Gemma 4 26B-A4B API

Gemma 4 26B A4B is a Google open multimodal model with 256K context, text, image, and video input, tools, and structured output.

Google Text Generation 256K context Released Mar 31, 2026 Native Inference

About Gemma 4 26B-A4B

Gemma 4 26B A4B is a Google open multimodal model with 256K context, text, image, and video input, tools, and structured output.

Supports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort or thinking_budget for bounded thinking, or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported.

Also known as Google Gemma 4 26B-A4B, Gemma-4-26B-A4B

reasoning vision video function calling cache multimodal json mode logprobs

Gemma 4 26B-A4B specs

Model ID
gemma-4-26b-a4b
Author
Google
Category
Text Generation
Released
Mar 31, 2026
Context window
256K tokens
Max output
32,768 tokens
Input
TextImageVideo
Output
Text
Structured output
JSON Schema
Endpoints
POST/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1/completionsPOST/v1beta/models/gemma-4-26b-a4b:generateContent
Alternate model IDs
gemma-4-26b-a4b-itgoogle/gemma-4-26b-a4bgoogle/gemma-4-26b-a4b-it

Gemma 4 26B-A4B API pricingSave up to 83%

Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.

Type
Spec
Rate
Input
per 1M prompt tokens
$0.15$0.05
Output
per 1M generated tokens
$0.50$0.29
Implicit cache read
per 1M cached input tokens
$0.15$0.025
Web Search (Linkup)
per call when invoked
$0.013
Compare on the full pricing page

How to call the Gemma 4 26B-A4B API

Gemma 4 26B-A4B serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id gemma-4-26b-a4b. Get an API key from the EmpirioLabs dashboard.

cURL
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b-a4b",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'
Python (OpenAI SDK)
from openai import OpenAI

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

response = client.chat.completions.create(
    model="gemma-4-26b-a4b",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)
Full Gemma 4 26B-A4B API reference

Gemma 4 26B-A4B API parameters

Request parameters supported by the Gemma 4 26B-A4B API on EmpirioLabs. Defaults apply when a field is omitted.

ParameterTypeDefaultRange / valuesDescription
temperaturenumber10 to 2Sampling temperature. 0 is deterministic and 2 is maximum randomness.
top_pnumber0.950.01 to 1Nucleus sampling probability mass. Lower values make outputs more focused.
max_tokensinteger81921 to 32768Maximum output tokens. When omitted: 8,192 at low and medium reasoning effort, 9,216 at high, and 32,768 at max or with thinking off.
stopstring--One or more stop strings.
reasoning_effortenummediumnone, low, medium, high, maxReasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.
enable_thinkingbooleantrue-Enable reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking.
thinking_budgetinteger4096128 to 32768Maximum tokens reserved for reasoning when thinking is enabled. When max_tokens is lower, room is kept for the answer; a very low max_tokens can be spent entirely on...
top_kinteger20min 1Limit sampling to the top K candidate tokens when supported.
presence_penaltynumber0-2 to 2Penalty for tokens that already appeared in the generated text.
frequency_penaltynumber0-2 to 2Penalty based on how often a token has already appeared.
repetition_penaltynumber1min 0.1Higher values discourage repeated phrasing.
seedinteger-0 to 2147483647Optional random seed for reproducible sampling.
logprobsbooleanfalse-Return token log probabilities when supported.
top_logprobsinteger-0 to 20Return up to this many top token log probabilities.
6 more parameters in the docs

Good to know

Supports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort or thinking_budget for bounded thinking, or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported.

Gemma 4 26B-A4B on the blog

Announcements, prompt tests, and comparisons that cover this model.

Gemma 4 26B-A4B API: common questions

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

On EmpirioLabs, Gemma 4 26B-A4B is billed pay as you go. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.

What inputs and outputs does Gemma 4 26B-A4B support?

Gemma 4 26B-A4B takes Text, Image, Video as input and returns Text.

What is the context window of Gemma 4 26B-A4B?

Gemma 4 26B-A4B supports a 256K-token context window with up to 32,768 output tokens per response.

Is the Gemma 4 26B-A4B API OpenAI-compatible?

Yes. Gemma 4 26B-A4B serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to gemma-4-26b-a4b.

What is the model ID for Gemma 4 26B-A4B?

Send gemma-4-26b-a4b as the model in your request. The alternate IDs gemma-4-26b-a4b-it, google/gemma-4-26b-a4b, google/gemma-4-26b-a4b-it also work.

When was Gemma 4 26B-A4B released?

Google released Gemma 4 26B-A4B on Mar 31, 2026.

Can I try Gemma 4 26B-A4B in the browser before integrating?

Yes. The EmpirioLabs playground runs Gemma 4 26B-A4B in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a Gemma 4 26B-A4B API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.

Compare Gemma 4 26B-A4B with other models

All model comparisons

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.