A4B Google | 1434.6 +151.9 | $0.138 | Balanced −97% Summarise −97% Chat −97% Code gen −97% Agentic −96% | no file input |
| GLM 4.7 Z.ai | 1435.3 +152.6 | $0.738 | Balanced −83% Summarise −85% Chat −84% Code gen −83% Agentic −86% | no image, file input |
| MiniMax M3 MiniMax | 1434.8 +152.1 | $0.525 | Balanced −88% Summarise −89% Chat −89% Code gen −88% Agentic −90% | no file input |
| GLM 5V Turbo Z.ai | 1436.8 +154.1 | $1.90 | Balanced −57% Summarise −58% Chat −60% Code gen −59% Agentic −64% | no file input |
| DeepSeek V4 Flash 0423 DeepSeek | 1431.6 +148.9 | $0.101 | Balanced −98% Summarise −97% Chat −98% Code gen −98% Agentic −98% | no image, file input |
| GLM 4.5 Z.ai | 1429.4 +146.7 | $1.00 | Balanced −77% Summarise −79% Chat −79% Code gen −78% Agentic −81% | no image, file input |
| MiMo-V2.5 Xiaomi | 1427.3 +144.6 | $0.175 | Balanced −96% Summarise −96% Chat −97% Code gen −97% Agentic −97% | no file input |
| R1 0528 DeepSeek | 1427.9 +145.2 | $0.912 | Balanced −79% Summarise −79% Chat −78% Code gen −79% Agentic −77% | no image, file input |
| DeepSeek V3.2 DeepSeek | 1424.6 +141.9 | $0.290 | Balanced −93% Summarise −91% Chat −95% Code gen −95% Agentic −93% | no image, file input |
| DeepSeek V3.2 Exp DeepSeek | 1424.4 +141.7 | $0.305 | Balanced −93% Summarise −89% Chat −94% Code gen −95% Agentic −90% | no image, file input |
| Qwen3 VL 235B A22B Instruct Qwen | 1420.9 +138.2 | $0.632 | Balanced −86% Summarise −90% Chat −83% Code gen −82% Agentic −86% | no file input |
| Qwen3 235B A22B Instruct 2507 Qwen | 1419.3 +136.6 | $0.205 | Balanced −95% Summarise −96% Chat −95% Code gen −95% Agentic −94% | no image, file input |
| DeepSeek V3.1 Terminus DeepSeek | 1419.6 +136.9 | $0.453 | Balanced −90% Summarise −89% Chat −90% Code gen −90% Agentic −90% | no image, file input |
| Qwen3 Next 80B A3B Instruct Qwen | 1418.6 +135.9 | $0.350 | Balanced −92% Summarise −94% Chat −90% Code gen −90% Agentic −92% | no image, file input |
| DeepSeek V3.1 DeepSeek | 1419.1 +136.4 | $0.825 | Balanced −81% Summarise −76% Chat −81% Code gen −82% Agentic −75% | no image, file input |
| Qwen3.5-122B-A10B Qwen | 1417.9 +135.2 | $0.715 | Balanced −84% Summarise −86% Chat −81% Code gen −80% Agentic −82% | no file input |
| Qwen3 235B A22B Thinking 2507 Qwen | 1413.8 +131.1 | $0.748 | Balanced −83% Summarise −87% Chat −79% Code gen −79% Agentic −81% | no image, file input |
| Inkling Small Thinking Machines | 1411.7 +129 | $0.637 | Balanced −85% Summarise −85% Chat −87% Code gen −87% Agentic −88% | no file input |
| Qwen3 Max Qwen | 1412.7 +130 | $1.56 | Balanced −64% Summarise −70% Chat −64% Code gen −62% Agentic −70% | no image, file input |
| Qwen3.5-27B Qwen | 1407.9 +125.2 | $0.536 | Balanced −88% Summarise −90% Chat −86% Code gen −85% Agentic −86% | no file input |
| MiniMax M2.7 MiniMax | 1405.3 +122.6 | $0.525 | Balanced −88% Summarise −89% Chat −89% Code gen −88% Agentic −90% | no image, file input |
| Step 3.5 Flash StepFun | 1403.8 +121.1 | $0.150 | Balanced −97% Summarise −96% Chat −96% Code gen −97% Agentic −95% | no image, file input |
| Qwen3 VL 235B A22B Thinking Qwen | 1400.6 +117.9 | $1.30 | Balanced −70% Summarise −77% Chat −64% Code gen −63% Agentic −67% | no file input |
| Qwen3.5-Flash Qwen | 1397.6 +114.9 | $0.114 | Balanced −97% Summarise −97% Chat −97% Code gen −97% Agentic −97% | no file input |
| Qwen3.5-35B-A3B Qwen | 1395.6 +112.9 | $0.500 | Balanced −89% Summarise −88% Chat −87% Code gen −88% Agentic −86% | no file input |
| Qwen3 30B A3B Instruct 2507 Qwen | 1384.3 +101.6 | $0.084 | Balanced −98% Summarise −98% Chat −98% Code gen −98% Agentic −98% | no image, file input |
| GLM 4.5 Air Z.ai | 1382.8 +100.1 | $0.310 | Balanced −93% Summarise −95% Chat −92% Code gen −92% Agentic −94% | no image, file input |
| Solar Pro 4 Upstage | 1376.2 +93.5 | $0.052 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% | no image, file input |
| DeepSeek V3 0324 DeepSeek | 1375 +92.3 | $0.438 | Balanced −90% Summarise −89% Chat −89% Code gen −90% Agentic −87% | no image, file input |
| GLM 4.6V Z.ai | 1374.7 +92 | $0.450 | Balanced −90% Summarise −90% Chat −91% Code gen −91% Agentic −92% | no file input |
| R1 DeepSeek | 1372.7 +90 | $1.15 | Balanced −74% Summarise −69% Chat −72% Code gen −74% Agentic −66% | 128K → 64K context 16K → 16K max output no image, file input |
| Qwen3 Next 80B A3B Thinking Qwen | 1367.5 +84.8 | $0.412 | Balanced −91% Summarise −92% Chat −89% Code gen −89% Agentic −89% | no image, file input |
| gpt-oss-120b OpenAI | 1365.6 +82.9 | $0.070 | Balanced −98% Summarise −98% Chat −98% Code gen −98% Agentic −98% | no image, file input |
| Qwen3 235B A22B Qwen | 1366 +83.3 | $0.796 | Balanced −82% Summarise −79% Chat −80% Code gen −82% Agentic −77% | 16K → 8K max output no image, file input |
| MiniMax M2.5 MiniMax | 1359 +76.3 | $0.472 | Balanced −89% Summarise −90% Chat −90% Code gen −89% Agentic −91% | no image, file input |
| Gemma 3 27B Google | 1358.3 +75.6 | $0.172 | Balanced −96% Summarise −97% Chat −96% Code gen −96% Agentic −96% | no file input |
| Mercury 2 Inception | 1357.8 +75.1 | $0.375 | Balanced −91% Summarise −92% Chat −93% Code gen −92% Agentic −93% | no image, file input |
| GLM 4.7 Flash Z.ai | 1352.9 +70.2 | $0.145 | Balanced −97% Summarise −98% Chat −96% Code gen −96% Agentic −97% | no image, file input |
| MiniMax M2 MiniMax | 1342.1 +59.4 | $0.446 | Balanced −90% Summarise −88% Chat −89% Code gen −90% Agentic −87% | no image, file input |
| Trinity Large Thinking Arcee | 1341.9 +59.2 | $0.378 | Balanced −91% Summarise −92% Chat −92% Code gen −92% Agentic −92% | no image, file input |
| Qwen3 32B Qwen | 1340.1 +57.4 | $0.130 | Balanced −97% Summarise −96% Chat −97% Code gen −97% Agentic −96% | no image, file input |
| MiniMax M1 MiniMax | 1341.9 +59.2 | $0.963 | Balanced −78% Summarise −75% Chat −76% Code gen −78% Agentic −72% | no image, file input |
| Gemma 3 12B Google | 1334.2 +51.5 | $0.075 | Balanced −98% Summarise −98% Chat −98% Code gen −98% Agentic −98% | no file input |
| o3 Mini High OpenAI | 1336.6 +53.9 | $1.93 | Balanced −56% Summarise −56% Chat −56% Code gen −56% Agentic −56% | no image input |
| DeepSeek V3 DeepSeek | 1332.6 +49.9 | $0.450 | Balanced −90% Summarise −88% Chat −89% Code gen −90% Agentic −87% | 16K → 16K max output no image, file input |
| GLM 4.5V Z.ai | 1333.6 +50.9 | $0.900 | Balanced −79% Summarise −79% Chat −82% Code gen −81% Agentic −83% | 128K → 66K context no file input |
| Qwen3 30B A3B Qwen | 1316.9 +34.2 | $0.215 | Balanced −95% Summarise −94% Chat −95% Code gen −95% Agentic −94% | no image, file input |
| o3 Mini OpenAI | 1319.2 +36.5 | $1.93 | Balanced −56% Summarise −56% Chat −56% Code gen −56% Agentic −56% | no image input |
| Olmo 3 32B Think Allen AI | 1298.5 +15.8 | $0.237 | Balanced −95% Summarise −93% Chat −94% Code gen −95% Agentic −93% | 128K → 66K context no image, file input no tool use |
| Granite 4.1 8B IBM | 1291.6 tie | $0.063 | Balanced −99% Summarise −98% Chat −99% Code gen −99% Agentic −98% | no image, file input |
| Gemma 3 4B Google | 1290.8 tie | $0.063 | Balanced −99% Summarise −98% Chat −99% Code gen −99% Agentic −98% | no file input no tool use |
| gpt-oss-20b OpenAI | 1287.8 tie | $0.055 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −98% | 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/).