cashcrown // Models

Gemma 3 / Gemma 4

we serve it

// 01Measured parameters

Loading measurements…

// 02Best for

summaries, classification, extraction, cheap tasks at scale

// 03Where in our routing

The OpenClaw router picks a model per task — the cheapest that can carry it. This model is:

summarization · primaryfast answers · fallbackclassification · fallback

// 04Where it works

// 05Try this model

Run this model on your own prompt — in a safe sandbox (PII masked, zero retention).

Sandbox: PII masked before the cloud, zero retention, per-IP limits.

// 06What we build with it

RecipeDoc Intelligence RecipeRank Sentinel ProductRank Sentinel

// 07FAQ

What is Gemma 3 / Gemma 4 best for?

A light, fast family — our default for summaries and high-volume tasks at low cost. Best for: summaries, classification, extraction, cheap tasks at scale.

Do you use Gemma 3 / Gemma 4 in production?

Yes — we serve it in production through the OpenClaw router, with PII masked before the cloud and measured parameters (see the live stat band).

Where does Gemma 3 / Gemma 4 sit in your routing?

The OpenClaw router picks this model for tasks: summarization (primary), fast answers (fallback), classification (fallback).

// //Other models

DeepSeek-V4 Mistral Large 3 Qwen3 / Qwen3-Coder GLM-5 / GLM-4.7

← model atlas Build with us

cashcrown // Models

Gemma 3 / Gemma 4

we serve it

// 01Measured parameters

Loading measurements…

// 02Best for

summaries, classification, extraction, cheap tasks at scale

// 03Where in our routing

The OpenClaw router picks a model per task — the cheapest that can carry it. This model is:

summarization · primaryfast answers · fallbackclassification · fallback

// 04Where it works

// 05Try this model

Run this model on your own prompt — in a safe sandbox (PII masked, zero retention).

Sandbox: PII masked before the cloud, zero retention, per-IP limits.

// 06What we build with it

RecipeDoc Intelligence RecipeRank Sentinel ProductRank Sentinel

// 07FAQ

What is Gemma 3 / Gemma 4 best for?

A light, fast family — our default for summaries and high-volume tasks at low cost. Best for: summaries, classification, extraction, cheap tasks at scale.

Do you use Gemma 3 / Gemma 4 in production?

Yes — we serve it in production through the OpenClaw router, with PII masked before the cloud and measured parameters (see the live stat band).

Where does Gemma 3 / Gemma 4 sit in your routing?

The OpenClaw router picks this model for tasks: summarization (primary), fast answers (fallback), classification (fallback).

// //Other models

DeepSeek-V4 Mistral Large 3 Qwen3 / Qwen3-Coder GLM-5 / GLM-4.7

← model atlas Build with us