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

Gemini 4 Neon

gemini-4-neonby Google
Try in Chat

Gemini 4 Neon, Google's fast reasoning model, close to Gemini 4 Carbon on coding, reasoning and agentic tasks at lower latency and cost, with a 1M-token context window and long decodes.

Context

1.05M

Max output

66K

Price per million tokens

$3in$0.15cached$15out

Speed

273 tok/s

Released

Nov 2026

Waterfall

  1. 1
    Gemini via Experiential Cloud$3/$1599.9% up273 tok/s7.92s
  2. 2
    Vertex AI via Experiential Cloud$3/$1599.9% up--

Quickstart

I want you to route my LLM calls for "gemini-4-neon" 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-4-neon" 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

Streaming

Streaming

Sending an unsupported field? See error referenceGemini docs

Providers serving this model2
Status
Gemini via Experiential Cloudexperiential273 tok/s7.92s99.9%#1 / 21.05M66K$3$15cache$0.15Write 5m: $3-no dataactivemeasured
Vertex AI via Experiential Cloudexperientialno datano data99.9%#2 / 21.05M66K$3$15cache$0.15Write 5m: $3-no dataactive-
Release notes