Gemma 3 12B vs Gemma 3 4B API pricing
Updated
Gemma 3 12B: USD 0.05 input, USD 0.15 output per 1M tokens (DeepInfra and 1 other). Gemma 3 4B: USD 0.04 input, USD 0.08 output per 1M tokens (Amazon Bedrock). At 3 input tokens per output token, Gemma 3 12B costs 50% more than Gemma 3 4B (USD 0.075 vs USD 0.05 per 1M).
How do Gemma 3 12B and Gemma 3 4B differ on price?
- Cheapest input price: Gemma 3 4B USD 0.04 against USD 0.05 per 1M tokens, so Gemma 3 12B costs 1.25× as much (25% more).
- Cheapest output price: Gemma 3 4B USD 0.08 against USD 0.15 per 1M tokens, so Gemma 3 12B costs 1.88× as much (88% more).
- Among the 201 indexed models, Gemma 3 12B ranks 11th cheapest and Gemma 3 4B 4th on the 3:1 blend.
- No input:output mix changes the answer: Gemma 3 4B is cheaper at every mix before cache discounts.
- Neither model has a standard price with a cached-input discount, so prompt caching does not lower either bill.
- Both state a context window of up to 131,072 tokens.
- Gemma 3 12B has 4 providers with a standard price, 1 more than Gemma 3 4B; 3 providers sell both (DeepInfra, Featherless and Amazon Bedrock).
- On one account, DeepInfra charges USD 0.075 for Gemma 3 12B (its cheapest price) and USD 0.0625 for Gemma 3 4B (1.25× its cheapest price) at 3:1, tied with 1 other provider for the lowest combined price among the providers that sell both.
- Shopping around matters more for Gemma 3 12B: its dearest standard price is 5.3× its cheapest, against 1.25× for Gemma 3 4B.
- For the one-developer coding agent preset, the gap is USD 291.60 a year in Gemma 3 4B's favour (Gemma 3 12B USD 103.50 a month, Gemma 3 4B USD 79.20).
- Per character of input, Gemma 3 12B costs 1.25× as much as Gemma 3 4B in every measured language, because both use the Gemma 3 27B tokenizer.
Gemma 3 12B and Gemma 3 4B 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.
| Price | Gemma 3 12B | Gemma 3 4B |
|---|---|---|
| Model page | Gemma 3 12B Google · 4 providers | Gemma 3 4B Google · 3 providers |
| Cheapest standard price, blended 3:1 | USD 0.075 USD 0.05 in / USD 0.15 out at DeepInfra and 1 other DeepInfra page checked 2026-11-14 | USD 0.05 lower USD 0.04 in / USD 0.08 out at Amazon Bedrock Amazon Bedrock page checked 2026-11-14 |
| Cheapest input | USD 0.05 DeepInfra source | USD 0.04 lower Amazon Bedrock source |
| Cheapest cached input | No standard price lists a cache price; cached tokens bill at the input price. | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 0.15 DeepInfra source | USD 0.08 lower Amazon Bedrock source |
| Maker's own API | Google 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 price | USD 0.07 / USD 0.22 input / output, 4 prices | USD 0.05 / USD 0.10 input / output, 3 prices |
| Context window | 131,072 tokens, largest stated; from 32,768 at some providers | 131,072 tokens, largest stated; from 32,768 at some providers |
| Providers with a standard price | 4 | 3 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do Gemma 3 12B and Gemma 3 4B 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).
| Workload | Gemma 3 12B | Gemma 3 4B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 7.20 DeepInfra | USD 5.04 Amazon Bedrock | USD 2.16 Gemma 3 4B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 14.25 DeepInfra | USD 10.80 Amazon Bedrock | USD 3.45 Gemma 3 4B lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 103.50 DeepInfra | USD 79.20 Amazon Bedrock | USD 24.30 Gemma 3 4B lower |
Gemma 3 4B is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 43% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
Gemma 3 4B 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 12B's, so the input:output ratio never changes the answer.
| Input : output tokens | Gemma 3 12B | Gemma 3 4B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.125 DeepInfra | USD 0.07 lower Amazon Bedrock |
| 1 : 1 | USD 0.10 DeepInfra | USD 0.06 lower Amazon Bedrock |
| 3 : 1 (the site’s blend) | USD 0.075 DeepInfra | USD 0.05 lower Amazon Bedrock |
| 10 : 1 (retrieval, long prompts) | USD 0.05909 DeepInfra | USD 0.04364 lower Amazon Bedrock |
| 30 : 1 (agents, big contexts) | USD 0.05323 DeepInfra | USD 0.04129 lower Amazon Bedrock |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Gemma 3 12B and Gemma 3 4B 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 12B (the same one for both, so the gap equals the price gap):
| Content | Gemma 3 12B | Gemma 3 4B |
|---|---|---|
| English | USD 0.011 DeepInfra | USD 0.0087 lower Amazon Bedrock |
| Arabic MSA | USD 0.017 DeepInfra | USD 0.014 lower Amazon Bedrock |
| Egyptian Arabic | USD 0.017 DeepInfra | USD 0.014 lower Amazon Bedrock |
| Hindi | USD 0.014 DeepInfra | USD 0.011 lower Amazon Bedrock |
| Chinese | USD 0.034 DeepInfra | USD 0.027 lower Amazon Bedrock |
| Spanish | USD 0.011 DeepInfra | USD 0.0090 lower Amazon Bedrock |
| Code | USD 0.015 DeepInfra | USD 0.012 lower Amazon Bedrock |
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
- Gemma 3 12B API pricing: all 4 providers and other tiers.
- Gemma 3 4B API pricing: all 3 providers and other tiers.
- Cost calculator with Gemma 3 12B and Gemma 3 4B preloaded
- Gemma 3 token counter
- Prompt caching calculator
More comparisons: Gemma 4 12B IT vs Gemma 3 12B · Gemma 3 27B vs Gemma 3 12B · every Gemma 3 12B comparison · every Gemma 3 4B comparison · all 662 price comparisons
Questions
Is Gemma 3 12B cheaper than Gemma 3 4B?
No. On a blend of 3 input tokens to 1 output token, Gemma 3 4B costs USD 0.05 per 1M tokens and Gemma 3 12B USD 0.075, at each model's cheapest standard price. For input alone, Gemma 3 4B is cheaper (USD 0.04 against USD 0.05 per 1M); for output alone, Gemma 3 4B is (USD 0.08 against USD 0.15). This compares price only, not quality.
What do Gemma 3 12B and Gemma 3 4B cost per 1M tokens?
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. Gemma 3 4B: from USD 0.04 input and USD 0.08 output at Amazon Bedrock; median of 3 standard prices USD 0.05 / USD 0.10. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Gemma 3 12B and Gemma 3 4B?
3 providers have a standard price for both: DeepInfra (USD 0.075 and USD 0.0625 at 3:1), Featherless (USD 0.075 and USD 0.0625 at 3:1), Amazon Bedrock (USD 0.14 and USD 0.05 at 3:1). The first 2 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 0.075 and USD 0.05.
Which is cheaper for a coding agent or a chatbot, Gemma 3 12B or Gemma 3 4B?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 103.50 a month on Gemma 3 12B (DeepInfra) against USD 79.20 on Gemma 3 4B (Amazon Bedrock), a difference of USD 24.30. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 7.20 a month on Gemma 3 12B (DeepInfra) against USD 5.04 on Gemma 3 4B (Amazon Bedrock), a difference of USD 2.16. 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 12B and Gemma 3 4B change?
Gemma 3 4B 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 12B's, so the input:output ratio never changes the answer.
Do Gemma 3 12B and Gemma 3 4B have cached input pricing?
Gemma 3 12B: no standard price lists a cached-input discount. Gemma 3 4B: 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 12B or Gemma 3 4B?
Both go up to 131,072 tokens on the providers that state it.