DeepInfra
Efficient

Gemma 2 9B (DI)

Compact

Mid-size Gemma 2, popular open model in the 9B class for on-prem chat and fine-tuning.

Gemma 2 9B (DI) is a efficient AI model from DeepInfra. It costs $0.0600 per million input tokens and $0.0600 per million output tokens (blended $0.0600/M), with a 8,000-token context window.

Profile inherited from upstream Gemma 2 9B ↗ — this is a hosted variant of the same open-weights model.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.0600/M
per million input tokens
OUTPUT
$0.0600/M
per million output tokens
BLENDED 70/30
$0.0600/M
unchanged since 3 May
CONTEXT
8,000
tokens

Hand-maintained from DeepInfra's published pricing; no check date on record.

What it is good at
  • Single-GPU friendly
  • Open weights
  • Wide ecosystem
Typical use cases
  • On-prem chat
  • Fine-tune base

Benchmarks

vs. best public score
Scores inherited from Gemma 2 9B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU71.3%
Multitask academic knowledge across 57 subjects. Source: Google DeepMind (self-reported), MMLU (5-shot), read 2026-11-10.
Graduate-level science questions, "Google-proof". No source recorded yet.
MATH45%
High-school competition math problems. No source recorded yet.
HumanEval40.2%
Python function synthesis from docstrings. Source: Google DeepMind (self-reported), HumanEval pass@1, read 2026-11-10.
LMArena Elo1267 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from DeepInfra

See all 11 →

Frequently asked questions

How much does Gemma 2 9B (DI) cost?

Gemma 2 9B (DI) costs $0.0600 per million input tokens and $0.0600 per million output tokens, for a blended reference rate of $0.0600 per million tokens.

What is Gemma 2 9B (DI)'s context window?

Gemma 2 9B (DI) supports up to 8,000 tokens of context in a single request.

What is Gemma 2 9B (DI) best for?

Gemma 2 9B (DI) is well suited to Single-GPU friendly, Open weights and Wide ecosystem.

Who makes Gemma 2 9B (DI)?

Gemma 2 9B (DI) is developed and served by DeepInfra. It was released in Jun 2024.

Terms used on this page