Gemma 4 E4B API

ジェムマ4 E4Bは、次の画像入力、関数呼び出し、構造化された出力、効率的な指示を持つGoogleオープンマルチモーダルチャットモデルです。

Googleテキスト生成8K コンテキストリリース Mar 31, 2026ネイティブ推論

About Gemma 4 E4B

ジェムマ4 E4Bは、次の画像入力、関数呼び出し、構造化された出力、効率的な指示を持つGoogleオープンマルチモーダルチャットモデルです。

テキストとイメージの入力、ストリーミング、関数ツール、構造化されたJSON出力、シード制御、および思考モードをデフォルトでサポートします。 請求は成功したメッセージです。

別名 Google Gemma 4 E4B, Gemma-4-E4B

visionfunction callingstructured outputreasoning

Gemma 4 E4B specs

モデルID
gemma-4-e4b
プロバイダー
Google
カテゴリ
テキスト生成
Released
Mar 31, 2026
コンテキスト長
8K tokens
最大出力
4,096 tokens
入力
TextImage
出力
Text
エンドポイント
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages

Gemma 4 E4B API pricing

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

タイプ
仕様
料金
メッセージ
固定式
$0.03
Web Search (Linkup)
per call when invoked
$0.013
料金ページ全体で比較

How to call the Gemma 4 E4B API

Gemma 4 E4B 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-e4b. 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-e4b",
    "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-e4b",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)
Full Gemma 4 E4B API reference

Gemma 4 E4B API parameters

Request parameters supported by the Gemma 4 E4B API on EmpirioLabs. Defaults apply when a field is omitted.

パラメータタイプデフォルト範囲 / 値説明
temperaturenumber0.70 to 2Sampling temperature. Lower values are more deterministic.
top_pnumber0.950 to 1Nucleus sampling probability mass.
min_pnumber00 to 1Minimum token probability filter.
max_tokensinteger40961 to 4096Maximum output tokens.
stopstring--One or more stop strings.
seedinteger-0 to 2147483647Optional deterministic sampling seed.
enable_thinkingbooleantrue-Enable the model reasoning channel before final output.
reasoning_effortenum-low, medium, highOpenAI-compatible hint. Medium and high enable thinking mode.
presence_penaltynumber0-2 to 2Penalize tokens that already appeared.
frequency_penaltynumber0-2 to 2Penalize repeated tokens by frequency.
repetition_penaltynumber10.1 to 2Discourage exact repeated text.
logprobsbooleanfalse-Return token log probabilities when supported.
top_logprobsinteger-0 to 20Number of alternate token log probabilities to return.
toolsarray--OpenAI-compatible function tool definitions.
5 more parameters in the docs

知っておくと便利

テキストとイメージの入力、ストリーミング、関数ツール、構造化されたJSON出力、シード制御、および思考モードをデフォルトでサポートします。 請求は成功したメッセージです。

Gemma 4 E4B API: common questions

How much does the Gemma 4 E4B API cost?

On EmpirioLabs, Gemma 4 E4B is billed pay as you go: メッセージ $0.03 固定式; Web Search (Linkup) $0.013 per call when invoked. The live rate card on this page always matches what the API charges.

What is the context window of Gemma 4 E4B?

Gemma 4 E4B supports a 8K-token context window with up to 4,096 output tokens per response.

Is the Gemma 4 E4B API OpenAI-compatible?

Yes. Gemma 4 E4B 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-e4b.

Can I try Gemma 4 E4B in the browser before integrating?

Yes. The EmpirioLabs playground runs Gemma 4 E4B 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 E4B 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.