Skip to content
OfferSign up and get $10 of credit for any model in Chat and the API. Top up from $1, with no processing fees. See free models →·Some free models are at the daily cap — refills 05:30 IST; requests auto-route to a live backup. Status →
One AI API Key
Get API key

OpenAI · GPT · Fast

GPT-6 Luna

Discount −65%New

The fast, low-cost model in OpenAI's GPT-6 series, for high-volume chat and light agent work.

Model id

gpt-6-luna
Get an API keyTry in Chat

Price per 1M tokens

Input
Regular rate $0.10now $0.035
Output
Regular rate $0.50now $0.175
Cached input
$0.0171% below input

65% below the market rate.

Added here 18 Oct 2026 — read the changelog for what changed and why.

Output is 5× the input rate. $1 covers about 8,196 prompts of 1,000 input + 500 output tokens. 1 credit = $1 of usage. All rates

Start using GPT-6 Luna

Set ONEAIAPIKEY_API_KEY to a key from your console, then run any example. Streaming is on so long answers are not cut off by idle-connection timeouts.

curl https://api.oneaiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $ONEAIAPIKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-luna",
    "stream": true,
    "messages": [{"role": "user", "content": "Explain the difference between a mutex and a semaphore in plain words."}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.oneaiapikey.com/v1",
    api_key=os.environ["ONEAIAPIKEY_API_KEY"],
)

stream = client.chat.completions.create(
    model="gpt-6-luna",
    messages=[{"role": "user", "content": "Explain the difference between a mutex and a semaphore in plain words."}],
    stream=True,  # recommended for long outputs
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.oneaiapikey.com/v1",
  apiKey: process.env.ONEAIAPIKEY_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "gpt-6-luna",
  messages: [{ role: "user", content: "Explain the difference between a mutex and a semaphore in plain words." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

More: quickstart · API reference · try it in Chat first

Benchmarks reported by the vendor

Scores for GPT-6 Luna as its maker published them, with the setting they state. We have not re-run them. Versions and settings differ between vendors, so compare only identical benchmark names; compare models side by side.

Tokens per day, by model

Last 7 days, UTC days

Hover, tap or drag across any day, or focus the chart and use the arrow keys, to see how every model did that day.

Real tokens served through this gateway, updated every 5 minutes. Ranked by usage, not quality.

Full ranking insights

GPT line-up

GPT-6 Luna or GPT-5.6 Terra or DeepSeek V4 Flash (free lane)?

Of the 5 GPT models on this site, GPT-5.6 Terra is the step up from GPT-6 Luna, and nothing in the family sits below it. DeepSeek V4 Flash (free lane) from DeepSeek is the closest-priced fast-tier model from another vendor. Each comparison lists the published rates and limits, then what favours each side.

GPT-6 LunavsGPT-5.6 Terra

Per 1M tokensGPT-6 LunaGPT-5.6 Terra
Input$0.03598% less$2
Output$0.17599% less$12
Cached input$0.0195% less$0.20
Context1.05Mthe same1.05M
Max output128kthe same128k

Pick GPT-6 Luna when

  • cost per request decides it: GPT-6 Luna charges input 98% less and output 99% less than GPT-5.6 Terra.
  • the work is high-volume chat, classification and light agents, which this catalogue lists for GPT-6 Luna and not for GPT-5.6 Terra.

Pick GPT-5.6 Terra instead when

  • GPT-6 Luna falls short and you want the balanced model of the pair.
  • GPT-6 Luna does not list JSON mode and your code depends on it.
  • your workload looks like general coding, writing and rAG, labels the catalogue gives GPT-5.6 Terra only.

GPT-6 LunavsDeepSeek V4 Flash (free lane)

Per 1M tokensGPT-6 LunaDeepSeek V4 Flash (free lane)
Input$0.03511% less$0.0392
Output$0.1752.2× as much$0.0784
Context1.05M5% larger1M
Max output128k67% less384k

Pick GPT-6 Luna when

  • cost per request decides it: GPT-6 Luna charges input 11% less than DeepSeek V4 Flash (free lane).
  • prompts run past 1M tokens: GPT-6 Luna reads up to 1.05M.
  • you rely on Vision, Structured output and Prompt caching, which DeepSeek V4 Flash (free lane) does not list.
  • requests include screenshots or other images.
  • the work is high-volume chat, classification and light agents, which this catalogue lists for GPT-6 Luna and not for DeepSeek V4 Flash (free lane).

Pick DeepSeek V4 Flash (free lane) instead when

  • the job runs well enough on the lower rates: output at 55% less.
  • the 128k output cap of GPT-6 Luna cuts answers short; DeepSeek V4 Flash (free lane) writes up to 384k.
  • GPT-6 Luna does not list JSON mode and your code depends on it.
  • your workload looks like budget coding, sub-agents and batch jobs, labels the catalogue gives DeepSeek V4 Flash (free lane) only.

Use cases

What GPT-6 Luna is listed for, and what it costs

The catalogue lists GPT-6 Luna for high-volume chat, classification and light agents. Each row prices one typical request at the published rates, with the arithmetic shown. The market-rate figure shows the same request at the lowest public price elsewhere. Token counts are examples; your prompts will differ.

Model your own traffic

  1. High-volume chat

    One chat reply: 1,500 tokens of conversation history in, 400 tokens out.

    “Explain the difference between a mutex and a semaphore in plain words.”

    Same request on GPT-5.6 Terra $0.0078 and DeepSeek V4 Flash (free lane) $0.00009.

    $0.000122

    per reply, about 81,967 per $10

    $0.00035 at the market rate

    0.0015 × $0.035 + 0.0004 × $0.175

  2. Classification

    One message sorted into a fixed set of labels: 800 tokens in, a 20-token label out.

    Give a fixed label set and ask for one label per item to keep answers short and cheap.

    “Label this support email as billing, bug, feature request or other. Reply with the label only.”

    Same request on GPT-5.6 Terra $0.00184 and DeepSeek V4 Flash (free lane) $0.000032.

    $0.000032

    per message, about 312,500 per $10

    $0.00009 at the market rate

    0.0008 × $0.035 + 0.00002 × $0.175

  3. Light agents

    One step of a tool-using agent: 20,000 tokens of instructions, tool results and history, 15,000 of them cached, and 1,000 tokens of tool calls and notes out.

    “Check the order status for each customer in this list and draft a reply to the late ones.”

    Same request on GPT-5.6 Terra $0.025 and DeepSeek V4 Flash (free lane) $0.000862.

    $0.0005

    per agent step, about 20,000 per $10

    $0.00115 at the market rate

    0.005 × $0.035 + 0.015 × $0.01 + 0.001 × $0.175

Overview

When GPT-6 Luna fits

GPT-6 Luna is a fast, low-cost model from OpenAI, available here under the exact model id “gpt-6-luna”. It is the entry point of the GPT line-up here, below GPT-5.6 Sol, GPT-6 Astra, GPT-6.1 Sol and GPT-5.6 Terra. OpenAI has not published a release date we can cite; it has been available here since 18 Oct 2026.

OpenAI documents tools, vision, reasoning, structured output and prompt caching for it, and it reads images as well as text.

It costs $0.035 per million input tokens and $0.175 per million output tokens, so output is 5× the input rate. That is 65% below the market rate of $0.10 input and $0.50 output per million tokens, the lowest public price we found at other API gateways. On the use cases below, output makes up 57% of the bill for high-volume chat, 11% for classification and 35% for light agents, so trimming the context you send saves more than capping the answer. With a 3:1 input-to-output mix it ranks 3rd lowest-cost of the 27 models on this site.

Cached input bills at $0.01 per million tokens, 71% below the standard input rate. In the light agents example, 15k of the 20k input tokens come from cache, which brings one agent step from $0.000876 down to $0.0005.

It is served through the OpenAI-compatible format at https://api.oneaiapikey.com/v1, so any SDK or tool that lets you set a custom base URL, for example Codex CLI, Cursor and Cline, can use it. It is not offered on the Anthropic Messages endpoint; pick an Anthropic-format model for Claude Code.

Similar models

Same tier, other vendors

Same key, same balance. Switching is a change to the model field.

Compare side by sideAll models

Use GPT-6 Luna with any balance.

GPT-6 Luna is a paid model: any balance above $0 pays for it, the $10.00 sign-up credit included. When it runs out, add $1 or more to your wallet. Every request is billed at the rates above, with a receipt in your usage log.

Create an accountSee pricing

GPT-6 Luna is developed by OpenAI. Model names and trademarks belong to their owners. One AI API Key is an independent API gateway and is not affiliated with, endorsed by or sponsored by OpenAI.