NOUMENOpen app
NOUMEN

OpenAI · Efficient

GPT 6 Luna Pro

Added Sep 22, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna with Pro reasoning mode enabled for higher-quality responses on complex tasks.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Reasoning effort
low · medium · high · xhigh · max
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.50
Cache read
$0.01
Cache write
$0.13

Reference prices as published by the model provider. API example

Specifications

Context window
1.1M
Max output
128K
Average output (7 days)
2.8K tokens
Longer than 96% of 473 models

Side by side

GPT 6 Luna Pro compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

GPT 6 Luna ProOpenAIThis modelGPT 5.6 Luna ProOpenAIRemove
ProviderOpenAIOpenAI
Discovery tierEfficientEfficient
AddedSep 22, 2026Jul 9, 2026
Limits
Context window1.05M1.05M
Max output128K128K
Average output2.8K tokens1.5K tokens
Pricing, USD per 1M tokens
Input$0.10Best$0.20
Output$0.50Best$1.20
Cache read$0.01Best$0.02
Cache write$0.13Best$0.25
Performance
Throughput295.0 tok/s978.7 tok/sBest
Time to first token26.8 s10.8 sBest
Request success (24h)100.0%Best99.8%
Benchmark indexes
Intelligence Index—37.3
Coding Index—71.4
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effortlow, medium, high, xhigh, maxnone, low, medium, high, xhigh, max

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • GPT 6 Luna Pro
  • GPT 5.6 Luna Pro

Intelligence Index

  • GPT 6 Luna Pro—
  • GPT 5.6 Luna Pro37.3
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 71.4

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 50.2%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 18.6%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 1,339 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 1,460 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 24.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 83.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 20.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 39.5%

  • GPQA Diamond

    Graduate-level science questions

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 91.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 11.6%

  • SciCode

    Scientific computing in Python

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 53.6%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 6 Luna Pro: —
    • GPT 5.6 Luna Pro: 83.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
295.0 tok/s
Faster than 92% of 260 models
Time to first token
26.8 s
Quicker than 1% of 260 models
Prompt cache hits
31.3%
About $0.0719 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 94.4%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-luna-pro",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="openai/gpt-6-luna-pro",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.