Gemma 4 26B A4B It
Google logo

Gemma 4 26B A4B It

gemma-4-26b-a4b-itllms.txt
Google
A Mixture-of-Experts model that activates only 4B parameters per inference,delivering high-performance reasoning with a fraction of the memory cost - idealfor cost-efficient, high-throughput server deployments.

Pricing

  • Input Tokens: $0.14 /M tokens
  • Output Tokens: $0.4 /M tokens
  • Cache Read: $0 /M tokens

Input Modalities

  • Text
  • Vision
  • Video

Output Modalities

  • Text

Context length

  • 262K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Document input
  • Structured outputs
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Providers

Google AI Studio google-gemma-4-26b-a4b-it
Pricing$0.14$0.4
Cache$0
Context262K
Max output131K
Latency1.9S
Throughput15.6TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
86.84% uptime today
Deepinfra deepinfra-gemma-4-26b-a4b-it
Pricing$0.088$0.385
Cache$0.011
Context128K
Max output128K
Latency0.4S
Throughput20.7TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today

Performance for gemma-4-26b-a4b-it

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="gemma-4-26b-a4b-it",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

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

Frequently asked questions

What is Gemma 4 26B A4B It?

A Mixture-of-Experts model that activates only 4B parameters per inference,delivering high-performance reasoning with a fraction of the memory cost - idealfor cost-efficient, high-throughput server deployments.