LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Cheapest good LLM for web design

DeepSeek V4 Flash 0423 leads
$0.182
models qualify
67

Output $/Mtok · read October 21

Cheapest output, $ per million tokens

  • Mistral Nemo $0.03
  • Gemma 3 4B $0.05
  • S Llama 3 8B Lunaris $0.05
  • Ling 3.0 Flash $0.063
  • Mistral Small 3 $0.08
  • Llama 3.1 8B Instruct $0.08
  • gpt-oss-20b $0.09
  • N Nex-N2.5-Mini $0.10

As of October 21, 2026, DeepSeek V4 Flash 0423 is the cheapest model at or above the median Design Arena: websites result, at $0.182 per million output tokens, ahead of Xiaomi MiMo-V2.5 ($0.238) and Inception Mercury 3 ($0.35).

This list narrows the best LLM for web design ranking.

Top 20 of 67, lower is better

Embed this data
Cheapest good LLM for web design
Rank Model Output $/Mtok Coding evidence Design Arena: websites Coding index
1
$0.182
1208 54.6
2
MiMo-V2.5 Xiaomi
$0.238
1266 34.0
3
Mercury 3 Inception
$0.35
1240 Not benchmarked
4
GPT-6 Luna OpenAI
$0.50
1272 71.4
5
$0.50
1272 71.0
6
Claude Haiku 5.5 Anthropic
$0.50
1263 75.9
7
$0.525
1309 77.2
8
Hy3 Tencent
$0.528
1230 43.9
9
$0.60
1312 83.3
10
MiMo-V2.5-Pro Xiaomi
$0.609
1267 40.0
11
MiMo-V2.6-Pro Xiaomi
$0.87
1308 72.6
12
MiniMax M2.5 MiniMax
$0.95
1222 59.4
13
R Beam 1.0 501B A23B Reflection
$1.00
1253 33.8
14
MiniMax M3 MiniMax
$1.20
1257 57.8
15
GPT-5.6 Luna OpenAI
$1.20
1256 61.5
16
MiniMax M2.7 MiniMax
$1.20
1243 28.4
17
MiniMax M2.1 MiniMax
$1.20
1201 Not benchmarked
18
$1.28
1269 Not benchmarked
19
$1.32
1238 Not benchmarked
20
GLM 5.3 Z.ai
$1.40
1295 73.1

How this list is built

Generated from the dataset on every refresh. Nobody picks the order by hand.

Models whose Design Arena: websites result is at or above 1201, the median of every model on that board, ordered by output price, cheapest first. Free listings are left out: they are a tariff, not a price.

Other lists

Rankings beyond coding · Methodology