YFarmXIntelligence for an accelerating worldBriefings
YFarmX
YFarmX

AI Desk · Model Identity

OpenAI: GPT-5.6 Luna

openai/gpt-5.6-luna · OpenAIDeclared and measured agree
Tokenizer lineage (measured)
GPT
Evidence confidence
Very high
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree.
Declared tokenizer tag
GPT
Entered catalogue
9 July 2026
Last tested
21 August 2026
Measurement
Measured
Evidence
  • ✓ exact tokenizer signature shared with 31 models
  • ✓ API-surface contract identical to a group member
Compare with OpenAI: GPT-5.6 Terra

Download JSONReport a correction

Identity statement

OpenAI: GPT-5.6 Luna is OpenAI's model. Its measured tokenizer sits with the GPT group, which is evidence that it builds on the GPT tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against OpenAI's authorship of the model itself.

Evidence stack

Signals of different kinds, weighed together
SignalResultReference
Tokenizer signatureExact match with 31 other modelstk_d1411c9d
API surfaceIdentical contract to 9 other entriesapi_b333d4ee
Context and output1,050,000 context · 128,000 max outputdeclared
Reasoning contractOptional · efforts max, xhigh, high, medium, low, none · default mediumdeclared
Serving providers observedOpenAImeasured 21 August 2026

Shares this fingerprint

Exact signature first; template-boundary shifts of the same signature beneath
OpenAI: GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613exact · 50/50OpenAI: GPT-4.1openai/gpt-4.1exact · 50/50OpenAI: GPT-4.1 Miniopenai/gpt-4.1-miniexact · 50/50OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nanoexact · 50/50OpenAI: GPT-4o-miniopenai/gpt-4o-miniexact · 50/50OpenAI: GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18exact · 50/50OpenAI: GPT-5openai/gpt-5exact · 50/50OpenAI: GPT-5 Nanoopenai/gpt-5-nanoexact · 50/50OpenAI: GPT-5.1openai/gpt-5.1exact · 50/50OpenAI: GPT-5.1-Codexopenai/gpt-5.1-codexexact · 50/50OpenAI: GPT-5.1-Codex-Maxopenai/gpt-5.1-codex-maxexact · 50/50OpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-miniexact · 50/50OpenAI: GPT-5.2openai/gpt-5.2exact · 50/50OpenAI: GPT-5.2-Codexopenai/gpt-5.2-codexexact · 50/50OpenAI: GPT-5.3-Codexopenai/gpt-5.3-codexexact · 50/50OpenAI: GPT-5.4openai/gpt-5.4exact · 50/50OpenAI: GPT-5.4 Miniopenai/gpt-5.4-miniexact · 50/50OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nanoexact · 50/50OpenAI: GPT-5.5openai/gpt-5.5exact · 50/50OpenAI: GPT-5.6 Solopenai/gpt-5.6-solexact · 50/50OpenAI: GPT-5.6 Terraopenai/gpt-5.6-terraexact · 50/50OpenAI: GPT Chat Latestopenai/gpt-chat-latestexact · 50/50OpenAI: gpt-oss-120bopenai/gpt-oss-120bexact · 50/50OpenAI: gpt-oss-20bopenai/gpt-oss-20bexact · 50/50OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20bexact · 50/50OpenAI: o3 Miniopenai/o3-miniexact · 50/50OpenAI: o3 Mini Highopenai/o3-mini-highexact · 50/50OpenAI: o4 Miniopenai/o4-miniexact · 50/50OpenAI: o4 Mini Highopenai/o4-mini-highexact · 50/50Thinking Machines: Inklingthinkingmachines/inklingexact · 50/50Thinking Machines: Inkling Smallthinkingmachines/inkling-smallexact · 50/50

Closest measured models

Agreement across the mutually clean test strings
OpenAI: GPT-5 Nanoopenai/gpt-5-nano50/50 · 100%OpenAI: gpt-oss-20bopenai/gpt-oss-20b50/50 · 100%OpenAI: gpt-oss-120bopenai/gpt-oss-120b50/50 · 100%OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b50/50 · 100%OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nano50/50 · 100%OpenAI: GPT-4o-miniopenai/gpt-4o-mini50/50 · 100%

Click a row to open the full comparison.

The measured fingerprint

Marginal prompt-token cost of each test string, grouped by script
All 50 rows

English and whitespace

en-prose14
en-long17
spaces-203
spaces-603
tabs-203
newlines-204
mixed-ws6

Digits

digits-93
digits-124
digits-3010
digits-sep7
float-long9

CJK

zh-common12
zh-long17
zh-rare20
ja-kana10
ja-kanji13
ko11

Other scripts

ru11
ar11
he10
hi11
th11
el14

Emoji

emoji-basic8
emoji-skin13
emoji-zwj-family11
emoji-zwj-x333
emoji-flags16
emoji-prof20

Rare Unicode

math31
boxdraw27
combining11
cjk-ext-b13
surrogates40
zalgo35
rtl-mix5

Code

py-code25
py-indent15
json20
html16
regex44
camel6
snake6

Repetition and encodings

rare-word-x531
repeat-tok22
base6434
hex11
url17
uuid27

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 6 prompt tokens.

Declared record

What the catalogue claims about this model

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Modalities
text+image+file->text
Declared tokenizer
GPT
Prompt price
$0.20 / M tokens
Completion price
$1.20 / M tokens

Supported parameters

include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetools

defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry

History

Every observation, kept as taken
  • 9 July 2026Enters the OpenRouter catalogue declared as GPT.
  • 21 August 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
  • 21 August 2026YFarmX assessment: consistent with the GPT family, very high confidence.

Cite this page as the evidence record for OpenAI: GPT-5.6 Luna: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.