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.

GoogleText Generation256K contextReleased Mar 31, 2026Native InferenceNew

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

reasoningvisionvideofunction callingstructured outputcachemultimodaljson modelogprobs

Gemma 4 26B-A4B specs

Model ID
gemma-4-26b-a4b
Provider
Google
Category
Text Generation
Released
Mar 31, 2026
Context window
256K tokens
Max output
32,768 tokens
Input
TextImageVideo
Output
Text
Endpoints
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages
POST /v1/completions

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

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

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. Lower values are more deterministic.
top_pnumber0.950 to 1Nucleus sampling probability mass.
max_tokensinteger40961 to 32768Maximum output tokens.
stopstring--One or more stop strings.
reasoning_effortenummediumnone, low, medium, high, maxReasoning effort. none disables thinking; low, medium, high, and max set bounded thinking budgets.
enable_thinkingbooleantrue-Enable the model reasoning channel before final output.
thinking_budgetinteger4096128 to 32768Maximum thinking tokens before the final answer. If max_tokens is lower, the service reserves room for the answer.
top_kinteger201 to 200Limit sampling to the top K candidate tokens when supported.
min_pnumber00 to 1Minimum probability threshold for token sampling.
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_penaltynumber10.1 to 2Penalty used by SGLang to reduce repeated text.
seedinteger-0 to 2147483647Optional random seed for reproducible sampling.
logprobsbooleanfalse-Return token log probabilities when supported.
8 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 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: Input $0.05 (was $0.15) per 1M prompt tokens; Output $0.29 (was $0.50) per 1M generated tokens; Implicit cache read $0.025 (was $0.15) per 1M cached input tokens. The live rate card on this page always matches what the API charges.

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.

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.

Ready to use better endpoints?

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