# Gemini 3.1 Flash Live Preview - Core.Today AI API

> Gemini 3.1 Flash optimized for real-time interactions and live streaming scenarios. Features low-latency responses with audio input support at dedicated pricing.

- **Provider**: Google
- **Model ID**: gemini-3.1-flash-live-preview
- **Category**: LLM
- **Credits**: 300 per request
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 131K tokens
- **Max Output**: 66K tokens
- **Training Cutoff**: January 2025
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: OpenAI, Google AI

### Capabilities
- Vision (image input)
- Function Calling
- Streaming
- JSON Mode
- System Prompt

### Token Pricing (per 1M tokens)
- **Input Tokens**: 1,394 credits ($0.93)
- **Output Tokens**: 8,361 credits ($5.57)

## Features
- Live API support (real-time bidirectional)
- Low-latency streaming responses
- 131,072 token context window
- 65,536 max output tokens
- Multimodal input: text, image, audio, video
- Output modalities: text + audio
- Function calling, thinking, audio generation, search grounding

## Use Cases
- Live customer support interactions
- Real-time voice-based assistants
- Interactive streaming applications
- Live transcription and analysis
- Real-time content moderation

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/gemini/v1beta/openai/chat/completions

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **messages**: array - Array of message objects (OpenAI format)

### Optional
- **temperature**: float (default: 1) - Sampling temperature (0-2)
- **top_p**: float (default: 0.95) - Nucleus sampling parameter
- **max_tokens**: integer - Maximum output tokens. Max: 65,536. Context window (input + output): 131,072 tokens.
- **stream**: boolean (default: true) - Enable Server-Sent Events streaming (recommended for live use)

## Examples

### Live Chat
Real-time streaming conversation
```json
{
  "model": "gemini-3.1-flash-live-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a real-time assistant. Respond quickly and concisely."
    },
    {
      "role": "user",
      "content": "What are the key differences between HTTP/2 and HTTP/3?"
    }
  ],
  "max_tokens": 1000,
  "stream": true
}
```

## Response Format
```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

## Tips
- Max output tokens: 65,536 — set max_tokens up to this limit
- Context window 131,072 tokens — smaller than non-Live Flash variants
- Enable streaming for the best real-time experience
- Audio input tokens are priced at $3.00/M separately
- Output supports both text and audio modalities
- Ideal for live interactions requiring low latency
- Use for real-time voice assistants and customer support

## Documentation
https://ai.google.dev/gemini-api/docs