How much does Gemma 4 26B A4B (free) cost via API?

It costs $0 per 1M tokens for both input and output, from the provider directly. OpenKey applies its flat 3% fee on provider list price, but 3% of $0 is still $0, so the OpenKey price matches the provider price exactly — free in both cases.

What is Gemma 4 26B A4B's context window?

It supports a 262,144-token context window, one of the larger windows in the catalog — larger than 56% of all catalog models. That's enough to hold very long documents, large codebases, or hours of transcribed audio/video content in a single request, alongside up to 32,768 tokens of output.

Is Gemma 4 26B A4B free to use?

Yes — both prompt and completion pricing are $0 per 1M tokens from the provider, and OpenKey passes that through unchanged since its 3% fee applies to provider price. It's one of 25 free models available on OpenKey's catalog of 329 models.

Does Gemma 4 26B A4B support tool calling and structured outputs?

Yes — its supported parameters include tools, tool_choice, response_format, and structured_outputs, alongside reasoning controls, seed, and standard sampling parameters like temperature and top_p. Reasoning is optional and off by default, but can be enabled per request.

How does Gemma 4 26B A4B compare to Gemini 2.5 Flash?

Gemma 4 26B A4B is free, while Gemini 2.5 Flash costs $0.30 per 1M input tokens and $2.50 per 1M output tokens from Google (before OpenKey's 3% fee, which brings it to roughly $0.309 and $2.575 per 1M). Gemma 4 26B A4B trades that paid tier's higher intelligence ceiling for zero cost and a MoE design that only activates 3.8B of its 25.2B parameters per token.

Gemma 4 26B A4B (free)

googlegemma-4-26b-a4b-it:free

Free

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 Hugging Face ↗

Modalities: image + text + video → text
In / out per 1M: Free / Free
Context: 262K tokens
Added: Apr 3, 2026

Max output: 33K tokens
Tokenizer: Gemma
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 tokens	Provider	+ 3% fee	You pay
Input	Free	—	Free
Output	Free	—	Free

Providers

2 endpoints serve Gemma 4 26B A4B (free). Figures are each provider’s own list price per 1M tokens — your OpenKey price is in the card above.

Provider	Context	Input /M	Output /M
Darkbloom	131K	Free	Free
Google AI Studio	262K	Free	Free

Provider list from the OpenRouter catalog, Jul 28, 2026. All providers

Benchmarks

Artificial Analysis

Agentic index: 11
Coding index: 39.3
Intelligence index: 25.7

Supported parameters

frequency_penalty
include_reasoning
max_tokens
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p

Call it

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

curl Python TypeScript

curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b-it:free",
    "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:free",
    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:free",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

About Gemma 4 26B A4B (free)

Gemma 4 26B A4B IT is Google DeepMind's mixture-of-experts model: 25.2B total parameters, but only 3.8B activate per token, so inference stays cheap while quality tracks closer to a much larger dense model. It handles text, image, and video input and answers in text, with a 262,144-token context window and up to 32,768 tokens of completion. On Artificial Analysis benchmarks it scores 25.7 on the intelligence index, 39.3 on coding, and 11 on agentic tasks — a profile suited to high-volume, cost-sensitive text and multimodal tasks rather than complex multi-step agent work.

It's free via OpenKey — provider price and OpenKey price are both $0/1M tokens for prompt and completion, so the 3% fee adds nothing. Its 262,144-token context window sits above 56% of catalog models, and it supports tool calling, structured outputs, and optional reasoning (off by default, can be enabled per request). Compared to Google's paid Gemini 2.5 line, where Flash Lite starts at $0.10/1M input, Gemma 4 26B A4B gives you a large context window and multimodal input at no cost, with a lower coding index (39.3) than what Gemini's flagship tiers typically target.

Questions

How much does Gemma 4 26B A4B (free) cost via API?: It costs $0 per 1M tokens for both input and output, from the provider directly. OpenKey applies its flat 3% fee on provider list price, but 3% of $0 is still $0, so the OpenKey price matches the provider price exactly — free in both cases.
What is Gemma 4 26B A4B's context window?: It supports a 262,144-token context window, one of the larger windows in the catalog — larger than 56% of all catalog models. That's enough to hold very long documents, large codebases, or hours of transcribed audio/video content in a single request, alongside up to 32,768 tokens of output.
Is Gemma 4 26B A4B free to use?: Yes — both prompt and completion pricing are $0 per 1M tokens from the provider, and OpenKey passes that through unchanged since its 3% fee applies to provider price. It's one of 25 free models available on OpenKey's catalog of 329 models.
Does Gemma 4 26B A4B support tool calling and structured outputs?: Yes — its supported parameters include tools, tool_choice, response_format, and structured_outputs, alongside reasoning controls, seed, and standard sampling parameters like temperature and top_p. Reasoning is optional and off by default, but can be enabled per request.
How does Gemma 4 26B A4B compare to Gemini 2.5 Flash?: Gemma 4 26B A4B is free, while Gemini 2.5 Flash costs $0.30 per 1M input tokens and $2.50 per 1M output tokens from Google (before OpenKey's 3% fee, which brings it to roughly $0.309 and $2.575 per 1M). Gemma 4 26B A4B trades that paid tier's higher intelligence ceiling for zero cost and a MoE design that only activates 3.8B of its 25.2B parameters per token.

More from Google

All Google models →

Google

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

ctx 66K in $0.258 out $1.54

Google

Nano Banana Pro (Gemini 3 Pro Image)

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

ctx 66K in $2.06 out $12.36

Google

Nano Banana 2 (Gemini 3.1 Flash Image)

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

ctx 131K in $0.515 out $3.09

Google

Gemini 3.5 Flash

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

ctx 1.0M in $1.54 out $9.27