BroadRouter

Gemma 3 12B API pricing

Updated

Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 tie for the lowest blended standard price for Gemma 3 12B; DeepInfra charges USD 0.05 per 1M input tokens and USD 0.15 per 1M output tokens. The median across 4 standard prices is USD 0.07 / USD 0.22. Each price is read from the provider's own pricing page.

Google · slug gemma-3-12b-it · up to 131,072 tokens of context · 4 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2025-07-09 (17 archived price points, 2 list-price changes): LLM API price history.

Does Google sell Gemma 3 12B directly?

Google publishes no price for Gemma 3 12B on its own API that we could find, so this page compares hosts only.

Gemma 3 12B model facts

Facts from Google's model card for google/gemma-3-12b-it and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

Gemma 3 12B: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes, with gated access. google/gemma-3-12b-it is public, but Hugging Face asks you to request access and accept the terms before you download (gated: manual).Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": "manual", 5 .safetensors files listed”
LicencegemmaGoogle model card metadata, checked 2026-11-16
Quote
“license: gemma”
Parameters in the weight files (Hugging Face count, not the maker's figure)About 12.2 billion (12,187,325,040)Hugging Face model API, checked 2026-11-16
Quote
“"safetensors": { "total": 12187325040 }”
Context length128K tokens input; 8,192 tokens outputGoogle model card, checked 2026-11-16
Quote
“Total input context of 128K tokens for the 4B, 12B, and 27B sizes … Total output context of 8192 tokens”
Input and outputText and images in; text outGoogle model card, checked 2026-11-16
Quote
“Images, normalized to 896 x 896 resolution and encoded to 256 tokens … Generated text in response to the input”
Tool callingNot found on Google's model card when we read itchecked 2026-11-16
First published on Hugging Face (not necessarily the release date)2025-03-01Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2025-03-01T19:11:34.000Z"”

Gemma 3 12B price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 5.3× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Gemma 3 12B API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1DeepInfra tied cheapest
google/gemma-3-12b-it
Notes and source quote
“$0.05 in $0.15 out / 1M tokens”
USD 0.05not publishedUSD 0.15USD 0.075131,072BFLOAT16DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
2Featherless tied cheapest
google/gemma-3-12b-it
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits). No cached price published.

“PRICING: INPUT $0.05 / OUTPUT $0.15”
USD 0.05not publishedUSD 0.15USD 0.07532,768FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
3Amazon Bedrock
Notes and source quote

Table headed "Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)".

“Gemma 3 12B $ 0.09 $ 0.29”
USD 0.09not publishedUSD 0.29USD 0.14not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
4Cloudflare Workers AI
@cf/google/gemma-3-12b-it
Notes and source quote

Cloudflare publishes this USD per-token price alongside the neuron price.

“@cf/google/gemma-3-12b-it $0.345 per M input tokens $0.556 per M output tokens”
USD 0.345not publishedUSD 0.556USD 0.3977not statednot statedCloudflare Workers AI page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot
google/gemma-3-12b-it
Notes and source quote

Flex service tier (0.8× standard).

“Flex (0.8×) $0.04 $0.12”
USD 0.04not publishedUSD 0.12USD 0.06131,072BFLOAT16DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra priority
google/gemma-3-12b-it
Notes and source quote

Priority service tier (1.5× standard).

“Priority (1.5×) $0.075 $0.225”
USD 0.075not publishedUSD 0.225USD 0.1125131,072BFLOAT16DeepInfra page
checked 2026-11-14
re-checked 2026-11-16

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

What does Gemma 3 12B cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Gemma 3 12B, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
DeepInfraUSD 7.20USD 14.25USD 103.50
FeatherlessUSD 7.20USD 14.25exceeds context
Amazon BedrockUSD 13.32USD 25.95USD 188.10
Cloudflare Workers AIUSD 41.06USD 91.14USD 671.04

For the support chatbot, the cheapest price (DeepInfra and 1 other, tied, USD 7.20 a month) saves USD 3.06 against the median (USD 10.26). For the coding agent the gap is USD 42.30 a month (29% lower).

Which Gemma 3 12B provider is cheapest for your traffic?

DeepInfra and Featherless share the lowest input price (USD 0.05) and the lowest output price (USD 0.15), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.

Gemma 3 12B: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
DeepInfra (no cache price)USD 0.075 cheapestUSD 0.075 cheapestUSD 0.075 cheapest
Featherless (no cache price)USD 0.075 cheapestUSD 0.075 cheapestUSD 0.075 cheapest
Amazon Bedrock (no cache price)USD 0.14USD 0.14USD 0.14
Cloudflare Workers AI (no cache price)USD 0.3977USD 0.3977USD 0.3977

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

None of the 4 providers publishes a cached-input discount for Gemma 3 12B, so cache hits do not change the ranking.

Context windows differ: 131,072 tokens at DeepInfra; 32,768 tokens at Featherless. Amazon Bedrock and Cloudflare Workers AI do not state one. The cheapest row is not always the one that fits a long prompt.

What does Gemma 3 12B cost in other languages?

The same text needs a different number of tokens in each language. With the Gemma 3 27B tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Gemma 3 12B:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.011DeepInfra
Arabic MSAUSD 0.017DeepInfra
HindiUSD 0.014DeepInfra
ChineseUSD 0.034DeepInfra
CodeUSD 0.015DeepInfra

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Estimate your own bill

The Google models whose cheapest standard price is closest to Gemma 3 12B's (USD 0.075 blended):

Google models priced closest to Gemma 3 12B
ModelCheapest inputCheapest outputMax contextProviders
Gemma 3 27BUSD 0.08USD 0.16198,0006
Gemma 3 4BUSD 0.04USD 0.08131,0723
Gemma 4 26B A4BUSD 0.07USD 0.34262,14411
gemma-4-31B-it-turboUSD 0.09USD 0.34262,1442
Gemma 4 31BUSD 0.10USD 0.34262,14412
Gemini 2.5 Flash-LiteUSD 0.10USD 0.40—2

Priced closest from other makers: Llama 3.2 1B Instruct (Meta, USD 0.0705) · IBM Granite 4.2 8B (IBM, USD 0.0825) · NVIDIA Nemotron 3.5 Lightning 30B A3B (NVIDIA, USD 0.085).

Compare Gemma 3 12B with

Also compared: vs Gemma 3 27B · vs Gemma 3 4B.

Every Gemma 3 12B price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Gemma 3 12B API cost per token?

From USD 0.05 per 1M input tokens (USD 0.00000005 per token) and USD 0.15 per 1M output tokens (USD 0.00000015 per token) at the lowest standard prices we found. The median of 4 standard prices is USD 0.07 input and USD 0.22 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Gemma 3 12B?

Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 are tied for the lowest price: DeepInfra and Featherless, each USD 0.075 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.05 (DeepInfra and 1 other, tied); for output alone, USD 0.15 (DeepInfra and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does Google sell Gemma 3 12B on its own API?

Google publishes no price for Gemma 3 12B on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is DeepInfra at USD 0.05 / USD 0.15 per 1M tokens.

Does Gemma 3 12B have cached input pricing?

None of the 4 standard prices includes a cached-input price, so budget repeated prompts at the full input price.

What is the Gemma 3 12B context window?

Up to 131,072 tokens. 1 standard price comes with less, down to 32,768 tokens (Featherless). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on Gemma 3 12B?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 103.50 a month at DeepInfra, USD 145.80 at the median price and USD 671.04 at Cloudflare Workers AI. Try your own numbers.

Is there a batch, flex or priority price for Gemma 3 12B?

Yes: flex / spot from DeepInfra at USD 0.04 / USD 0.12; priority from DeepInfra at USD 0.075 / USD 0.225 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is Gemma 3 12B free to use through an API?

No provider in our data lists a free price for Gemma 3 12B as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Is Gemma 3 12B open source, with open weights, and what is its licence?

Google publishes the weights on Hugging Face as google/gemma-3-12b-it, with gated access: Hugging Face asks you to request access and accept the terms before you download. The licence, as the Google model card metadata states it: gemma. Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Google's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

How many parameters does Gemma 3 12B have?

Google's model card does not state a total that we found. Hugging Face counts about 12.2 billion (12,187,325,040) parameters in the published weight files of google/gemma-3-12b-it. That is a file-level count, not the maker's figure, and it can include extra modules (checked 2026-11-16).

How do I call Gemma 3 12B with the OpenAI SDK?

BroadNet does not serve Gemma 3 12B. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: DeepInfra (https://api.deepinfra.com/v1/openai, model google/gemma-3-12b-it). Each provider page quotes the provider's docs with a check date.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity