LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Cheapest good LLM for coding

DeepSeek V4.1 Flash leads
$0.0112
models qualify
68

Output $/Mtok · read October 20

Cheapest output, $ per million tokens

  • DeepSeek V4.1 Flash $0.0112
  • 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

As of October 20, 2026, DeepSeek V4.1 Flash is the cheapest model at or above the median coding index, at $0.0112 per million output tokens, ahead of Z.ai GLM 5.3 Flash ($0.16) and DeepSeek V4 Flash 0423 ($0.182).

This list narrows the best LLM for coding ranking.

Top 20 of 68, lower is better

Embed this data
Cheapest good LLM for coding
Rank Model Output $/Mtok Evidence Coding index
1
DeepSeek V4.1 Flash DeepSeek
$0.0112
 77.2
2
GLM 5.3 Flash Z.ai
$0.16
 71.0
3
DeepSeek V4 Flash 0423 DeepSeek
$0.182
 54.6
4
MiMo-V2.6-Flash Xiaomi
$0.28
 61.9
5
Qwen3 Coder 30B A3B Instruct Qwen
$0.28
 60.4
6
DeepSeek V3.2 Exp DeepSeek
$0.41
 55.0
7
Qwen3.8 Flash Qwen
$0.47
 87.4
8
Claude Haiku 5.5 Anthropic
$0.50
 75.9
9
GPT-6 Luna OpenAI
$0.50
 71.4
10
Nemotron 3.5 Super VL NVIDIA
$0.50
 65.5
11
DeepSeek V4.1 Flash 1017 DeepSeek
$0.60
 83.3
12
MiMo-V2.6-Pro Xiaomi
$0.87
 72.6
13
MiniMax M2.5 MiniMax
$0.95
 59.4
14
DeepSeek V3 DeepSeek
$1.0287
 70.2
15
GPT-5.6 Luna OpenAI
$1.20
 61.5
16
MiniMax M3 MiniMax
$1.20
 57.8
17
GLM 5.3 Z.ai
$1.40
 73.1
18
GLM 5 Z.ai
$1.92
 59.7
19
DeepSeek V4 Pro 0813 DeepSeek
$1.98
 54.6
20
GPT-5 Mini OpenAI
$2.00
 59.8

How this list is built

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

Models whose coding index is at or above 54.6, the median of every scored model, ordered by output price, cheapest first. Above the median means better than half the field on the same index.

Other lists

Rankings beyond coding · Methodology