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

Gemini 3.5 Flash

gemini-3.5-flashby GeminiZDR enforceable
Try in Chat

Context

1.05M

Max output

66K

Price per million tokens

$1.50in$0.15cached$9out

Speed

254 tok/s

Released

May 2026

Waterfall

  1. 1
    Vertex AI via Experiential Cloud$1.50/$9100% up214 tok/s1.44s
  2. 2
    Gemini via Experiential Cloud$1.50/$999.9% up254 tok/s1.83s
  3. 3
    Experiential Cloud$1.50/$999.9% up--

Quickstart

I want you to route my LLM calls for "gemini-3.5-flash" 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 "gemini-3.5-flash" 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, video, pdf, audio

Sampling

Temperature0-2Top-p0-1Stop sequences*

Tools & structure

ToolsStructured output

Reasoning

Reasoningminimal · low · medium · highDefaultmedium

Streaming

Streaming

Sending an unsupported field? See error referenceVertex AI docs

Benchmarks8
BenchmarkScoreSource
MMLU-Propublic leaderboard · Aug 202690.0%public leaderboard · Aug 2026
LiveBenchpublic leaderboard · Aug 202674.6%public leaderboard · Aug 2026
AIME 2025public leaderboard · Aug 202696.7%public leaderboard · Aug 2026
AIME 2026public leaderboard · Aug 202695.0%public leaderboard · Aug 2026
Humanity's Last Examvendor reported · Aug 202640.2%vendor reported · Aug 2026
MATH-500public leaderboard · Aug 202696.4%public leaderboard · Aug 2026
LMArena EloLMArena · Aug 20261483LMArena · Aug 2026
Terminal-Benchvendor reported · Aug 202676.2vendor reported · Aug 2026
Providers serving this model3
Status
Experiential Cloudexperientialno datano data99.9%#2 / 31.05M66K$1.50$9cache$0.15Write (uniform rate): $0.23-no dataactive-
Gemini via Experiential Cloudexperiential254 tok/s1.83s99.9%#1 / 31.05M66K$1.50$9cache$0.15-no dataactivemeasured
Vertex AI via Experiential Cloudexperiential214 tok/s1.44s100%#3 / 31.05M66K$1.50$9cache$0.15Write (uniform rate): $0.23-no dataactivemeasured
Release notes