Gemma 2 27B

Google DeepMindgoogle/gemma-2-27b-itProviders: 1
Inputi$0.65per 1M tokens
Outputi$0.65per 1M tokens
Contexti8K8,192 tokens
ReleasedJul 13, 2024Max output: 2K

Where it stands

Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.

100110120130140150160170$0.01$0.03$0.1$0.3$1$3$10$30$100Overall indexPrice per million tokens, log scale (3 parts input to 1 part output)↖ Cheaper and smarterGemma 2 27B
Scores: Epoch AI (CC BY 4.0). Prices: OpenRouter. View as a table

About this model

Gemma 2 27B is an AI model from Google DeepMind, made available through the API on July 13, 2024. It can read up to 8,192 tokens in one request, roughly 15 pages of text, and write up to 2,048 tokens in a single answer.

Through the API it costs $0.65 per million input tokens and $0.65 per million output tokens. Its pricing puts it among the more affordable models we track, which makes it a good fit for high-volume tasks.

Its weights are openly published (google/gemma-2-27b-it), so it can also be downloaded and run on your own hardware.

Quality scores

Rankings →
122.1Overall index · #125 of 136
  • GPQA DiamondVery hard multiple-choice questions in biology, physics and chemistry, written by PhD experts. Random guessing scores 25%.36.5%#107 of 116
  • AIME mathCompetition-level math problems in the style of the American Invitational Mathematics Examination. Share solved.1.4%#110 of 112

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

Companies that serve this model through an API: 1. Prices per million tokens, cheapest first.

ProviderInputiOutputiContextiUptime (24 h)i
NextBitint4
$0.65$0.658K100.0%

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Use it in your code

Call Gemma 2 27B through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "google/gemma-2-27b-it", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    $0.52
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    $0.033
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    $273

Cost calculator →

Similar-priced alternatives

ModelInputiOutputiContexti
Kimi K2.6Moonshot AI
$0.65$3.41256KCompare with ⇄
Qwen3 Coder PlusAlibaba Qwen
$0.65$3.251MCompare with ⇄
$0.66$1.981MCompare with ⇄
Aion 3.5 MiniAion Labs
$0.70$1.40256KCompare with ⇄
$0.70$0.70128KCompare with ⇄
$0.60$2.40256KCompare with ⇄

News about Google DeepMind

See all →

Frequently asked questions

How much does Gemma 2 27B cost?
Gemma 2 27B costs $0.65 per million input tokens and $0.65 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.52.
What is the context window of Gemma 2 27B?
Gemma 2 27B can read up to 8,192 tokens in one request, about 15 pages of text. It can write up to 2,048 tokens in a single answer.
Is Gemma 2 27B open source?
Yes. Its weights are published (google/gemma-2-27b-it), so you can download it and run it on your own hardware, or use it through one of 1 API providers.
Who makes Gemma 2 27B?
Gemma 2 27B is made by Google DeepMind. It became available through the API on July 13, 2024.
How good is Gemma 2 27B?
Gemma 2 27B has an overall index of 122.1 in Epoch AI’s independent tests, ranking #125 of 136 models we track.
Can Gemma 2 27B read images?
No. Gemma 2 27B only accepts text as input.
What are the alternatives to Gemma 2 27B?
Models with a similar price from other companies include Kimi K2.6, Qwen3 Coder Plus and DeepSeek V4 Pro 0813. You can compare them side by side on this page.