Claude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MClaude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/M
Google
Google
Efficient

Gemma 2 27B

Open

Largest Gemma 2, superseded by Gemma 3 but still common where the 2 family is well-tested.

Gemma 2 27B is a efficient AI model from Google. It costs $0.270 per million input tokens and $0.270 per million output tokens (blended $0.270/M), with a 8,000-token context window.

INPUT
$0.270/M
per million input tokens
OUTPUT
$0.270/M
per million output tokens
BLENDED 70/30
$0.270/M
unchanged since 3 May
CONTEXT
8,000
tokens
What it is good at
  • Open weights
  • 8K context
  • Wide HF/inference support
Typical use cases
  • Existing Gemma 2 deployments
  • Fine-tune base

Benchmarks

vs. best public score
MMLU75%
Multitask academic knowledge across 57 subjects.
Graduate-level science questions, "Google-proof".
MATH49%
High-school competition math problems.
Python function synthesis from docstrings.
LMArena Elo1218 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Google

See all 24

Frequently asked questions

How much does Gemma 2 27B cost?

Gemma 2 27B costs $0.270 per million input tokens and $0.270 per million output tokens, for a blended reference rate of $0.270 per million tokens.

What is Gemma 2 27B's context window?

Gemma 2 27B supports up to 8,000 tokens of context in a single request.

What is Gemma 2 27B best for?

Gemma 2 27B is well suited to Open weights, 8K context and Wide HF/inference support.

Who makes Gemma 2 27B?

Gemma 2 27B is developed and served by Google. It was released in Jun 2024.

Terms used on this page