Enterprise DNAEnterprise DNA
OpenAI logo

Models · Best vision

GPT-6 Luna

by OpenAI

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.

Visit OpenAI ↗

Our verdict

Not reviewed yet

We have not reviewed GPT-6 Luna yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.

Best for

Cost-conscious everyday automation

Notes

GPT-6 Luna is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Summarising short operational notes
  • file, image, text input; text output on the listed OpenRouter route

Cons

  • Assuming lower token prices guarantee lower total task cost
  • Using output without checking source fidelity
  • Catalogue base token rates have additional pricing overrides. Context length, time window, caching, reasoning, tools or media can change total cost; the simple calculator is not a full quote.

Key facts

What we have checked

Input price
$0.100 per million tokens
Checked OpenRouter models API
Output price
$0.500 per million tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.010 per million cached input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.100 per million input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.500 per million output tokens
Checked OpenRouter models API
Price on azure
$0.010 per million cached input tokens
Checked OpenRouter models API
Price on azure
$0.100 per million input tokens
Checked OpenRouter models API
Price on azure
$0.500 per million output tokens
Checked OpenRouter models API
Price on openai
$0.0050 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
90.5% (for 22 Sept 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
78.9% (for 22 Sept 2026)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
41.4% (for 22 Sept 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `openai/gpt-6-luna`.

  • openrouter · openai/gpt-6-luna · Docs

OpenRouter id: openai/gpt-6-luna

Price

What GPT-6 Luna costs, over time

Input price

$0.100 to $0.100

US dollars per million input tokens. 24 Sept 2026 to 10 Nov 2026, 37 days.

Source: OpenRouter models API. Checked .

Output price

$0.500 to $0.500

US dollars per million output tokens. 24 Sept 2026 to 10 Nov 2026, 37 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
amazon-bedrockCached input$0.010 per million cached input tokensSince 7 Nov 20261 changeOpenRouter models API
amazon-bedrockInput$0.100 per million input tokensSince 7 Nov 20261 changeOpenRouter models API
amazon-bedrockOutput$0.500 per million output tokensSince 7 Nov 20261 changeOpenRouter models API
azureCached input$0.010 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureInput$0.100 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureOutput$0.500 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
openaiCached input$0.0050 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
openaiInput$0.050 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
openaiOutput$0.250 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much GPT-6 Luna is used

Tokens served a day

72.9B to 1.1T

tokens a day on OpenRouter. 22 Sept 2026 to 10 Nov 2026, 50 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How GPT-6 Luna scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index27.9indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,388EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena web development rating (Elo)1,577EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena vision rating (Elo)1,211EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Apex agents (best-across-versions)44.3percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Arc agi (best-across-versions)86.7percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)59.3percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)36percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)90.1percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)42.4percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)56.1percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)78.9percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Show 9 more scores
ScoreValueSourceChecked
Furniture assembly (best-across-versions)44.2percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)90.5percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)44.5percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)7percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated98.9percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)64percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)41.4percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Spireclimb (best-across-versions)0percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Weirdml v3 (best-across-versions)12percentAs of 22 Sept 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    cached input per mtok: 0.011 to 0.01

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 0.55 to 0.5

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.11 to 0.1

    Source: OpenRouter models API

USAGE / OPENROUTER

How much GPT-6 Luna is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
7.1T ▼24%
Requests, last 7 days
561M
Tool calls, last 7 days
113M
Intelligence score
27.9
People's vote
1388
Average cost per request
7.9¢
Price per million tokens
$0.1 in · $0.5 out
02.5T5T22 Sept: 72.9B tokens, 2.7M requests23 Sept: 412B tokens, 24.3M requests24 Sept: 543B tokens, 31.4M requests25 Sept: 628B tokens, 26.1M requests26 Sept: 626B tokens, 24M requests27 Sept: 609B tokens, 23.5M requests28 Sept: 828B tokens, 34.2M requests29 Sept: 808B tokens, 34.9M requests30 Sept: 1.1T tokens, 44.5M requests1 Oct: 1.2T tokens, 48.3M requests2 Oct: 891B tokens, 42.2M requests3 Oct: 687B tokens, 34.4M requests4 Oct: 771B tokens, 32.8M requests5 Oct: 846B tokens, 41.7M requests6 Oct: 1T tokens, 52.9M requests7 Oct: 1.1T tokens, 51.9M requests8 Oct: 1.3T tokens, 54.8M requests9 Oct: 1.3T tokens, 57.8M requests10 Oct: 871B tokens, 45.3M requests11 Oct: 733B tokens, 43.5M requests12 Oct: 862B tokens, 53.9M requests13 Oct: 1T tokens, 58.3M requests14 Oct: 1.1T tokens, 61.1M requests15 Oct: 974B tokens, 59.6M requests16 Oct: 1T tokens, 66.1M requests17 Oct: 706B tokens, 57.7M requests18 Oct: 689B tokens, 48.9M requests19 Oct: 885B tokens, 65.6M requests20 Oct: 1T tokens, 68.1M requests21 Oct: 956B tokens, 78M requests22 Oct: 1T tokens, 79.4M requests23 Oct: 1.6T tokens, 80.9M requests24 Oct: 1.5T tokens, 69.6M requests25 Oct: 1.5T tokens, 81.2M requests26 Oct: 1.6T tokens, 80.4M requests27 Oct: 1.1T tokens, 79.5M requests28 Oct: 1.5T tokens, 85.6M requests29 Oct: 2.8T tokens, 99.1M requests30 Oct: 1.2T tokens, 76.4M requests31 Oct: 820B tokens, 64.3M requests1 Nov: 815B tokens, 60.2M requests2 Nov: 1.1T tokens, 84.7M requests3 Nov: 1.1T tokens, 84.3M requests4 Nov: 1.1T tokens, 83.6M requests5 Nov: 1.1T tokens, 80.9M requests6 Nov: 1.2T tokens, 90.6M requests7 Nov: 856B tokens, 70M requests8 Nov: 757B tokens, 65.1M requests9 Nov: 1T tokens, 82.5M requests10 Nov: 1.1T tokens, 88.1M requests22 Sept6 Oct20 Oct3 Nov10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with GPT-6 Luna.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperOpenAI
Exact model identifieropenai/gpt-6-luna
Inputfile, image, text
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
1.1M tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
22 Sept 2026
Listed retirement date
Not established

Catalogue base token rates have additional pricing overrides. Context length, time window, caching, reasoning, tools or media can change total cost; the simple calculator is not a full quote.

Consider it for

  • Summarising short operational notes
  • Lightweight agents with narrowly scoped read-only tools

Watch for

  • Assuming lower token prices guarantee lower total task cost
  • Using output without checking source fidelity

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Summarise: Order 41 arrived Monday; two units damaged; replacement requested Tuesday; no refund approved. Return status, next action and unresolved facts in three bullets.

Check the result: The summary retains the damaged count, replacement request and absence of a refund approval.

Compare another approach

anthropic claude sonnet 5 5 ↗openai gpt 6 1 sol ↗
Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

openai/gpt-6-luna: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-07
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 27.9 (2026-11-09) ↗Vals Index: 52.322 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →