openai/gpt-6-luna
The fast, low-cost tier of GPT-6 for everyday work at scale.
Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.
Sign in first to upload images to this vision model.
SELECT user_id, SUM(amount) AS total_spend
FROM orders
WHERE created_at >= '2026-01-01'
AND created_at < '2027-01-01'
GROUP BY user_id
ORDER BY total_spend DESC
LIMIT 5;
This sums each user’s order amounts during 2026 and returns the five highest totals.
GPT-6 Luna was released by OpenAI on September 22, 2026, alongside GPT-6 Sol, as the high-throughput member of the GPT-6 family. OpenAI's model page positions it for focused, high-volume tasks: classification, extraction, summarization, routing, and the high-concurrency steps of an agent pipeline. OpenAI's deprecations table names it as the replacement for GPT-4.1, GPT-4.1 mini, GPT-4o mini and some GPT-4o snapshots (shutting down January 14, 2027) and for gpt-5.4-nano (April 1, 2027).
It is not a stripped-down model. It has a 1.05M-token context window (up to 922K input), 128K max output, text and image input, and a knowledge cutoff of May 18, 2026. Reasoning effort takes none, low, medium, high, xhigh or max, with medium as the default; set none for plain completions and raise it for the occasional hard step. On RouteMux it supports tool calling and explicit prompt caching, and it is reachable over OpenAI Chat Completions, OpenAI Responses and Anthropic Messages, so moving an existing client to Luna is a model-string change.
Against the previous generation, GPT-5.6 Luna (released July 9, 2026), the context window, output limit and reasoning effort values are the same, and 6 Luna's knowledge cutoff is three months later (5.6 Luna stops at February 16, 2026). Stay on 5.6 Luna when one conversation switches between GPT-5.6 Sol, Terra and Luna and should reuse reasoning across them, which OpenAI documents for the 5.6 family along with carrying reasoning across turns by default, or when your pipeline is already tuned to it.
At the standard tier (input up to 272K tokens) it bills $0.05 per 1M input tokens and $0.25 per 1M output tokens, with cached input at $0.005 per 1M tokens. OpenAI lists $0.1, $0.5 and $0.01 for the same three.
Prices verified 2026-10-06
Fast $0.1 / $0.5 /M
Cache read $0.005/M · Cache write $0.0625/M
| Tier | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Standard ≤272K | $0.05 | $0.005 | $0.0625 | $0.25 |
| Standard >272K | $0.1 | $0.01 | $0.125 | $0.375 |
| Priority ≤272K | $0.1 | $0.01 | $0.125 | $0.5 |
| Priority >272K | $0.2 | $0.02 | $0.25 | $0.75 |
reasoning_effort is a request parameter defaulting to medium; none switches reasoning off entirely.Limited time10% extra Credits on your first top-up — up to 200 bonus Credits
Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.
Use any of these IDs to call this model via the API.
openai/gpt-6-lunaReplace the ROUTEMUX_KEY placeholder with your API key. Create one →
from openai import OpenAI
client = OpenAI(
base_url="https://api.routemux.com/v1",
api_key="<ROUTEMUX_KEY>",
)
completion = client.chat.completions.create(
model="openai/gpt-6-luna",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)The fast, low-cost tier of GPT-6 for everyday work at scale.
GPT-6 Luna supports a context window of up to 1.05M tokens, with up to 128K output tokens per request.
Through RouteMux, GPT-6 Luna costs $0.05 for input and $0.25 for output (USD per 1M tokens), below the official list price.
GPT-6 Luna is OpenAI-compatible: point your base URL at RouteMux and set the model field to openai/gpt-6-luna — no code changes needed.
GPT-6 Luna accepts text, image as input and produces text as output.
GPT-6 Luna was released on September 22, 2026.
Reviewed by the RouteMux team on 2026-10-24
24,680 requests · last 30 days