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

GPT-5.5

gpt-5.5by GPT
Try in Chat

Context

1.05M

Max output

128K

Price per million tokens

$5in$0.50cached$30out

Speed

60 tok/s

Released

Apr 2026

Waterfall

  1. 1
    OpenAI via Experiential Cloud$5/$3099.8% up60 tok/s900ms
  2. 2N
    Novita via Experiential Cloud$5/$3099.9% up--

Quickstart

I want you to route my LLM calls for "gpt-5.5" 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-5.5" 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

Temperature0-2 · reasoning off onlyTop-p0-1

Tools & structure

ToolsStrict toolsParallel tool callsStructured output

Reasoning

Reasoninglow · medium · high · xhighDefaultmedium

Streaming

Streaming

Sending an unsupported field? See error referenceOpenAI docs

Benchmarks9
BenchmarkScoreSource
MMLU-Propublic leaderboard · Aug 202688.9%public leaderboard · Aug 2026
GPQA Diamondvendor reported · Aug 202693.6%vendor reported · Aug 2026
SWE-bench Verifiedpublic leaderboard · Aug 202680.6%public leaderboard · Aug 2026
LiveBenchpublic leaderboard · Aug 202680.2%public leaderboard · Aug 2026
AIME 2025public leaderboard · Aug 2026100.0%public leaderboard · Aug 2026
AIME 2026public leaderboard · Aug 2026100.0%public leaderboard · Aug 2026
Humanity's Last Examvendor reported · Aug 202641.4%vendor reported · Aug 2026
LMArena EloLMArena · Aug 20261466LMArena · Aug 2026
Terminal-Benchvendor reported · Aug 202682.7vendor reported · Aug 2026
Providers serving this model4
Status
Azure Foundry via Experiential Cloudexperientialgpt-5.5no datano data99.9%#3 / 31.05M128K$5$30cache$0.50-no dataactiveestimated
OpenAI via Experiential Cloudexperiential60 tok/s900ms99.8%#1 / 31.05M128K$5$30cache$0.50Write 5m: $6.25-no dataactiveestimated
NNovita via Experiential Cloudexperientialno datano data99.9%#2 / 31.05M128K$5Pro 5% · Max 10% · Ultra 20% off$30cache$0.50-no dataactive-
Azure Foundrygpt-5.5-2026-04-24deployed 2026-04-24no datano data99.9%-1.05M128K$5≈$30≈cache$0.50≈-no dataactiveestimated
Release notes