Gemma 3N E4B Instruct

LLM
Google

Gemma 3N E4B Instruct is a multimodal chat model from Google designed for text, image, and audio understanding. It supports structured outputs and offers a 32,768-token context window.

Context tokens

32,768

Output tokens

8,192

Training cutoff

Jun 1, 2024

Released

Jun 26, 2025

Schema

Each image is encoded to 256 tokens, so including multiple images can consume context quickly. The underlying model also understands audio, but audio input is not available through Together.ai's Chat Completions API, so only text and images are accepted here.

Schema documentation

Capabilities

Tool use
Structured output
Multimodal

Supported input media

image
text

Supported tools

  • Google Maps

    Grounding with Google Maps connects the generative capabilities of Gemini with the rich, factual, and up-to-date data of Google Maps. This feature enables developers to easily incorporate location-aware functionality into their applications. When a user query has a context related to Maps data, the Gemini model leverages Google Maps to provide factually accurate and fresh answers that are relevant to the user's specified location or general area.

  • Google Search

    Grounding with Google Search connects the Gemini model to real-time web content and works with all available languages. This allows Gemini to provide more accurate answers and cite verifiable sources beyond its knowledge cutoff.

  • Seclai Content Tools

    Inspect source documents connected to your account. Includes tools for loading full content, reading character ranges, searching within documents, viewing stats, and listing available content sources. When a source_connection_content_version_id is provided in agent run metadata it is used as the default. Otherwise the model can discover content via list_content_sources.

  • Seclai Knowledge Base

    Search your knowledge bases using semantic similarity. Includes search_knowledge_base and list_knowledge_bases. When a knowledge_base_id is provided in the prompt or agent run metadata it is used as the default. Otherwise the model can discover available knowledge bases at runtime.

  • Seclai Memory Banks

    Manage persistent memory across agent runs. Includes tools for listing memory banks, writing entries, searching memory via semantic similarity, and loading entries in chronological order. Supports two memory types: 'conversation' (speaker-attributed turns) and 'general' (freeform text). Use key to organize entries by topic, session, or user.

  • Seclai Web Tools

    Fetch web pages and search the web from within agent prompt calls. Includes seclai_web_fetch for retrieving page content in markdown, HTML, or plain text, and seclai_web_search for finding relevant pages with content snippets.

Pricing

TypeCreditsUnits
Input0.80Credits per 1k tokens
Output1.60Credits per 1k tokens

Variants

No variants available for this model.

Try This Model

Write a prompt and experiment with Gemma 3N E4B Instruct in the model experiments page. You can compare it with other models side by side.