Skip to content
AI Atlas
ModelActiveClosed / proprietaryIdentity probable

gpt-5.6-luna

OpenAIfamily · GPT 5.6developers.openai.com/api/docs/models/gpt-5.6-lu

GPT-5.6 model optimized for cost-sensitive workloads

Open in Graph
data quality73

Updated 5 h ago · first seen 11 Sept 2026

model_01M293V76ZRTWE98GJGHREAFGX

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
None recorded — closed weightsofficial_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
gpt-5-6-lunagpt-5-6-luna-highgpt-5-6-luna-lowgpt-5-6-luna-mediumgpt-5-6-luna-non-reasoninggpt-5-6-luna-xhighgpt-5.6-lunaopenai/gpt-5.6-lunaIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
5Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Closed / proprietary— weights not available; 7 dimensions unknown.

Weights are not available; the model is reachable only through an API or a product.

  • Weights

    No

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    —

  • Redistribution

    —

  • Derivatives

    —

dimensions marked null are unknown, not false

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Knowledge cutoff

Source:OpenAI Platform docsT1observed 15 h agohigh

Official page
developers.openai.com/api/docs/models/gpt-5.6-luna

Source:OpenAI Platform docsT1observed 15 h agohigh

API model id

Source:OpenAI Platform docsT1observed 15 h agohigh

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Architecture

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Capabilities

Modalities

Modalities
imagetext
Input
textimage
Output
text

Capabilities

  • Tool calling

    Yes

    OpenAI Platform docs · T1

  • Structured output

    Yes

    OpenAI Platform docs · T1

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Yes

    OpenAI Platform docs · T1

  • Audio

    Unavailable

  • Fine-tuning available

    No

    OpenAI Platform docs · T1

Context window

Source:OpenRouter public model & pricing listingT2observed 5 h agomedium

Max output

Source:OpenAI Platform docsT1observed 15 h agohigh

Knowledge cutoff

Source:OpenAI Platform docsT1observed 15 h agohigh

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Benchmarks88

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=v4.0 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv4.0reasoning_effortmaxconditions differ across rows → partially comparable10non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
Terminal-Benchagentic · accuracy · variant=v2.1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv2.1reasoning_effortmaxconditions differ across rows → partially comparable12non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Agentic Codingcoding · average score · variant=Agentic CodingOfficial boardvariantAgentic Codingrelease2026-06-251−28.8 ptvs DeepSeek-V4.1-Flash25 Jun 2026livebench.aiT2
LiveBench Codingcoding · average score · variant=CodingOfficial boardvariantCodingrelease2026-06-251−3.46 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
SciCodecoding · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoning_effortmaxconditions differ across rows → partially comparable10−9.49 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoning_effortmaxversion4.3conditions differ across rows → partially comparable12−15.9vs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBenchgeneral · global_averageOfficial boardrelease2026-06-251−9.86 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
LiveBench Data Analysisgeneral · average score · variant=Data AnalysisOfficial boardvariantData Analysisrelease2026-06-251−4.94 ptvs gpt-6-astra25 Jun 2026livebench.aiT2
LiveBench Languagegeneral · average score · variant=LanguageOfficial boardvariantLanguagerelease2026-06-251−18.1 ptvs Claude Fable 525 Jun 2026livebench.aiT2
LiveBench Instruction Followinginstruction-following · average score · variant=IFOfficial boardvariantIFrelease2026-06-251−21.3 ptvs Gemini 3.8 Flash25 Jun 2026livebench.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoning_effortmaxconditions differ across rows → partially comparable12−19.7 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Mathematicsmath · average score · variant=MathematicsOfficial boardvariantMathematicsrelease2026-06-251−9.81 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
MMMU-Promultimodal · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoning_effortxhighconditions differ across rows → partially comparable12−8.33 ptvs gpt-6-astraobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoning_effortmaxconditions differ across rows → partially comparable6non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond6−5.15 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2
LiveBench Reasoningreasoning · average score · variant=ReasoningOfficial boardvariantReasoningrelease2026-06-251−7.01 ptvs gpt-6-astra25 Jun 2026livebench.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 88 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing5

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inCache writeOutput / 1MBatch in / outNative unitsStatusObservedSource
OpenAI APIcheapest outputopenai/gpt-5.6-luna:batch1.05Mout 128K$0.01———active6 h agosince 11 Sept 2026openrouter.aiT2
OpenRouteropenai/gpt-5.6-luna:batch1.05Mout 128K$0.01———active2 h agosince 12 Sept 2026openrouter.aiT2
OpenAI APIgpt-5.6-luna—$0.02$0.25$0.10 / $0.60flex_input_per_mtok=0.1flex_output_per_mtok=0.6fast_mode_input_per_mtok=0.4+5active7 h agosince 11 Sept 2026developers.openai.comT1
OpenAI APIopenai/gpt-5.6-luna1.05Mout 128K$0.02$0.25——active6 h agosince 11 Sept 2026openrouter.aiT2
OpenRouteropenai/gpt-5.6-luna1.05Mout 128K$0.02$0.25——active2 h agosince 12 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of gpt-5.6-luna$0$0.50$1$1.5Sept 26Sept 26Sept 26Sept 26Sept 26OpenAI API: first observed → $1.2 · 11 Sept 2026OpenAI API: $1.2 → $0.60 · 11 Sept 2026OpenRouter: first observed → $1.2 · 12 Sept 2026OpenRouter: $1.2 → $0.60 · 12 Sept 2026
  • OpenAI API
  • OpenRouter
  • OpenRouter$1.2 → $0.6012 Sept 2026
  • OpenRouterfirst observed $1.212 Sept 2026
  • OpenAI API$1.2 → $0.6011 Sept 2026
  • OpenAI APIfirst observed $1.211 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of gpt-5.6-luna$0$0.05$0.10$0.15$0.20$0.25Sept 26Sept 26Sept 26Sept 26Sept 26OpenAI API: first observed → $0.20 · 11 Sept 2026OpenAI API: $0.20 → $0.10 · 11 Sept 2026OpenRouter: first observed → $0.20 · 12 Sept 2026OpenRouter: $0.20 → $0.10 · 12 Sept 2026
  • OpenAI API
  • OpenRouter
  • OpenRouter$0.20 → $0.1012 Sept 2026
  • OpenRouterfirst observed $0.2012 Sept 2026
  • OpenAI API$0.20 → $0.1011 Sept 2026
  • OpenAI APIfirst observed $0.2011 Sept 2026

Versions & Artifacts0

Version history

Context window2 changes

11 Sept 2026→11 Sept 2026→12 Sept 2026current

Knowledge cutofffirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline30

Full timeline →

Change history56

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 11 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 11 Sept 2026 24 claims in force

Release date
9 Jul 2026
Openness
proprietary
Context window
1.05M tokens
Max output
128K tokens
Knowledge cutoff
Feb 2026
Modalities
image, text
Input modalities
text, image
Output modalities
text
Tokenizer
GPT
API model id
gpt-5.6-luna
Capabilities
streaming, structured_outputs, function_calling, file_search, image_input, web_search, prompt_caching
Default snapshot
gpt-5.6-luna
File input
Yes
Fine-tuning available
No
Aa median output tokens per second
104.4
Openrouter id
openai/gpt-5.6-luna
Reasoning
Yes
Snapshots
gpt-5.6-luna
Structured output
Yes
Supported parameters
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools
Tool calling
Yes
Vision
Yes
56 claims · 28 properties7 conflicting

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
9 Jul 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Opennessopenness6

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
proprietary → currentcurrentArtificial AnalysisT2mediumdeterministic
proprietary → currentcurrentArtificial AnalysisT2mediumdeterministic
proprietary → currentcurrentArtificial AnalysisT2mediumdeterministic
proprietary → currentcurrentArtificial AnalysisT2mediumdeterministic
proprietary → currentcurrentArtificial AnalysisT2mediumdeterministic
proprietary → currentcurrentOpenAI Platform docsT1highdeterministic

Context windowcontext_length8conflicting claims

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
1.05M tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic
1M tokens → currentcurrentArtificial AnalysisT2mediumdeterministic
1M tokens → currentcurrentArtificial AnalysisT2mediumdeterministic
1M tokens → currentcurrentArtificial AnalysisT2mediumdeterministic
1M tokens → supersededArtificial AnalysisT2mediumdeterministic
1M tokens → currentconflictingArtificial AnalysisT2mediumdeterministic
1M tokens → currentcurrentArtificial AnalysisT2mediumdeterministic
1.05M tokens → currentcurrentOpenAI Platform docsT1conflicteddeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
128K tokens → currentcurrentOpenAI Platform docsT1highdeterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
ValueValid from → toStatusSourceConfidenceExtractor
Feb 2026 → currentcurrentOpenAI Platform docsT1highdeterministic

Modalitiesmodalities2conflicting claims

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
document, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentcurrentOpenAI Platform docsT1conflicteddeterministic

Input modalitiesmodalities_input6conflicting claims

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
document, image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
image, text → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
text, image → currentcurrentOpenAI Platform docsT1conflicteddeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenAI Platform docsT1highdeterministic

Tokenizertokenizer1

Claim history for Tokenizer
ValueValid from → toStatusSourceConfidenceExtractor
GPT → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

API model idapi_model_id1

Claim history for API model id
ValueValid from → toStatusSourceConfidenceExtractor
gpt-5.6-luna → currentcurrentOpenAI Platform docsT1highdeterministic

Official pageofficial_url1

Claim history for Official page
ValueValid from → toStatusSourceConfidenceExtractor
https://developers.openai.com/api/docs/models/gpt-5.6-luna → currentcurrentOpenAI Platform docsT1highdeterministic

Aa context windowaa_context_window1

Claim history for Aa context window
ValueValid from → toStatusSourceConfidenceExtractor
1,000,000 tokens → currentcurrentArtificial AnalysisT2mediumdeterministic

Aa opennessaa_openness1

Claim history for Aa openness
ValueValid from → toStatusSourceConfidenceExtractor
proprietary → currentcurrentArtificial AnalysisT2mediumdeterministic

Capabilitiescapabilities1

Claim history for Capabilities
ValueValid from → toStatusSourceConfidenceExtractor
streaming, structured_outputs, function_calling, file_search, image_input, web_search, prompt_caching → currentcurrentOpenAI Platform docsT1highdeterministic

Default snapshotdefault_snapshot1

Claim history for Default snapshot
ValueValid from → toStatusSourceConfidenceExtractor
gpt-5.6-luna → currentcurrentOpenAI Platform docsT1highdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
GPT-5.6 model optimized for cost-sensitive workloads → currentcurrentOpenAI Platform docsT1highdeterministic

File inputfile_input1

Claim history for File input
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Fine-tuning availablefine_tuning_available1

Claim history for Fine-tuning available
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentOpenAI Platform docsT1highdeterministic

Aa median output tokens per secondmetric.aa_median_output_tokens_per_second6

Claim history for Aa median output tokens per second
ValueValid from → toStatusSourceConfidenceExtractor
108.2 → currentcurrentArtificial AnalysisT2mediumdeterministic
108.3 → currentcurrentArtificial AnalysisT2mediumdeterministic
104.4 → currentcurrentArtificial AnalysisT2mediumdeterministic
109.8 → currentcurrentArtificial AnalysisT2mediumdeterministic
104.6 → currentcurrentArtificial AnalysisT2mediumdeterministic
111.9 → currentcurrentArtificial AnalysisT2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
openai/gpt-5.6-luna → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
ValueValid from → toStatusSourceConfidenceExtractor
9 Jul 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning6

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentArtificial AnalysisT2mediumdeterministic
Yes → currentcurrentArtificial AnalysisT2mediumdeterministic
Yes → currentcurrentArtificial AnalysisT2mediumdeterministic
No → currentcurrentArtificial AnalysisT2mediumdeterministic
Yes → currentcurrentArtificial AnalysisT2mediumdeterministic
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Snapshotssnapshots1

Claim history for Snapshots
ValueValid from → toStatusSourceConfidenceExtractor
gpt-5.6-luna → currentcurrentOpenAI Platform docsT1highdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenAI Platform docsT1highdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenAI Platform docsT1highdeterministic

Visionvision1

Claim history for Vision
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenAI Platform docsT1highdeterministic

Weights availableweights_available1

Claim history for Weights available
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

29

Source tiers

T1T216 / 13

Freshest observation

5 h ago

Conflicts

7 flagged

Source documents 7

Source documents
SourceDocumentTypeTierLast observedSnapshots
OpenAI Platform docsdevelopers.openai.com/api/docs/deprecations.md model_docsT1· Official1 h ago2
OpenAI Platform docsdevelopers.openai.com/api/docs/pricing.md pricingT1· Official1 h ago2
OpenAI Platform docsdevelopers.openai.com/api/docs/models.md model_docsT1· Official1 h ago1
OpenAI Platform docsdevelopers.openai.com/api/docs/models/gpt-5.6-luna.md model_pageT1· Official15 h ago1
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago11
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary5 h ago2
LiveBenchlivebench.ai/table_2026_06_25.csv leaderboardT2· Quality secondary13 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (73/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →