How much does Gemma 3 12B cost per million tokens?

$0.075 per million input tokens and $0.1625 per million output tokens, as listed on OpenRouter on October 22, 2026.

Does Gemma 3 12B support prompt caching?

OpenRouter lists no cached input price for this model, so assume every input token is billed at the full rate.

Is there a cheaper model as good as Gemma 3 12B?

gpt-oss-20b scores 38.5 on the LLMBenchmark Index, within two points of Gemma 3 12B or above it, and costs $0.15 per million output tokens.

Gemma 3 12B API pricing

As of October 22, 2026, Google Gemma 3 12B costs $0.075 per million input tokens and $0.1625 per million output tokens, the median of 2 providers on OpenRouter.

Gemma 3 12B benchmarks and specs · Every Google model's price

Input, per million tokens$0.075
Output, per million tokens$0.1625
Cached input, per millionNo cache price listed
Context window131K tokens
Max output16K tokens
Output speedNot measured

What a request costs

Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.

Cost of three workloads on Gemma 3 12B
Workload	Tokens	One request	1,000 requests	Fits the context window
Chat turn	1K input + 500 output tokens	$0.0002	$0.156	Yes
Repository review	50K input + 3K output tokens	$0.0042	$4.24	Yes
Agent loop	200K input + 10K output tokens	$0.017	$16.63	No, it would need splitting
Solved coding task	One SWE-bench Verified attempt, divided by the share that succeed	Not computable	Not computable

Price history

The price of Gemma 3 12B here is the median across 2 providers on OpenRouter, so we do not track price changes for it.

Cheaper models as good as Gemma 3 12B

Models within two points of Gemma 3 12B or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.

gpt-oss-20b$0.15 Overall 38.5 against 28.0 · 8% cheaper output

Gemma 3 12B pricing questions

How much does Gemma 3 12B cost per million tokens?: $0.075 per million input tokens and $0.1625 per million output tokens, as listed on OpenRouter on October 22, 2026.
Does Gemma 3 12B support prompt caching?: OpenRouter lists no cached input price for this model, so assume every input token is billed at the full rate.
Is there a cheaper model as good as Gemma 3 12B?: gpt-oss-20b scores 38.5 on the LLMBenchmark Index, within two points of Gemma 3 12B or above it, and costs $0.15 per million output tokens.
Has the price of Gemma 3 12B changed?: The price of Gemma 3 12B here is the median across 2 providers on OpenRouter, so we do not track price changes for it.