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 3 9B

Open

Mid-size Gemma 3, fits on a single consumer GPU while keeping vision support.

Gemma 3 9B is a efficient AI model from Google. It costs $0.090 per million input tokens and $0.090 per million output tokens (blended $0.090/M), with a 128,000-token context window.

INPUT
$0.090/M
per million input tokens
OUTPUT
$0.090/M
per million output tokens
BLENDED 70/30
$0.090/M
unchanged since 3 May
CONTEXT
128,000
tokens
What it is good at
  • Single-GPU deployable
  • Vision
  • Open weights
Typical use cases
  • On-device / on-prem chat
  • Fine-tune base

Benchmarks

vs. best public score
MMLU71%
Multitask academic knowledge across 57 subjects.
Graduate-level science questions, "Google-proof".
MATH55%
High-school competition math problems.
Python function synthesis from docstrings.
LMArena Elo1170 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 3 9B cost?

Gemma 3 9B costs $0.090 per million input tokens and $0.090 per million output tokens, for a blended reference rate of $0.090 per million tokens.

What is Gemma 3 9B's context window?

Gemma 3 9B supports up to 128,000 tokens of context in a single request.

What is Gemma 3 9B best for?

Gemma 3 9B is well suited to Single-GPU deployable, Vision and Open weights.

Who makes Gemma 3 9B?

Gemma 3 9B is developed and served by Google.

Terms used on this page