Gemma 3 4B

Provider: Google AI US

Input price
$0.04
/ 1M tokens
Output price
$0.08
/ 1M tokens
Cache price
$0.02
/ 1M tokens (read)
Context
131K tokens
Max output 16K tokens

Overview

Google's Gemma 3 4B is a budget budget model targeting lightweight multilingual chat and vision tasks within a 131072 token context window.

Strengths

  • Processes vision and text inputs
  • Outputs up to 16384 tokens
  • Supports 131072 token context window
  • Features $0.02/1M cached input pricing

Best use cases

  • Lightweight vision and text processing
  • Multilingual translation tasks
  • Cost-sensitive rapid prototyping

Pricing position

Input costs $0.04 and output costs $0.08 per million tokens, matching Llama 3.1 8B while undercutting Gemma 3 12B.

Caveats

No free tier is available, and output pricing is slightly higher than Mistral Small 3.

Notes drafted by an LLM from the figures on this page (2026-11-15) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
16K tokens
Knowledge cutoff
2024-08-31
Listed on OpenRouter
2025-03-13
Tracked since
2026-05-08
Last updated
2026-11-15

Features

Image inputJSON output

Price history

  • 2026-11-15 Price change $0.04 / $0.05 → $0.04 / $0.08

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.01
1M (small app) 1 0.5 $0.08
10M (mid scale) 10 5 $0.80
100M (large) 100 50 $8.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Google AI

Similar-priced models

Source: OpenRouter API (google/gemma-3-4b-it)