Google: Gemma 4 26B A4B

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

262KContext Window

262KMax Output

Supported Protocols:reasoninginclude_reasoningmax_tokenstemperaturetop_pfrequency_penaltypresence_penaltystopseedtool_choicetoolsstructured_outputs

Online

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.

Capabilities

👁 Vision🧠 Reasoning🔧 Function CallingText GenerationCode GenerationAnalysis & Reasoningmodels.reasoning

Technical Specs

Input Modality

Image、Text、Video

Output Modality

Text

Arch

—

Default Temperature

Default Top_P

0.95

Default Top_K

Pricing

Pay per use, no monthly fees

Input Token< ¥0.001/1K Token

Output Token< ¥0.001/1K Token

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

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

print(response.choices[0].message.content)