Models / Google

Gemma 3n E4B API pricing

$0.20 in, $0.16 out per million tokens.

gemma-3n-e4b-itmanaged routeOpenAI SDK

Price · per million tokens, USD

Get a key
TokensGoogle list priceUplinkSwitchSaving
Input—$0.20—
Cached input—$0.00—
Output—$0.16—
No list price on record. Prices read from the live catalog on 2026-11-16; the page follows the catalog.
Real-model check: Steady since Oct 29

Gemma 3n E4B specs

Context window
8,192 tokens

Gemma 3n E4B: what it is · from Google’s own model page, read 2026-10-29

The larger of Google’s two Gemma 3n models, made for phones, laptops and other low-resource devices. Google’s card says selective parameter activation lets it run at an effective size of 4B parameters, and that Gemma 3n handles text, image, video and audio input and was trained on data in over 140 spoken languages. It is served as gemma-3n-e4b-it at $0.20 input and $0.16 output per million tokens, on the same key as every other model in the catalog.

Gemma 3n E4B
DeveloperGoogle
Parametersan effective 4B, with more in the weights
Context32K tokens on Google’s card; served with an 8,192-token window
Licensethe Gemma Terms of Use
SourceGoogle’s Gemma 3n model card

From Google’s Gemma 3n model card, read 2026-10-29.

curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"gemma-3n-e4b-it","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

Gemma 3n E4B next to Google’s other models · per million tokens, live

ModelHere, in / out1,000 chat turns
Gemma 3n E2B$0.12 / $0.08$0.28
Gemini 2.5 Flash Lite$0.075 / $0.30$0.30
Gemma 3n E4B$0.20 / $0.16$0.48
Gemini 3.1 Flash Lite$0.15 / $0.90$0.75
Gemini 3.1 Flash Lite Preview$0.1875 / $1.125$0.94
Gemini 3.5 Flash Lite$0.225 / $1.875$1.39
Gemma 4 12B$0.40 / $1.20$1.40
Gemini 2.5 Flash$0.30 / $2.50$1.85
Gemini 3 Flash Preview$0.375 / $2.25$1.88
Gemma 4 26B-A4B$0.56 / $1.60$1.92
Gemini 3.8 Flash$0.4925 / $2.25$2.11
Gemini 3.6 Flash$0.4925 / $2.25$2.11
Gemini 3.7 Flash$0.4925 / $2.25$2.11
Gemini 4 Argon$0.60 / $3.00$2.70
Gemma 3 27B$1.20 / $1.20$3.00
Gemini Flash Lite Latest$0.72 / $6.00$4.44
Gemini 2.5 Pro$0.9375 / $7.50$5.63
Gemini 3.1 Pro$1.20 / $7.20$6.00
Gemini 3.1 Pro Preview$1.20 / $7.20$6.00
Gemma 31B Heretic Uncensored$1.50 / $8.25$7.13
Gemini 3.5 Flash$1.50 / $9.00$7.50
Gemma 4 31B$3.00 / $4.00$8.00
Gemini Flash Latest$1.80 / $9.00$8.10
Gemini 4 Carbon$2.3529 / $11.7647$10.59
Gemini 3 Pro Preview$5.00 / $22.50$21.25
Gemini 3.1 PRO Preview LOW$5.00 / $22.50$21.25
Gemini 3.1 PRO Preview Customtools$4.80 / $28.80$24.00
Gemini PRO Latest$4.80 / $28.80$24.00

A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.

Worked for Gemma 3n E4B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.20 input and $0.16 output per million tokens, that is $0.40 + $0.08 = $0.48, paid from prepaid credit with no subscription.

Gemma 3n E4B API key · base URL and setup

  1. Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
  2. Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
  3. Send gemma-3n-e4b-it as the model. The same key calls every other model in the catalog.
Python · OpenAI SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uplinkswitch.com/v1",
    api_key="sk-uplink-live-...",
)

completion = client.chat.completions.create(
    model="gemma-3n-e4b-it",
    messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)
TypeScript · OpenAI SDK
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uplinkswitch.com/v1',
  apiKey: 'sk-uplink-live-...',
});

const completion = await client.chat.completions.create({
  model: 'gemma-3n-e4b-it',
  messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);
curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"gemma-3n-e4b-it","messages":[{"role":"user","content":"Hello"}]}'

What would it cost? · paste a prompt, priced before you send it

Input is counted at about 4 characters per token.

Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.

Gemma 3n E4B questions

Gemma 3n E4B is a model from Google, with a 8,192-token context window. Through UplinkSwitch it answers the OpenAI SDK on one key as gemma-3n-e4b-it.

$0.20 per million input tokens and $0.16 per million output tokens, with cached input at $0.00.

It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0003.

Gemma 3n E4B has a 8,192-token context window.

gemma-3n-e4b-it. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Gemma 3n E4B and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.

Every day each model gets the same test prompt, and the results are public on /proof. Gemma 3n E4B's latest result: Steady since Oct 29.

Yes: gemma-3n-e4b-it on the OpenAI format at https://api.uplinkswitch.com/v1, $0.20 input and $0.16 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.

An effective 4B, with more in the weights, per Google’s Gemma 3n model card.

32K tokens on Google’s card; served with an 8,192-token window, per Google’s Gemma 3n model card.

Its weights are open on Hugging Face (google/gemma-3n-E4B-it); the license is the Gemma Terms of Use.

$0.048 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.20 input and $0.16 output per million tokens, from prepaid credit with no subscription.

E4B runs at an effective 4B parameters, E2B at an effective 2B, per Google’s card. Gemma 3n E4B is $0.20 / $0.16 per million tokens in / out, $0.48 for 1,000 chat turns; Gemma 3n E2B is $0.12 / $0.08 per million tokens in / out, $0.28 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.
Join on Telegram