# Gemma 3 4B IT

> Gemma 3 4B IT is Google's instruction-tuned 4B open model — multimodal (text and image input), with a 128K context window and multilingual support in over 140 languages.

**ID**: `google/gemma-3-4b-it`  
**Creator**: Google  
**Category**: text  
**Context**: 131K tokens  
**Pricing**: $0.05 / $0.10 per 1M · billed by your provider (BYOK)  
**Released**: 2025-03-12  
**Web page**: https://anyrouter.dev/model/google/gemma-3-4b-it

**Input modalities**: text, image  
**Output modalities**: text  

**Tokenizer**: Gemma

**Capabilities**: chat, streaming, function-calling, vision

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemma-3-4b-it",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| huggingface-byok | $0.05/M (list) | $0.10/M (list) |
| openrouter-byok | $0.05/M (list) | $0.10/M (list) |
| google-aistudio-byok | $0.05/M (list) | $0.10/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Benchmarks

- **GPQA Diamond**: 0.3
- **HLE**: 0.1
- **τ²-Bench Telecom**: 0.0
- **SciCode**: 0.1

## Source

- Upstream docs: https://ai.google.dev/gemma/docs/core/model_card_3