// head_to_head

GPT-6 Luna vs Hy-MT2-1.8B

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

Hy-MT2-1.8B 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-6 Luna

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

tencent

Hy-MT2-1.8B

Blended / 1M
$0.077
Context
8K
Released
Aug 20, 2026
Overall score
Not evaluated

Specs and pricing

MetricGPT-6 LunaHy-MT2-1.8B
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.

$0.200$0.077win
Input price / 1M$0.100$0.044win
Output price / 1M$0.500$0.177win
Cached input / 1M

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

$0.010
Context window1.1Mwin8K
Max output tokens128Kwin4K

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-6 LunaHy-MT2-1.8B
Support chatbot

1.2K in / 400 out × 200K requests

$57.52/mo$24.72/mo
RAG assistant

8K in / 600 out × 100K requests

$74.00/mo$45.82/mo
Coding agent

40K in / 4K out × 20K requests

$69.60/mo$49.36/mo
Document extraction

20K in / 1.5K out × 50K requests

$133.00/mo$57.27/mo
Bulk classification

500 in / 20 out × 5M requests

$255.00/mo$127.70/mo
Run these two through the cost calculator

Which should you pick?

You need to fit large documents in one call

GPT-6 Luna

Wider context window — 1.1M against 8K.

You are cost-constrained

Hy-MT2-1.8B

Cheaper on blended list price at $0.077 per million tokens.

GPT-6 Luna vs Hy-MT2-1.8B FAQ

Which is better, GPT-6 Luna or Hy-MT2-1.8B?

Hy-MT2-1.8B 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-6 Luna cheaper than Hy-MT2-1.8B?

Hy-MT2-1.8B is cheaper. On a 3:1 input:output blend, GPT-6 Luna lists at $0.200 per million tokens and Hy-MT2-1.8B at $0.077 — Hy-MT2-1.8B is 2.6× cheaper. Input and output are priced separately — GPT-6 Luna charges $0.100 in and $0.500 out, Hy-MT2-1.8B charges $0.044 and $0.177 — so the model that looks cheaper flips depending on how output-heavy your workload is.

Does GPT-6 Luna or Hy-MT2-1.8B have a bigger context window?

GPT-6 Luna has the larger context window: 1.1M for GPT-6 Luna against 8K for Hy-MT2-1.8B. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.

Do GPT-6 Luna and Hy-MT2-1.8B support prompt caching?

GPT-6 Luna publishes a cached-input rate of $0.010 per million tokens against a full input rate of $0.100. The catalogue lists no separate cached rate for Hy-MT2-1.8B, which means the provider does not price it separately here — not that caching is unavailable.

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.