Gemma 3 27B

Provider: Google AI US

Input price
$0.08
/ 1M tokens
Output price
$0.35
/ 1M tokens
Cache price
$0.04
/ 1M tokens (read)
Context
131K tokens
Max output 118K tokens

Overview

Google's Gemma 3 27B is a mid-tier open weights model targeted at multilingual chat, vision processing, and structured tasks.

Strengths

  • Supports 131k context window and vision inputs
  • Features function calling and native JSON mode
  • Processes over 140 languages natively

Best use cases

  • Multilingual chat applications requiring structured JSON outputs
  • Document analysis tasks utilizing visual inputs
  • Cost-sensitive reasoning and math workloads

Pricing position

Priced at $0.08 input and $0.35 output per million tokens, sitting above the 12B variant ($0.15 out) and below Qwen3 Next 80B ($1.10 out).

Caveats

Offers no free tier and features a smaller 131k context window compared to larger 1M+ context peers.

Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
118K tokens
Knowledge cutoff
2024-08-31
Listed on OpenRouter
2025-03-12
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputFunction callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.03
1M (small app) 1 0.5 $0.26
10M (mid scale) 10 5 $2.55
100M (large) 100 50 $25.50

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Google AI

Similar-priced models

Source: OpenRouter API (google/gemma-3-27b-it)