Azure

GPT 6 Luna

gpt-6-luna

OpenAI's most efficient model for focused, high-volume tasks

VisionTool CallingCachingReasoningWebJSON

Quick facts

Released
September 2026
Model type
Proprietary
Model family
GPT Luna
Input modalities
Supports: Text, Image, PDF
Output modalities
Supports: Text
Available regions
USEUGlobal
Zero data retention
Yes
Available on nexos.ai
Yes

Pricing and specifications of GPT 6 Luna

Explore GPT 6 Luna pricing per million input, output, and cached tokens, along with its context window and maximum output limits.

Input / 1MOutput / 1MCached input / 1MContextMax output
$0.10$0.50$0.011.1M128K

Available providers

Provider Region Input / 1M Output / 1M Cache / 1M ZDR
Azure Global $0.10 $0.50 $0.01
Azure EU $0.12 $0.60 $0.01
Azure US $0.11 $0.55 $0.01
OpenAI Global $0.11 $0.55 $0.01
OpenAI Global $0.10 $0.50 $0.01
OpenAI US $0.11 $0.55 $0.01

Specifications

Context window

1.1M tokens

Max output

128K tokens

Input

Output

Benchmarks of GPT 6 Luna

How GPT 6 Luna scores on independent benchmarks tracked by Epoch AI.

Quality

Epoch Capabilities Index

156.4

ECI rank

#38 of 257

GPQA Diamond

Graduate-level scientific reasoning

90.9%

ARC-AGI-2

Abstract reasoning on novel puzzles

59.3%

FrontierMath

Expert-level mathematics

83.1%

OTIS Mock AIME

Competition mathematics

98.9%

APEX-Agents

Long-horizon professional services tasks

44.3%

SimpleQA Verified

Short-form factual accuracy

41.4%

Benchmark data: Epoch AI, ‘Capabilities & benchmarking’, licensed under CC BY 4.0.

Quickstart

Start using GPT 6 Luna

Model ID

gpt-6-luna

Base URL

https://api.nexos.ai/v1

Code

from openai import OpenAI

# Get your API key from the nexos.ai dashboard
client = OpenAI(
    base_url="https://api.nexos.ai/v1",
    api_key="YOUR_NEXOS_API_KEY",
)

response = client.chat.completions.create(
    model="gpt-6-luna",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)
import OpenAI from 'openai';

// Get your API key from the nexos.ai dashboard
const client = new OpenAI({
  baseURL: 'https://api.nexos.ai/v1',
  apiKey: 'YOUR_NEXOS_API_KEY',
});

const response = await client.chat.completions.create({
  model: 'gpt-6-luna',
  messages: [{ role: 'user', content: 'Hello!' }],
});

console.log(response.choices[0].message.content);
curl https://api.nexos.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_NEXOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-luna",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other OpenAI models

Models from OpenAI with comparable capabilities and pricing.

ModelInputOutputContextCapabilitiesRegion
GPT 5.6 Terra$2.20$13.20922K
VisionToolsCacheThinkWebJSON
USEUGlobal
GPT 6 Astra$10.00$50.00922K
VisionToolsCacheThinkWebJSON
USGlobal
GPT 6.1 Sol$2.20$11.00922K
VisionToolsCacheThinkWebJSON
USEUGlobal

Start building with GPT 6 Luna

Access GPT 6 Luna and 200+ other AI models through nexos.ai.

FAQ

Common questions about GPT 6 Luna, its availability and usage.