getcheapaicredits

Model vs model · live prices

GPT-6 Luna vs Kimi K2.5

GPT-6 Luna is 4.5× cheaper than Kimi K2.5 at a 3:1 input:output mix ($0.2 vs $0.9 per million tokens).
Per 1M tokensOpenAI: GPT-6 LunaMoonshotAI: Kimi K2.5
Input$0.1$0.45
Output$0.5$2.25
Cached input$0.01$0.07
Blended 3:1$0.2$0.9
Context window1.1M262K
ReleasedSeptember 22, 2026January 27, 2026
Tools · reasoningTools · ReasoningTools · Reasoning

List prices from OpenRouter, refreshed hourly. Lower price and larger context highlighted.

What the same work costs on each

At list price, before batch or caching discounts.
WorkloadGPT-6 LunaKimi K2.5Difference
1,000 chat messages
1,000 input + 500 output tokens each
$0.35$1.58$1.23
1,000 RAG questions
8,000 input + 500 output tokens each
$1.05$4.73$3.68
100 coding-agent steps
30,000 input + 2,000 output tokens each, no caching
$0.40$1.80$1.40

Which one should you use?

Price is only half the decision: run both on a sample of your own prompts and compare quality, speed and failure rate. If GPT-6 Luna is good enough for a task, it saves $1.23 per thousand chat messages. A common setup is to route easy requests to the cheaper model and keep Kimi K2.5 for the hard ones.

Both are available behind one OpenAI-compatible key through OpenRouter or a reseller, so switching is a one-line change. See where credits cost least today and how to cut the token bill.

Related comparisons

FAQ

Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare