Gemma 3 4B IT
by Google
Google Gemma 3 4B multimodal open model balancing compact size and rich multimodal understanding.
Parameters
4B Dense
Context Length
128K
Category
chat
Available Serverless
Run queries immediately, pay only for usage
$0.06in|$0.13out
Per 1M Tokens
About this model
Google Gemma 3 4B multimodal open model balancing compact size and rich multimodal understanding.
Capabilities
Vision128K contextMultimodalStreaming
Model Details
- Provider
- Model ID
- gemma-3-4b-it
- Parameters
- 4B Dense
- Context Length
- 128K tokens
- Category
- chat
API Usage
Use the DOS API to integrate Gemma 3 4B IT into your applications. Our API is compatible with OpenAI's client libraries for easy migration.
Model ID
gemma-3-4b-itPython
python
from dos import DOS
client = DOS()
response = client.chat.completions.create(
model="gemma-3-4b-it",
messages=[
{"role": "user", "content": "Hello, how are you?"}
]
)
print(response.choices[0].message.content)cURL
bash
curl https://api.dos.ai/v1/chat/completions \
-H "Authorization: Bearer $DOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemma-3-4b-it",
"messages": [
{"role": "user", "content": "Hello, how are you?"}
]
}'Node.js
javascript
import DOS from 'dos-ai';
const client = new DOS();
const response = await client.chat.completions.create({
model: "gemma-3-4b-it",
messages: [
{ role: "user", content: "Hello, how are you?" }
]
});
console.log(response.choices[0].message.content);Related Models
DOS.AI
DOS.AI Auto
Smart routing - automatically picks the best model for your request. Free for simple tasks, paid models for complex ones.
Usage-based
DOS.AI
DOS.AI
DOS.AI's hosted Qwen 3.5 35B-A3B model for text generation.
$0.07 / 1M tokens
Google
Gemma 3 1B IT
Google Gemma 3 1B on-device text model providing low-latency execution for mobile and edge computing.
$0.03 / 1M tokens