# Gemma (latest)

> Always resolves to the newest live Gemma model — currently Gemma 4 26B A4B (google/gemma-4-26b-a4b-it). Gemma 4 is Google's most intelligent family of open models, built from Gemini 3 research to maximize intelligence-per-parameter.

**ID**: `google/gemma-latest`  
**Creator**: Google  
**Category**: text  
**Context**: 262K tokens  
**Family alias**: always resolves to the newest live family member — currently [`google/gemma-4-26b-a4b-it`](https://anyrouter.dev/model/google/gemma-4-26b-a4b-it). Specs below are google/gemma-4-26b-a4b-it's.  
**Fallback order**: `google/gemma-4-26b-a4b-it`  
**Input**: $0.10/M  
**Output**: $0.30/M  
**Released**: 2026-04-03  
**Web page**: https://anyrouter.dev/model/google/gemma-latest

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

**Tokenizer**: Gemma

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

## 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-latest",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| aihubmix-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |
| hue | $0.10/M | $0.30/M |

## Benchmarks

- **GPQA Diamond**: 0.7
- **HLE**: 0.1
- **τ²-Bench Telecom**: 0.4
- **SciCode**: 0.4