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

GPT-5

gpt-5by GPTZDR enforceable
Try in Playground

Context

400K

Max output

128K

Price per million tokens

$1.25in$0.13cached$10out

Speed

1046 tok/s

Released

-

Waterfall

  1. 1
    Experiential Cloud$1.25/$10100% up1046 tok/s3.37s
  2. 2
    Azure Foundry via Experiential Cloud$1.25/$1099.9% up--

Quickstart

I want you to route my LLM calls for "gpt-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.ai/v1 as the base URL.
2. Authenticate with my Experiential API key from the EXPLABS_API_KEY environment variable. If it isn't set, stop and tell me to create one under Settings -> API Keys and export it.
3. Use the model id "gpt-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

Sampling

Temperature*0-2Top-p*0-1

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

Benchmarks9
BenchmarkScoreSource
MMLU-ProHugging Face · Aug 202686.3%Hugging Face · Aug 2026
GPQA Diamondvendor reported · Aug 202685.7%vendor reported · Aug 2026
SWE-bench Verifiedvendor reported · Aug 202674.9%vendor reported · Aug 2026
AIME 2025vendor reported · Aug 202694.6%vendor reported · Aug 2026
Humanity's Last Examvendor reported · Aug 202624.8%vendor reported · Aug 2026
MMMUvendor reported · Aug 202684.2%vendor reported · Aug 2026
IFEvalHugging Face · Aug 202687.5%Hugging Face · Aug 2026
LMArena EloLMArena · Aug 20261406LMArena · Aug 2026
Terminal-Benchpublic leaderboard · Aug 202635.2public leaderboard · Aug 2026
Providers serving this model3
Status
Experiential Cloudexperiential1046 tok/s3.37s100%#1 / 2400K128K$1.25Pro 5% · Max 10% · Ultra 20% off$10cache$0.13-no dataactivemeasured
Azure Foundry via Experiential Cloudexperientialgpt-5no datano data99.9%#2 / 2400K128K$1.25$10cache$0.13-no dataactive-
Azure Foundrygpt-5-2025-08-07deployed 2025-08-07no datano data99.9%-400K128K$0.61≈$2.94≈no data≈-no dataactiveestimated
Release notes