BroadRouter

Gemma 3 27B vs Gemma 3 12B API pricing

Updated

Gemma 3 27B: USD 0.08 input, USD 0.16 output per 1M tokens (DeepInfra). Gemma 3 12B: USD 0.05 input, USD 0.15 output per 1M tokens (DeepInfra and 1 other). At 3 input tokens per output token, Gemma 3 27B costs 33% more than Gemma 3 12B (USD 0.10 vs USD 0.075 per 1M).

Gemma 3 27B and Gemma 3 12B are neighbouring sizes of the same Google generation (27B and 12B parameters, by name). Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do Gemma 3 27B and Gemma 3 12B differ on price?

Gemma 3 27B and Gemma 3 12B prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Gemma 3 27B and Gemma 3 12B API prices compared
PriceGemma 3 27BGemma 3 12B
Model pageGemma 3 27B
Google · 6 providers
Gemma 3 12B
Google · 4 providers
Cheapest standard price, blended 3:1USD 0.10
USD 0.08 in / USD 0.16 out at DeepInfra
DeepInfra page checked 2026-11-14
USD 0.075 lower
USD 0.05 in / USD 0.15 out at DeepInfra and 1 other
DeepInfra page checked 2026-11-14
Cheapest inputUSD 0.08
DeepInfra source
USD 0.05 lower
DeepInfra source
Cheapest cached inputUSD 0.04
Parasail source
No standard price lists a cache price; cached tokens bill at the input price.
Cheapest outputUSD 0.16
DeepInfra source
USD 0.15 lower
DeepInfra source
Maker's own APIGoogle publishes no paid standard price on its own API that we found.Google publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.1095 / USD 0.25
input / output, 6 prices
USD 0.07 / USD 0.22
input / output, 4 prices
Context window198,000 tokens, largest stated; from 32,768 at some providers131,072 tokens, largest stated; from 32,768 at some providers
Providers with a standard price64

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do Gemma 3 27B and Gemma 3 12B cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Gemma 3 27B and Gemma 3 12B
WorkloadGemma 3 27BGemma 3 12BDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 10.08
DeepInfra
USD 7.20
DeepInfra
USD 2.88
Gemma 3 12B lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 21.60
DeepInfra
USD 14.25
DeepInfra
USD 7.35
Gemma 3 12B lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 123.30
Parasail
USD 103.50
DeepInfra
USD 19.80
Gemma 3 12B lower

Gemma 3 12B is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 52% more than the cheaper one.

Does the cheaper model change with your input:output ratio?

Gemma 3 12B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Gemma 3 27B's, so the input:output ratio never changes the answer.

Price per 1M tokens of Gemma 3 27B and Gemma 3 12B at different input:output mixes
Input : output tokensGemma 3 27BGemma 3 12B
1 : 3 (long answers)USD 0.14
DeepInfra
USD 0.125 lower
DeepInfra
1 : 1USD 0.12
DeepInfra
USD 0.10 lower
DeepInfra
3 : 1 (the site’s blend)USD 0.10
DeepInfra
USD 0.075 lower
DeepInfra
10 : 1 (retrieval, long prompts)USD 0.08727
DeepInfra
USD 0.05909 lower
DeepInfra
30 : 1 (agents, big contexts)USD 0.08258
DeepInfra
USD 0.05323 lower
DeepInfra

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Gemma 3 27B and Gemma 3 12B cost per character in other languages?

Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Gemma 3 27B tokenizer for Gemma 3 27B (the same one for both, so the gap equals the price gap):

Input cost per 1M characters by language, Gemma 3 27B and Gemma 3 12B
ContentGemma 3 27BGemma 3 12B
EnglishUSD 0.017
DeepInfra
USD 0.011 lower
DeepInfra
Arabic MSAUSD 0.027
DeepInfra
USD 0.017 lower
DeepInfra
Egyptian ArabicUSD 0.027
DeepInfra
USD 0.017 lower
DeepInfra
HindiUSD 0.022
DeepInfra
USD 0.014 lower
DeepInfra
ChineseUSD 0.054
DeepInfra
USD 0.034 lower
DeepInfra
SpanishUSD 0.018
DeepInfra
USD 0.011 lower
DeepInfra
CodeUSD 0.023
DeepInfra
USD 0.015 lower
DeepInfra

From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.

Check it on your own traffic

More comparisons: Gemma 4 31B vs Gemma 3 27B · Mistral Small 3.2 vs Gemma 3 27B · Gemma 4 12B IT vs Gemma 3 12B · Gemma 3 12B vs Gemma 3 4B · every Gemma 3 27B comparison · every Gemma 3 12B comparison · all 662 price comparisons

Questions

Is Gemma 3 27B cheaper than Gemma 3 12B?

No. On a blend of 3 input tokens to 1 output token, Gemma 3 12B costs USD 0.075 per 1M tokens and Gemma 3 27B USD 0.10, at each model's cheapest standard price. For input alone, Gemma 3 12B is cheaper (USD 0.05 against USD 0.08 per 1M); for output alone, Gemma 3 12B is (USD 0.15 against USD 0.16). This compares price only, not quality.

What do Gemma 3 27B and Gemma 3 12B cost per 1M tokens?

Gemma 3 27B: from USD 0.08 input and USD 0.16 output at DeepInfra; median of 6 standard prices USD 0.1095 / USD 0.25. Gemma 3 12B: from USD 0.05 input and USD 0.15 output at DeepInfra and 1 other; median of 4 standard prices USD 0.07 / USD 0.22. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Gemma 3 27B and Gemma 3 12B?

3 providers have a standard price for both: DeepInfra (USD 0.10 and USD 0.075 at 3:1), Featherless (USD 0.15 and USD 0.075 at 3:1), Amazon Bedrock (USD 0.2675 and USD 0.14 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.10 and USD 0.075.

Which is cheaper for a coding agent or a chatbot, Gemma 3 27B or Gemma 3 12B?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 123.30 a month on Gemma 3 27B (Parasail) against USD 103.50 on Gemma 3 12B (DeepInfra), a difference of USD 19.80. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 10.08 a month on Gemma 3 27B (DeepInfra) against USD 7.20 on Gemma 3 12B (DeepInfra), a difference of USD 2.88. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Gemma 3 27B and Gemma 3 12B change?

Gemma 3 12B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Gemma 3 27B's, so the input:output ratio never changes the answer.

Do Gemma 3 27B and Gemma 3 12B have cached input pricing?

Gemma 3 27B from USD 0.04 per 1M cached input tokens (Parasail; 2 of 6 standard prices list a discount). Gemma 3 12B: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, Gemma 3 27B or Gemma 3 12B?

Gemma 3 27B: up to 198,000 tokens, against 131,072 for Gemma 3 12B, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity