MultimodalAPI only

Gemma 3n E4B Instructed

Google

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: Multimodal
Access: API only
Released: June 26, 2025
License: proprietary
Parameters: 8000000000
Context window: 32,000 tokens
Knowledge cutoff: June 1, 2024
Output speed: 42 tok/s
Latency (TTFT): 0.43s
API pricing: $20.00 in · $40.00 out / 1M tokens

Capabilities

Function callingStructured output

Benchmarks

Reasoning

23.7

Coding

HumanEval	75
LiveCodeBench	13.2
MBPP	63.6

Math

AIME 2025	11.6
MGSM	67

General

MMLU	64.9
MMLU-Pro	50.6

Compare Gemma 3n E4B Instructed with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all Gemma 3n E4B Instructed alternatives →