// head_to_head

GPT-4.1 Nano vs GPT-6 Luna

Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.

OpenRouter + LiveBenchAll comparisonsFull leaderboard

GPT-4.1 Nano is the cheaper of the two; neither can be ranked on quality here.

Neither model has a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.

openai

GPT-4.1 Nano

Blended / 1M
$0.175
Context
1.0M
Released
Apr 14, 2025
Overall score
Not evaluated
tool callingimage inputfile inputprompt caching

openai

GPT-6 Luna

Blended / 1M
$0.200
Context
1.1M
Released
Sep 22, 2026
Overall score
Not evaluated
reasoningtool callingfile inputimage inputprompt caching

Specs and pricing

MetricGPT-4.1 NanoGPT-6 Luna
LiveBench overall

Mean of the seven LiveBench category scores, 0–100. Higher is better.

Cost per point

Measured benchmark spend divided by overall score — dollars per point of capability.

Blended price / 1M

3:1 input:output mix, the usual shape of production traffic.

$0.175win$0.200
Input price / 1M$0.100$0.100
Output price / 1M$0.400win$0.500
Cached input / 1M

Price of an input token served from the prompt cache, where the provider publishes one.

$0.025$0.010win
Context window1.0M1.1M
Max output tokens33K128Kwin

What each one costs to run

Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.

WorkloadGPT-4.1 NanoGPT-6 Luna
Support chatbot

1.2K in / 400 out × 200K requests

$50.60/mo$57.52/mo
RAG assistant

8K in / 600 out × 100K requests

$74.00/mo$74.00/mo
Coding agent

40K in / 4K out × 20K requests

$70.00/mo$69.60/mo
Document extraction

20K in / 1.5K out × 50K requests

$126.25/mo$133.00/mo
Bulk classification

500 in / 20 out × 5M requests

$252.50/mo$255.00/mo
Run these two through the cost calculator

Which should you pick?

You are cost-constrained

GPT-4.1 Nano

Cheaper on blended list price at $0.175 per million tokens.

GPT-4.1 Nano vs GPT-6 Luna FAQ

Which is better, GPT-4.1 Nano or GPT-6 Luna?

GPT-4.1 Nano is the cheaper of the two; neither can be ranked on quality here. Neither model has a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.

Is GPT-4.1 Nano cheaper than GPT-6 Luna?

GPT-4.1 Nano is cheaper. On a 3:1 input:output blend, GPT-4.1 Nano lists at $0.175 per million tokens and GPT-6 Luna at $0.200 — GPT-4.1 Nano is 14% cheaper. Input and output are priced separately — GPT-4.1 Nano charges $0.100 in and $0.400 out, GPT-6 Luna charges $0.100 and $0.500 — so the model that looks cheaper flips depending on how output-heavy your workload is.

Does GPT-4.1 Nano or GPT-6 Luna have a bigger context window?

They are effectively the same — 1.0M for GPT-4.1 Nano and 1.1M for GPT-6 Luna.

Do GPT-4.1 Nano and GPT-6 Luna support prompt caching?

Both publish a cached-input rate: $0.025 per million for GPT-4.1 Nano and $0.010 for GPT-6 Luna, against full input rates of $0.100 and $0.100. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.

Related comparisons

How these numbers are produced

  • Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
  • ScoresLiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
  • Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
  • “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.

Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.