Skip to content

OpenAI · Chat

GPT-6 Luna

OpenAI 🇺🇸ChatGPT familyOne of its sources says the weights aren't publicly available.The maker currently lists 11 Mar 2028 as the deprecation date. Plans can change.
From Neosantara's listing:
GPT-6 Luna is OpenAI's lightweight, high-speed reasoning model optimized for low-latency subagent tasks, rapid exploration, and high-throughput operations.
llminfo IQ
135.6
Maker's price
$0.20 blended / 1M
Max context
1.1M
Listings
104

Evidence and sources

llminfo IQ 135.6, ranked among chat models. From 227 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 116.9, 95% interval 111–123. From 13 benchmark families across 6 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (63.4). Cheaper per task than its benchmark results predict. From 44 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (51 ±11). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. By effort: default 47 · low 39 · medium 47 · high 51 · max 51.Median 51,758 output tokens per task at max effort.How the Yap score worksReleased 22 Sep 2026Maker HQ: US (according to OpenAI's own website)
All rankings: #4 on OpenRouter this month #4 on OpenRouter this week #6 on OpenRouter today #83 on NanoGPT recentlySources: OpenAI API data, Writer Pricing, LiteLLM data, Models.dev data, AI/ML API data, Neosantara Inference data, llminfo researchPrimary data from OpenAI API from Writer Pricing: name, variant from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from Neosantara Inference: description from llminfo research: release date
Tags from its sources:instructreasoningtoolsvisiondocumentlong-contextefficienthigh-throughput

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 10 maker's prices.

Input & output

as stated by the model's providers
Text
Images
Files
Choices and scores
Text

Capabilities

Supported operations and provider-stated features

DecisionVisionReasoningFunction callingStructured outputPrompt cachingPDF inputComputer useWeb searchBatch API

Listings

 OpenAIgpt-6-lunaSources: LiteLLM data, Models.dev data, OpenAI API data922K$0.10cache read $0.01batch $0.05$0.50cache write $0.125batch $0.25——
 Kunavogpt-6-lunaSource: Models.dev data1.1M$0.04cache read $0.004$0.20cache write $0.05——
 Nous Portalopenai/gpt-6-luna:batch · batchSource: Nous Portal Inference Gateway data1.1M$0.05cache read $0.005$0.25cache write $0.0625——
 OpenRouterInference by OpenAIopenai/gpt-6-luna-pro · flex, proSource: OpenRouter data docs922K$0.05cache read $0.005$0.25cache write $0.06256227,730ms
 Vercelopenai/gpt-6-luna-batch · batchSource: Vercel AI Gateway data1.1M$0.05cache read $0.005$0.25——
 Outerlabsgpt-6-lunaSource: Models.dev data1.1M$0.06cache read $0.006$0.30——
 Uplinkswitchgpt-6-lunaSource: Models.dev data1.1M$0.0625cache read $0.0125$0.20——
 Iteracomputeopenai/gpt-6-lunaSource: Models.dev data1.1M$0.08cache read $0.008$0.40cache write $0.10——
 Tokenmixgpt-6-lunaSources: TokenMix data, TokenMix PricingNot published by the provider$0.095$0.475——
 Microsoft Azureazure/gpt-6-luna-2026-09-22 · 2026-09-22Source: LiteLLM data922K$0.10cache read $0.01$0.50cache write $0.125——

12 listings without a price are hidden.

Included in plans

OpenLimits MaxopenlimitsSubscription€120/moPlan page
OpenLimits UltimateopenlimitsSubscription€299/moPlan page
Copilot EnterprisegithubSubscription$39/moextra use billed past the allowancePlan page
Copilot ProgithubSubscription$10/moextra use billed past the allowancePlan page
Copilot Pro+githubSubscription$39/moextra use billed past the allowancePlan page
Copilot BusinessgithubSubscription$19/moextra use billed past the allowancePlan page
Copilot MaxgithubSubscription$100/moextra use billed past the allowancePlan page
ChatGPT GoOpenAISubscription$8/moPlan page
ChatGPT PlusOpenAISubscription$20/moPlan page
ChatGPT ProOpenAISubscription$100/moPlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO64 related benchmarks · 64 results
Source: LMArena data · Nov 2026
BenchmarkMax
Arena ELO
Chinese
Creative Writing
English
Show 60 more benchmarksHide 60 benchmarks
BenchmarkMax
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Search Factuality
Search Style-Controlled
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - German
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Japanese
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Homework
Vision - Humor
Vision Style-Controlled
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Agentic

Design Arena EloSource: Design Arena Leaderboards data · Nov 2026
GDPval-AA v2adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Artificial Analysis · Haiku 5.5 card snapshot · max · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 82-task offline subset · OpenAI API · max · context compaction
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · OSWorld 2.0 offline v2026.08.08
Source: Clinical Benchmarks data docs · Oct 2026
Setting not stated
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 100 EHR tasks · max · five attempts/task
Source: OpenRouter benchmark exports
22 Sep 2026 version (gpt-6-luna) · 90-day results
Across 3 providers lowest 68% median 68.1% highest 68.4%OpenRouter's automatic routing 67.3%
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
  • Amazon Bedrock
  • Azure
  • OpenAI
  • OpenRouter's automatic routing
22 Sep 2026 version (gpt-6-luna-pro) · 90-day results
Across 2 providers lowest 68.5% median 68.9% highest 69.3%OpenRouter's automatic routing 66.7%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • OpenAI
  • Azure
  • OpenRouter's automatic routing

Coding

Arena ELOSource: LMArena data · Nov 2026
FrontierCode 1.1 MainReasoning effort · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ValsSource: Vals AI

Reasoning

AutomationBenchReasoning effort · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

General

Science

GPQA Diamond8 results
Source: OpenRouter benchmark exports
22 Sep 2026 version (gpt-6-luna) · 90-day results
Across 3 providers lowest 87.7% median 87.8% highest 88.2%OpenRouter's automatic routing 87.4%
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
  • OpenAI
  • Amazon Bedrock
  • Azure
  • OpenRouter's automatic routing
22 Sep 2026 version (gpt-6-luna-pro) · 90-day results
Across 2 providers lowest 88.9% median 89% highest 89%OpenRouter's automatic routing 88.4%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • OpenAI
  • Azure
  • OpenRouter's automatic routing

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs · Sep 2026

Math

Instruction following

Vision

Factuality

OCR

Other

Artificial Analysis10 related benchmarks · 10 results
Briefcase
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · v1.1 · Artificial Analysis · Haiku 5.5 card snapshot · max
Show 4 more resultsHide 4 results
DeepSWE v1.1Reasoning effort · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
HealthBench HardOpenAI, length-adjusted, maximum reasoning effort, 31.4 (25.4, 1241) (adjusted, raw, mean response characters) · Source: HealthBench Hard (Arcophos) data docs · Reported by the model's developer. The source relaying it did not verify it. · Sep 2026
MentalHealthBench17 related benchmarks · 17 results
Overall
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Acuity · Emergent
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Acuity · High acuity
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Acuity · Non-acute
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Behavior · Actionable guidance and coping
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Behavior · Alarmism and under-response
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Show 11 more resultsHide 11 results
Behavior · Collaboration and user agency
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Behavior · Communication and writing
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Behavior · Context seeking and assessment
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Behavior · Empathy and emotional support
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Behavior · Interpretation and cognitive reframing
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Behavior · Reality-testing calibration
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
Behavior · Refusals and harm avoidance
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
User profile · Caregiver
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
User profile · Clinician
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
User profile · Layperson
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
User profile · Teen
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI evaluation · 95% CI available on source page
MultiLangBench6 related benchmarks · 6 results
COBOL test pass rate
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI publication · SQLite 3.40.1 from scratch · COBOL · maximum reasoning effort · 272-test recommended subset in public harness; exact publication test selection and API snapshot not stated
20-language average test pass rate
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI publication · SQLite 3.40.1 from scratch · 20-language average · maximum reasoning effort · 272-test recommended subset in public harness; exact publication test selection and API snapshot not stated
Estimated average API cost
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI publication · 20-language average · maximum reasoning effort · estimated API cost per sample · exact API snapshot not stated
Fortran test pass rate
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI publication · SQLite 3.40.1 from scratch · Fortran · maximum reasoning effort · 272-test recommended subset in public harness; exact publication test selection and API snapshot not stated
OCaml test pass rate
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI publication · SQLite 3.40.1 from scratch · OCaml · maximum reasoning effort · 272-test recommended subset in public harness; exact publication test selection and API snapshot not stated
Visual Basic test pass rate
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI publication · SQLite 3.40.1 from scratch · Visual Basic · maximum reasoning effort · 272-test recommended subset in public harness; exact publication test selection and API snapshot not stated
Vals17 related benchmarks · 19 results
Show 13 more resultsHide 13 results
Immigration
Source: Vals AI
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
Router Index
Source: Vals AI
SAGE
Source: Vals AI
SRE Bench
Source: Vals AI

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · BullshitBench by Peter Gostev, MIT (licence) · Deep20Bench edition 1.1, Patrick Heusser. Results CC BY 4.0; native question scores and fraction-to-percent success rates. (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Arcophos. HealthBench Hard Leaderboard. https://healthbenchhard.ai. CC BY 4.0. Source document linked on each result. (licence) · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.

Around the web

  • Models | OpenAI API
    GPT-6.1 Terra A fast, efficient model for visual reasoning, precise computer use, and clear, natural …GPT-6.1 Terra A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. Model ID gpt-6.1-terra Reasoning nonelowmediumhighxhighmax Input price $1 / Input MTok Ou…

    developers.openai.com

    Docs
  • What is GPT? Everything you need to know | Zapier
    ## What is GPT? GPT is a family of AI models built by OpenAI. It …## What is GPT? GPT is a family of AI models built by OpenAI. It stands for Generative Pre-trained Transformer, which is basically a description of what the AI models do and how they work (I'll dig i…

    zapier.com

  • OpenAI makes GPT-4 generally available
    GPT-4 can generate text (including code) and accept image and text inputs -- an improvement …GPT-4 can generate text (including code) and accept image and text inputs -- an improvement over GPT-3.5, its predecessor, which only accepted text -- and performs at "human level" on various profess…

    finance.yahoo.com

  • OpenAI
    In 2020, OpenAI announced GPT-3, a language model trained on large internet datasets. GPT-3 is …In 2020, OpenAI announced GPT-3, a language model trained on large internet datasets. GPT-3 is aimed at natural language answering questions, but it can also translate between languages and coherentl…

    en.wikipedia.org

  • OpenAI brings its GPT-4.1 models to ChatGPT
    2 min read OpenAI is releasing its GPT-4.1 and GPT-4.1 mini AI models in ChatGPT, …2 min read OpenAI is releasing its GPT-4.1 and GPT-4.1 mini AI models in ChatGPT, the company announced in a post on X Wednesday. The GPT-4.1 models should help software engineers who are using ChatG…

    finance.yahoo.com

  • OpenAI brings its GPT-4.1 models to ChatGPT
    OpenAI launched GPT-4.1 and GPT-4.1 mini in April, but only released the models through its …OpenAI launched GPT-4.1 and GPT-4.1 mini in April, but only released the models through its developer-facing API. At the time, the company faced criticism from the AI research community for shipping …

    finance.yahoo.com

  • OpenAI brings its GPT-4.1 models to ChatGPT
    OpenAI launched GPT-4.1 and GPT-4.1 mini in April, but only released the models through its …OpenAI launched GPT-4.1 and GPT-4.1 mini in April, but only released the models through its developer-facing API. At the time, the company faced criticism from the AI research community for shipping …

    au.finance.yahoo.com

  • ChatGPT
    OpenAI models are released in four tiers: Luna, Terra, Sol, and Astra. Some older OpenAI …OpenAI models are released in four tiers: Luna, Terra, Sol, and Astra. Some older OpenAI models had variants called "mini" or "nano", such as GPT-5 mini and GPT-5 nano, with nano versions accessible …

    en.wikipedia.org

  • Introducing ChatGPT | OpenAI
    Image 1: Diagram showing the three-step methodology behind the training of ChatGPT. ChatGPT is fine-tuned …Image 1: Diagram showing the three-step methodology behind the training of ChatGPT. ChatGPT is fine-tuned from a model in the GPT‑3.5 series, which finished training in early 2022. You can learn more…

    openai.com

  • GPT-5 is here | OpenAI
    GPT‑5 excels at writing, research, analysis, coding, and problem-solving. It delivers more accurate, professional responses …GPT‑5 excels at writing, research, analysis, coding, and problem-solving. It delivers more accurate, professional responses and feels like collaborating with a smart, thoughtful colleague. Learn how …

    openai.com

Also known as: aws-mantle/gpt-6-luna, azure/eu/gpt-6-luna, azure/gpt-6-luna, azure/gpt-6-luna-2026-09-22, azure/us/gpt-6-luna, azure_ai/gpt-6-luna, bedrock_mantle/openai.gpt-6-luna, chatgpt/gpt-6-luna, databricks/databricks-gpt-6-luna, github_copilot/gpt-6-luna, global.openai.gpt-6-luna, gmi/openai/gpt-6-luna, gpt-6 luna, gpt-6-luna-low, gpt-6-luna-max, gpt-6-luna-medium, gpt-6-luna-pro, gpt-6-luna@eu, openai-gpt-6-luna, openai.gpt-6-luna, openai/gpt-6-luna, openai/gpt-6-luna-batch, openai/gpt-6-luna-fast, openai/gpt-6-luna-pro, openai/gpt-6-luna-pro:batch, openai/gpt-6-luna:batch, opencode_go/gpt-6-luna, perplexity/openai/gpt-6-luna, us.openai.gpt-6-luna

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works