BroadRouter

Gemma 3 27B API pricing

Updated

Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Gemma 3 27B is DeepInfra at USD 0.08 per 1M input tokens and USD 0.16 per 1M output tokens. The median across 6 standard prices is USD 0.1095 / USD 0.25. Each price is read from the provider's own pricing page.

Google · slug gemma-3-27b-it · up to 198,000 tokens of context · 6 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 27B directly?

Google publishes no price for Gemma 3 27B on its own API that we could find, so this page compares hosts only.

Gemma 3 27B model facts

Facts from Google's model card for google/gemma-3-27b-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 27B: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes, with gated access. google/gemma-3-27b-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", 12 .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 27.4 billion (27,432,406,640)Hugging Face model API, checked 2026-11-16
Quote
“"safetensors": { "total": 27432406640 }”
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": "2025-03-01T19:10:19.000Z"”

Gemma 3 27B 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 2.7× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Gemma 3 27B API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1DeepInfra cheapest
google/gemma-3-27b-it
Notes and source quote
“$0.08 in $0.16 out / 1M tokens”
USD 0.08not publishedUSD 0.16USD 0.10131,072FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
2Novita AI
google/gemma-3-27b-it
Notes and source quote
“Gemma 3 27B 96K $0.119 /Mt $0.2 /Mt”
USD 0.119not publishedUSD 0.20USD 0.139298,304not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
3Venice
google-gemma-3-27b-it
Notes and source quote
“| Google Gemma 3 27B Instruct | `google-gemma-3-27b-it` | $0.12 | $0.20 | — | — | Private |”
USD 0.12not publishedUSD 0.20USD 0.14198,000FP8Venice page
checked 2026-11-15
re-checked 2026-11-16
4Featherless
google/gemma-3-27b-it
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.1 / CACHED $0.08 / OUTPUT $0.3”
USD 0.10USD 0.08USD 0.30USD 0.1532,768FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
5Parasail
Notes and source quote
“Gemma 3 27B $0.08 $0.45 $0.04”
USD 0.08USD 0.04USD 0.45USD 0.1725not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
6Amazon Bedrock
Notes and source quote

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

“Gemma 3 27B $ 0.23 $ 0.38”
USD 0.23not publishedUSD 0.38USD 0.2675not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot
google/gemma-3-27b-it
Notes and source quote

Flex service tier (0.8× standard).

“Flex (0.8×) $0.064 $0.128”
USD 0.064not publishedUSD 0.128USD 0.08131,072FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra priority
google/gemma-3-27b-it
Notes and source quote

Priority service tier (1.5× standard).

“Priority (1.5×) $0.12 $0.24”
USD 0.12not publishedUSD 0.24USD 0.15131,072FP8DeepInfra 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 27B 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 27B, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
DeepInfraUSD 10.08USD 21.60USD 158.40
Novita AIUSD 14.31USD 31.56USD 232.20
VeniceUSD 14.40USD 31.80USD 234.00
FeatherlessUSD 13.32USD 27.06exceeds context
ParasailUSD 13.14USD 23.07USD 123.30
Amazon BedrockUSD 27.54USD 60.90USD 448.20

For the support chatbot, the cheapest price (DeepInfra, USD 10.08 a month) saves USD 3.74 against the median (USD 13.81). For the coding agent the gap is USD 81.00 a month (40% lower). The winner changes with the workload: Parasail wins the cache-heavy agent, DeepInfra the chatbot.

Which Gemma 3 27B provider is cheapest for your traffic?

DeepInfra has the lowest input price (USD 0.08) and the lowest output price (USD 0.16), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

Gemma 3 27B: 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 0.10 cheapestUSD 0.10 cheapestUSD 0.10 cheapest
Novita AI (no cache price)USD 0.1392USD 0.1392USD 0.1392
Venice (no cache price)USD 0.14USD 0.14USD 0.14
FeatherlessUSD 0.15USD 0.1425USD 0.1365
ParasailUSD 0.1725USD 0.1575USD 0.1455
Amazon Bedrock (no cache price)USD 0.2675USD 0.2675USD 0.2675

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.

2 of 6 providers publish a cached-input price below the input price: Featherless (20% off), Parasail (50% off). DeepInfra, Novita AI, Venice and Amazon Bedrock publish none, so cached tokens there bill at the input price.

Context windows differ: 198,000 tokens at Venice; 131,072 tokens at DeepInfra; 98,304 tokens at Novita AI; 32,768 tokens at Featherless. Parasail and Amazon Bedrock do not state one. The cheapest row is not always the one that fits a long prompt.

What does Gemma 3 27B 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 27B:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.017DeepInfra
Arabic MSAUSD 0.027DeepInfra
HindiUSD 0.022DeepInfra
ChineseUSD 0.054DeepInfra
CodeUSD 0.023DeepInfra

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 27B's (USD 0.10 blended):

Google models priced closest to Gemma 3 27B
ModelCheapest inputCheapest outputMax contextProviders
Gemma 3 12BUSD 0.05USD 0.15131,0724
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
Gemma 3 4BUSD 0.04USD 0.08131,0723

Priced closest from other makers: Ministral 3 3B (Mistral AI, USD 0.10) · GPT OSS Safeguard 20B (OpenAI, USD 0.1025) · Mistral Small 3.2 24B Instruct (Mistral AI, USD 0.1062).

Compare Gemma 3 27B with

Also compared: vs Gemma 4 31B · vs Mistral Small 3.2 24B Instruct · vs Gemma 3 12B.

Every Gemma 3 27B 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 27B API cost per token?

From USD 0.08 per 1M input tokens (USD 0.00000008 per token) and USD 0.16 per 1M output tokens (USD 0.00000016 per token) at the lowest standard prices we found. The median of 6 standard prices is USD 0.1095 input and USD 0.25 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 27B?

Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra, ranked on a blend of 3 input tokens to 1 output token (USD 0.10 per 1M). For input alone the lowest price is USD 0.08 (DeepInfra and 1 other, tied); for output alone, USD 0.16 (DeepInfra). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does Google sell Gemma 3 27B on its own API?

Google publishes no price for Gemma 3 27B 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 0.08 / USD 0.16 per 1M tokens.

Does Gemma 3 27B have cached input pricing?

2 of 6 standard prices include one. The lowest is USD 0.04 per 1M at Parasail; the median is USD 0.06. Providers without one bill cached input at the input price. What cached input means.

What is the Gemma 3 27B context window?

Up to 198,000 tokens. 3 standard prices come with less, down to 32,768 tokens (Featherless, Novita AI and DeepInfra). 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 27B?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 123.30 a month at Parasail, USD 204.30 at the median price and USD 448.20 at Amazon Bedrock. Try your own numbers.

Is there a batch, flex or priority price for Gemma 3 27B?

Yes: flex / spot from DeepInfra at USD 0.064 / USD 0.128; priority from DeepInfra at USD 0.12 / USD 0.24 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 27B free to use through an API?

No provider in our data lists a free price for Gemma 3 27B 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 27B open source, with open weights, and what is its licence?

Google publishes the weights on Hugging Face as google/gemma-3-27b-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 27B have?

Google's model card does not state a total that we found. Hugging Face counts about 27.4 billion (27,432,406,640) parameters in the published weight files of google/gemma-3-27b-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 27B with the OpenAI SDK?

BroadNet does not serve Gemma 3 27B. 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-3-27b-it). Each provider page quotes the provider's docs with a check date.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity