Console

Models / Google

Gemma 4 12B API pricing

$0.40 in, $1.20 out per million tokens.

gemma-4-12b-itmanaged routeOpenAI SDK

Price · per million tokens, USD

Get a key
TokensGoogle list priceUplinkSwitchSaving
Input—$0.40—
Cached inputBilled at the input rate.
Output—$1.20—
No list price on record.
Real-model check: Steady since Oct 20

Also try

Gemma 4 12B: what it is · from Google’s own model card, read 2026-10-20

Google DeepMind’s Gemma 4 12B Unified, which reads text, images, audio and video with no separate encoders. It brings Gemma 4’s native audio and vision to a small model. It is served as gemma-4-12b-it at $0.40 input and $1.20 output per million tokens, on the same key as every other model in the catalog.

Gemma 4 12B
DeveloperGoogle
Parameters12B, dense
Contextup to 256K tokens
LicenseApache-2.0
Published2026-05-23
Downloads, 30 days to 2026-10-201,692,786
Sourcegoogle/gemma-4-12B-it

From google/gemma-4-12B-it, read 2026-10-20.

curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"gemma-4-12b-it","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

Gemma 4 12B next to Google’s other models · per million tokens, live

ModelHere, in / out1,000 chat turns
Gemini 2.5 Flash Lite$0.075 / $0.30$0.30
Gemini 2.5 Flash$0.09 / $0.75$0.56
Gemini 3.1 Flash Lite$0.15 / $0.90$0.75
Gemini 3.1 Flash Lite Preview$0.1875 / $1.125$0.94
Gemma 4 12B$0.40 / $1.20$1.40
Gemini 3 Flash Preview$0.375 / $2.25$1.88
Gemma 4 26B-A4B$0.56 / $1.60$1.92
Gemini 3.6 Flash$0.4925 / $2.25$2.11
Gemini 3.7 Flash$0.4925 / $2.25$2.11
Gemini 3.8 Flash$0.4925 / $2.25$2.11
Gemini 4 Argon$0.60 / $3.00$2.70
Gemini 2.5 Pro$0.9375 / $7.50$5.63
Gemini 3.1 Pro Preview$1.20 / $7.20$6.00
Gemma 31B Heretic Uncensored$1.50 / $8.25$7.13
DiffusionGemma 26B A4B$3.00 / $3.00$7.50
Gemini 3.5 Flash$1.50 / $9.00$7.50
Gemma 4 31B$3.00 / $4.00$8.00

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 4 12B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.40 input and $1.20 output per million tokens, that is $0.80 + $0.60 = $1.40, paid from prepaid credit with no subscription.

Gemma 4 12B 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-4-12b-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-4-12b-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-4-12b-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-4-12b-it","messages":[{"role":"user","content":"Hello"}]}'
Guides: Cursor, Cline, Roo Code, Kilo Code, SDKs.

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.

More from Google

Gemma 4 12B questions

Gemma 4 12B is a model from Google. Through UplinkSwitch it answers the OpenAI SDK on one key as gemma-4-12b-it.

$0.40 per million input tokens and $1.20 per million output tokens.

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 $0.001.

gemma-4-12b-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 4 12B 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 4 12B's latest result: Steady since Oct 20.

Yes: gemma-4-12b-it on the OpenAI format at https://api.uplinkswitch.com/v1, $0.40 input and $1.20 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.

12B, dense, per google/gemma-4-12B-it.

Up to 256K tokens, per google/gemma-4-12B-it.

Its weights are open on Hugging Face (google/gemma-4-12B-it); the license is Apache-2.0.

$0.14 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.40 input and $1.20 output per million tokens, from prepaid credit with no subscription.
Read: Compare LLM API prices and work out your bill.
Get a key · All models