Gemma 4 12B (Reasoning) API Pricing

Google · released 2026-06-03 · merges 2 reasoning-effort tiers

Benchmarks shown for the highest-scoring reasoning tier. Merged tiers: Gemma 4 12B (Reasoning), Gemma 4 12B (Non-reasoning).

Pricing

$0.10
input / 1M tokens
0.010¢ / 1K
$0.30
output / 1M tokens
0.030¢ / 1K
$0.15
blended / 1M tokens
0.015¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.014¢
RAG query4,000 in / 500 out0.055¢
Long document summary50,000 in / 1,000 out0.53¢
Code review of a 2k-line file30,000 in / 2,000 out0.36¢
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$4.20

Cost = (input tokens ÷ 1,000,000 × $0.10) + (output tokens ÷ 1,000,000 × $0.30).

Benchmarks

14.2
Intelligence
#183 of 533
31.0
Coding
#111 of 197
Math
139
Tokens/sec
1.31s
Time to first token

Similar intelligence, lower price

ModelIntelligenceBlended $/1M
Qwen3.5 4B (Reasoning)13.1$0.06
Nemotron 3.5 Lightning12.9$0.095
GPT-5 nano (high)13.0$0.138

Leaderboard neighbours

ModelIntelligenceBlended $/1M
Gemini 2.5 Pro Preview (May' 25)14.5$3.438
K-EXAONE (Reasoning)14.4
ERNIE 5.0 Thinking Preview14.3
Gemma 4 12B (Reasoning)14.2$0.15
Mistral Medium 3.514.2$3.00
Nova 2.0 Pro Preview (medium)14.2$3.438
Grok Code Fast 114.1

More from Google

ModelIntelligenceBlended $/1M
Gemini 3.8 Flash (high)40.9$1.50
Gemini 3.7 Flash (medium)39.6$1.50
Gemini 3.6 Flash (high)34.0$1.50
Gemini 3.5 Flash (medium)33.6$3.375
Gemini 3.1 Pro Preview29.7$4.50
Gemini 3 Pro Preview (high)28.0$4.50
Gemini 3 Flash Preview (Reasoning)26.3$1.125
Gemini 3.5 Flash-Lite22.2$0.85

Count tokens & estimate cost for Gemma 4 12B (Reasoning) See Gemma 4 12B (Reasoning) on the leaderboard

Source: Artificial Analysis · last synced 2026-09-22

FAQ

Who develops Gemma 4 12B (Reasoning)?

Gemma 4 12B (Reasoning) is developed by Google, released 2026-06-03.

How much does Gemma 4 12B (Reasoning) cost per million tokens?

Gemma 4 12B (Reasoning) costs $0.10 per 1M input tokens and $0.30 per 1M output tokens ($0.15 blended), per Artificial Analysis's official pricing data.

How does Gemma 4 12B (Reasoning) rank on benchmarks?

Gemma 4 12B (Reasoning) scores 14.2 on the Artificial Analysis Intelligence Index, ranking #183 of 533 models we track.

Is there a cheaper model with similar intelligence to Gemma 4 12B (Reasoning)?

Yes — Qwen3.5 4B (Reasoning) scores similar intelligence (13.1) at $0.06/1M blended, versus $0.15/1M for Gemma 4 12B (Reasoning).

Where does this data come from?

Pricing and benchmark data for Gemma 4 12B (Reasoning) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.