Google logo

Gemma 4 26B A4B IT API

google/gemma-4-26b-a4b-it

Call Gemma 4 26B A4B IT through UberLLM’s OpenAI-compatible API — from $0.0005/M input and $0.0016/M output, routed automatically to the cheapest healthy seller. Google · 262,144 token context. Fee included.

Try it live — no signup
Demo · a few prompts a day, no sign-up

Gemma 4 26B A4B IT pricing

Price now · per 1M tokens
Input
$0.000491
Output
$0.00163
Cached input
$0.000273
% off list
99% off
12% of input served from cache
List price · per 1M tokens
Input
$0.0743
Output
$0.2475
Cached input
$0.0413
Providers and their list prices, per 1M tokens
ProviderInputOutputCached input
Venice AI$0.13$0.40$0.05
Bankr$0.13$0.40
Morpheus$0.15$0.40
Jatevo$0.1625$0.50
Amazon Bedrock$0.1625$0.50

UberLLM routes every request to the cheapest healthy seller for this model. The price shown includes UberLLM’s 10% fee.

How to use Gemma 4 26B A4B IT with the OpenAI SDK

Already using the OpenAI SDK? Change one line — the base URL — and call Gemma 4 26B A4B IT with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uberllm.dev/v1",
    api_key="ull_your_key_here",
)

resp = client.chat.completions.create(
    model="google/gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Gemma 4 26B A4B IT API — FAQ

How much does the Gemma 4 26B A4B IT API cost?

Gemma 4 26B A4B IT is listed from $0.0005 per million input tokens and $0.0016 per million output tokens through UberLLM, which routes each request to the cheapest healthy seller on a live marketplace and bills the price shown, which includes UberLLM's 10% fee.

How do I call Gemma 4 26B A4B IT via API?

Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "google/gemma-4-26b-a4b-it". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.

Is Gemma 4 26B A4B IT OpenAI-compatible on UberLLM?

Yes. Every model on UberLLM — including Gemma 4 26B A4B IT — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.

More Google models