Gemma 3 12B IT pricing & specs
Google · released 2025-03-12 · ● verified 2026-10-11
input / 1M$0.05via Novita AI
output / 1M$0.10via Novita AI
context131.1K
max output8.2K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Gemma 3 12B IT |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −20% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −12% |
| Gemma 3 27B IT | $0.08 | $0.16 | 131.1K | +60% |
| Ministral 3 3B | $0.10 | $0.10 | 131.1K | +60% |
| Qwen3.5 9B | $0.10 | $0.15 | 262.1K | +80% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Novita AI | $0.05 | $0.10 |
| DeepInfra | $0.05 | $0.15 |
| Amazon Bedrock | $0.09 | $0.29 |
// faq
How much does Gemma 3 12B IT cost?
Gemma 3 12B IT costs $0.05 per million input tokens and $0.10 per million output tokens (cheapest tracked host: Novita AI). At 50M input and 10M output tokens per month that is about $3.50.
What is the context window of Gemma 3 12B IT?
131.1K tokens, with up to 8.2K output tokens per request.
What are cheaper alternatives to Gemma 3 12B IT?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out) offer the same input types and capabilities for less.
Is Gemma 3 12B IT open weights?
Yes. It is available from 3 tracked hosts; the cheapest is Novita AI at $0.05 input and $0.10 output per million tokens.
// spec sheet
- input / 1M
- $0.05
- output / 1M
- $0.10
- blended (3:1)
- $0.0625
- context
- 131.1K
- max output
- 8.2K
- input types
- text · image
- reasoning
- no
- tool calling
- yes
- structured output
- no
- open weights
- yes
- knowledge cutoff
- 2024-08
- price source
- Novita AI
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Gemma 3 12B IT | $0.05 | $0.10 | $3.50 |
| Gemma 3 27B IT | $0.08 | $0.16 | $5.60 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.