Gemma 2 27B

Provider: Google AI US

Input price
$0.65
/ 1M tokens
Output price
$0.65
/ 1M tokens
Context
8K tokens
Max output 2K tokens

Overview

Gemma 2 27B is a Google AI model, likely positioned as a mid-tier offering within the Gemma family. It targets workloads requiring structured outputs and moderate context understanding. This model emphasizes predictable input and output pricing.

Strengths

  • Features symmetrical input and output pricing at $0.65 per million tokens.
  • Supports JSON mode, ideal for structured data generation and API integration.
  • Offers a competitive output token price compared to many similarly-priced peer models.
  • Suitable for tasks needing a moderate context window of 8192 tokens.
  • Provides a maximum output length of 2048 tokens for reasonably sized responses.

Best use cases

  • Generating structured JSON outputs for programmatic use and data processing.
  • Backend automation requiring consistent data formats from model responses.
  • Content summarization or generation for short to medium-length documents.
  • Building conversational agents that need controlled, structured replies.
  • Extracting specific entities or data points from text in a JSON format.

Pricing position

Priced at $0.65/M tokens for both input and output, Gemma 2 27B is significantly more expensive than its sibling Gemma 3 and 4 models, which start as low as $0.04/M input. However, its output price is competitive, notably lower than peers like Qwen3 Coder Plus ($3.25/M out) or GLM 5 ($1.92/M out), with only R1 Distill Llama 70B ($0.80/M out) being somewhat comparable.

Caveats

The 8192-token context window is modest compared to other Google AI models like Gemma 3 (131072 tokens) or Gemini 2.0 Flash Lite (1048576 tokens), limiting its use for very long documents. This model also does not offer a free tier. For tasks not requiring JSON mode or needing much larger context, other more cost-effective Google AI options are available.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
2K tokens
Knowledge cutoff
2024-06-30
Listed on OpenRouter
2024-07-13
Tracked since
2026-05-08
Last updated
2026-11-10

Features

JSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.10
1M (small app) 1 0.5 $0.98
10M (mid scale) 10 5 $9.75
100M (large) 100 50 $97.50

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Google AI

Similar-priced models

Source: OpenRouter API (google/gemma-2-27b-it)