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

GPT-5.4 Mini

gpt-5.4-miniby GPT
Try in Chat

Context

400K

Max output

128K

Price per million tokens

$0.75in$0.075cached$4.50out

Released

-

Waterfall

  1. 1N
    Novita via Experiential Cloud$0.75/$4.5099.9% up--

Quickstart

I want you to route my LLM calls for "gpt-5.4-mini" 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-5.4-mini" 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, image, pdf

Tools & structure

ToolsStrict toolsParallel tool callsStructured output

Reasoning

Reasoningnone · minimal · low · medium · high · xhighDefaultmedium

Streaming

Streaming

Limits

Max output128,000Max-tokens fieldmax_completion_tokens

Sending an unsupported field? See error reference

Benchmarks7
BenchmarkScoreSource
GPQA Diamondvendor reported · Aug 202688.0%vendor reported · Aug 2026
SWE-bench Verifiedpublic leaderboard · Aug 202673.0%public leaderboard · Aug 2026
LiveBenchpublic leaderboard · Aug 202666.4%public leaderboard · Aug 2026
AIME 2026paper · Aug 202635.7%paper · Aug 2026
Humanity's Last Examvendor reported · Aug 202628.2%vendor reported · Aug 2026
LMArena EloLMArena · Aug 20261412LMArena · Aug 2026
Terminal-Benchvendor reported · Aug 202660.0vendor reported · Aug 2026
Providers serving this model3
Status
Azure Foundry via Experiential Cloudexperientialgpt-5.4-minino datano data99.9%#1 / 2400K128K$0.75$4.50cache$0.075-no dataactive-
NNovita via Experiential Cloudexperientialno datano data99.9%#2 / 2400K128K$0.75Pro 5% · Max 10% · Ultra 20% off$4.50cache$0.075-no dataactive-
Azure Foundrygpt-5.4-mini-2026-03-17deployed 2026-03-17no datano data99.9%-400K128K$0.61≈$2.94≈no data≈-no dataactiveestimated
Release notes