GPT-6 Luna

openai/gpt-6-luna
NewFeatured
VisionToolsJSONReasoning
by OpenAI · 2026-09-22

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks. Multimodal input (text, image, file), 1.05M-token context, configurable reasoning effort, tools and structured outputs.

Endpoints:/v1/chat/completions
ctx1M tokens
Max output128K
Inputtext + image + file
Outputtext
p50 TTFT10.00 s
INPUT$0.10/ 1M tokens
OUTPUT$0.50/ 1M tokens
p50 TTFT10.00 s7d
p95 TTFT10.00 s7d
TRAFFIC71.7Ktokens / 7d
Get the GPT-6 Luna API →▶ Try in playground</> Use via API

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, below GPT-6 Sol and the flagship GPT-6 Astra. It targets high-volume and latency-sensitive workloads — chat, classification,…

What is GPT-6 Luna?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="openai/gpt-6-luna",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • seed
  • structured_outputs
  • tool_choice
  • tools

Pricing

TierInput / 1M tokensOutput / 1M tokensCache read / 1MCache write / 1M
≤ 272K$0.100$0.500$0.010$0.125
≤ ∞$0.200$0.750$0.020$0.250
Tier selected by input token count of each request

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $2.20 · With prompt caching $1.89

Estimate based on list price

Tiered pricing — this estimate uses base-tier rates.

Token & cost estimator

Input tokens: 20Cost per request: $0.000252

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

last 7 days
p50 TTFT
10.00 s
Output speed
31.7 tok/s
p95 TTFT
10.00 s
Error rate
0%

Public benchmarks

Last evaluated 2026-09-22
37.3
AA Intelligence
Better than 74% of models compared
#35 of 145
Humanity's Last Exam
38.5
Long-Context Recall
83.3
SciCode
54.6
Source: artificialanalysis.ai

Community buzz

What developers are saying this week

Hacker News7 mentions · 7dup 6 vs the previous week

How it compares

GPT-6 LunaGPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$0.10$21.00$60.00$5.00
Output $/M$0.50$168.00$270.00$30.00
Context1.1M400K1.1M—
Quality8/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

Browse AI model comparisons →

More from OpenAI

See all models from openai →
GPT-5.5 ProFlagship
openai/gpt-5.5-pro
$30.00 in · $180.00 out / 1M
· quality 10/10
 Compare side-by-side
GPT-5.2Cheapest
openai/gpt-5.2
$1.75 in · $14.00 out / 1M
400K ctx· quality 9/10
 Compare side-by-side
openai/gpt-5.2-chat-latest
openai/gpt-5.2-chat-latest
$1.75 in · $14.00 out / 1M
· quality 9/10
 Compare side-by-side

FAQ

Where does Luna sit in the GPT-6 series?
It is the fast, cost-efficient tier, below GPT-6 Sol and the flagship GPT-6 Astra. Choose Luna for speed and price on high-volume work; step up to Sol or Astra when a task needs more depth.
What inputs does it accept?
Text, images and files, with text output. It serves a ~1.05M-token context window with up to 128K output tokens.
What capabilities does it support?
Configurable reasoning effort (reasoning_effort), function calling / tools, structured (JSON) outputs via response_format, and seeded sampling — all through the OpenAI-compatible API.
How is it priced?
Pricing is tiered by prompt size: a standard rate up to 272K input tokens, stepping up for prompts beyond that. See the pricing on this page for the current rate.

Embed this badge

Paste into your blog post
OpenAI: GPT-6 Luna•$0.10/M in•10000ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-6-luna" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-6-luna.svg" alt="OpenAI: GPT-6 Luna on OrcaRouter" /> </a>
Markdown [![OpenAI: GPT-6 Luna](https://www.orcarouter.ai/embed/openai/gpt-6-luna.svg)](https://www.orcarouter.ai/models/openai/gpt-6-luna)

Model card as data

GET /api/public/models/openai/gpt-6-lunaOpen
Machine-readable:/llms.txt/llms-full.txt