Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocs
Sign in
Continue with GoogleContinue with GitHub
or
Models

GPT-5.6 Luna

gpt-5.6-lunaby GPT
Try in Chat

Context

1.05M

Max output

128K

Price per million tokens

$0.20in$0.020cached$1.20out

Speed

60 tok/s

Released

Jul 2026

Waterfall

  1. 1
    OpenAI via Experiential Cloud$0.20/$1.2099.9% up60 tok/s900ms
  2. 2N
    Novita via Experiential Cloud$0.20/$1.2099.9% up--

Quickstart

I want you to route my LLM calls for "gpt-5.6-luna" through the Experiential gateway instead of calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL and key swap. Please:

1. Point the client at https://api.experientiallabs.jp/v1 as the base URL.
2. Securely ask me for my API key. Authenticate with my Experiential key from EXPLABS_API_KEY. I can create one under Settings -> API Keys.
3. Use the model id "gpt-5.6-luna" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key, leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my Experiential credits.

Tell me which files you changed.
CapabilitiesAccepts text, pdf, image

Sampling

Temperature*0-2 · reasoning off onlyTop-p*0-1

Tools & structure

ToolsStrict toolsParallel tool callsStructured output

Reasoning

Reasoningnone · low · medium · high · xhigh · maxDefaultmedium

Streaming

Streaming

Sending an unsupported field? See error referenceOpenAI docs

Benchmarks8
BenchmarkScoreSource
MMLU-Propublic leaderboard · Aug 202686.5%public leaderboard · Aug 2026
GPQA Diamondvendor reported · Aug 202692.3%vendor reported · Aug 2026
SWE-bench Verifiedpublic leaderboard · Aug 202693.0%public leaderboard · Aug 2026
LiveBenchpublic leaderboard · Aug 202673.6%public leaderboard · Aug 2026
AIME 2025public leaderboard · Aug 202699.2%public leaderboard · Aug 2026
MATH-500public leaderboard · Aug 202693.7%public leaderboard · Aug 2026
LMArena EloLMArena · Aug 20261429LMArena · Aug 2026
Terminal-Benchvendor reported · Aug 202684.7vendor reported · Aug 2026
Providers serving this model4
Status
Azure Foundry via Experiential Cloudexperientialgpt-5.6-lunano datano data99.9%#3 / 31.05M128K$0.20$1.20cache$0.020-no dataactiveestimated
OpenAI via Experiential Cloudexperiential60 tok/s900ms99.9%#1 / 31.05M128K$0.20$0.40 past 272K$1.20$1.80 past 272Kcache$0.020$0.040 past 272KWrite 5m: $0.25$0.50 past 272K-no dataactiveestimated
NNovita via Experiential Cloudexperientialno datano data99.9%#2 / 31.05M128K$0.20$0.40 past 272KPro 5% · Max 10% · Ultra 20% off$1.20$1.80 past 272Kcache$0.020$0.040 past 272KWrite (uniform rate): $0.25$0.50 past 272K-no dataactive-
Azure Foundrygpt-5.6-luna-2026-07-09deployed 2026-07-09no datano data99.9%-1.05M128K$0.20≈$1.20≈cache$0.020≈-no dataactiveestimated
Release notes