Skip to content
OpenKey

Gemma 4 26B A4B

GoogleReleased Apr 3, 2026

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...

Try in playground
Context window
262K tokens
Input
image, text, video
Output
text
Tokenizer
Gemma
Released
Apr 3, 2026
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.060$0.0018$0.062
Output$0.330$0.0099$0.340

Benchmarks

Artificial Analysis

Intelligence index
25.7
Coding index
39.3
Agentic index
11

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model google/gemma-4-26b-a4b-it.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b-it",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

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

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "google/gemma-4-26b-a4b-it",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Gemma 4 26B A4B cost via API?
Through OpenKey, Gemma 4 26B A4B costs $0.062 per 1M input tokens and $0.340 per 1M output tokens. That is the provider price ($0.060 / $0.330) plus a flat 3% fee — nothing else.
What is Gemma 4 26B A4B 's context window?
Gemma 4 26B A4B accepts up to 262K tokens of context.
Is Gemma 4 26B A4B OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "google/gemma-4-26b-a4b-it" using any OpenAI SDK — only the base URL and API key change.
What inputs does Gemma 4 26B A4B support?
Gemma 4 26B A4B accepts image, text, video input and produces text output.

More from Google

All Google models →