NOUMENOpen app
NOUMEN

OpenAI · Efficient

GPT 5.6 Luna Pro

Added Jul 9, 2026

Compare models

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

Loading models…

Use in the app

GPT-5.6 Luna with Pro reasoning mode. Pro mode performs more model work for difficult tasks; reasoning effort remains independently configurable and defaults to medium.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Reasoning effort
none · low · medium · high · xhigh · max
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.20
Output
$1.20
Cache read
$0.02
Cache write
$0.25

Reference prices as published by the model provider. API example

Specifications

Context window
1.1M
Max output
128K
Average output (7 days)
1.5K tokens
Longer than 87% of 465 models

Side by side

GPT 5.6 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 5.6 Luna ProOpenAIThis modelGPT 6 Sol ProOpenAIRemove
ProviderOpenAIOpenAI
Discovery tierEfficientFrontier
AddedJul 9, 2026Sep 22, 2026
Limits
Context window1.05M1.05M
Max output128K128K
Average output1.5K tokens135 tokens
Pricing, USD per 1M tokens
Input$0.20Best$2.00
Output$1.20Best$10.00
Cache read$0.02Best$0.20
Cache write$0.25Best$2.50
Performance
Throughput949.8 tok/s—
Time to first token9.6 s—
Request success (24h)99.8%—
Benchmark indexes
Intelligence Index37.3—
Coding Index71.4—
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effortnone, low, medium, high, xhigh, maxlow, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • GPT 5.6 Luna Pro
  • GPT 6 Sol Pro

Intelligence Index

  • GPT 5.6 Luna Pro37.3
  • GPT 6 Sol Pro—

GPT 5.6 Luna Pro tested at max reasoning effort

GPT 5.6 Luna Pro: Better than 81% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

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

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

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

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

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

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

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

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

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

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

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

  • AA-LCRv1.1

    Reasoning across long documents

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

  • MLCR-AA

    Long-context reasoning over medical records

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

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

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

  • GPQA Diamond

    Graduate-level science questions

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

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

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

  • SciCode

    Scientific computing in Python

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

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

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

Scores from Artificial Analysis, updated Oct 26, 2026. GPT 5.6 Luna Pro was tested at max reasoning effort; compare scores measured at the same effort.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
949.8 tok/s
Faster than 99% of 247 models
Time to first token
9.6 s
Quicker than 10% of 247 models
Prompt cache hits
80.7%
About $0.0548 per 1M input tokens with caching
Request success (24h)
99.8%
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 57.1%
  • 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-5.6-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-5.6-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.