# Gemini Flash (latest)

> Always resolves to the newest live Gemini Flash model — currently Gemini 3 Flash (google/gemini-3-flash). Google's Gemini 3 Flash model combining fast inference with strong reasoning, coding, and multimodal understanding across a 1M-token context window.

**ID**: `google/gemini-flash-latest`  
**Creator**: Google  
**Category**: text  
**Context**: 1M tokens  
**Family alias**: always resolves to the newest live family member — currently [`google/gemini-3-flash`](https://anyrouter.dev/model/google/gemini-3-flash). Specs below are google/gemini-3-flash's.  
**Fallback order**: `google/gemini-3-flash`  
**Input**: $0.50/M  
**Output**: $3.00/M  
**Released**: 2025-12-17  
**Web page**: https://anyrouter.dev/model/google/gemini-flash-latest

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: chat, streaming, function-calling, 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/gemini-flash-latest",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| antigravity-byok | $0 | $0 |
| antigravity | $0 | $0 |
| aihubmix-byok | $0 | $0 |
| ollama-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |
| opencode-zen-byok | $0 | $0 |
| cline-byok | $0 | $0 |
| google-aistudio-byok | $0 | $0 |
| google-agent-platform-byok | $0 | $0 |

## Benchmarks

- **GPQA Diamond**: 0.8
- **HLE**: 0.1
- **τ²-Bench Telecom**: 0.4
- **SciCode**: 0.5
- **OTIS Mock AIME**: 0.9
- **SimpleQA (verified)**: 0.7

Benchmark data from [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0).