# Gemini 3.1 Flash Lite - Core.Today AI API

> Stable release of the ultra-lightweight Gemini 3.1 Flash Lite. The most cost-effective Gemini model at $0.25/$1.50 per million tokens, with cached input (90% discount), audio input, and batch (50% discount) support. Ideal for high-throughput, budget-conscious applications.

- **Provider**: Google
- **Model ID**: gemini-3.1-flash-lite
- **Category**: LLM
- **Credits**: 1 per request
- **Speed**: Fast
- **Quality**: Standard

## Model Specifications
- **Context Window**: 1.0M 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**: 464 credits ($0.31)
- **Output Tokens**: 2,787 credits ($1.86)
- **Cached Tokens**: 46 credits ($0.03)

## Features
- Most cost-effective Gemini model
- Stable model ID (no preview suffix)
- 1,048,576 token context window
- 65,536 max output tokens
- Multimodal input: text, image, audio, video, PDF
- Cached input (90% off) and batch (50% off) pricing
- Function calling, structured outputs, thinking, search grounding, code execution

## Use Cases
- High-volume text processing
- Real-time chat applications
- Quick classification and routing
- Lightweight data extraction
- Audio transcription and understanding

## 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). Supports text, image, audio, video, and PDF inputs.

### Optional
- **temperature**: float (default: 1) - Sampling temperature (0-2). Lower values produce more deterministic outputs.
- **top_p**: float (default: 0.95) - Nucleus sampling parameter (0-1).
- **max_tokens**: integer - Maximum output tokens. Max: 65,536. Context window (input + output): 1,048,576 tokens.
- **response_format**: object - Output format constraint. Use `{ type: 'json_object' }` for structured JSON output.
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming.

## Examples

### Quick Classification
Lightweight text classification with Flash Lite
```json
{
  "model": "gemini-3.1-flash-lite",
  "messages": [
    {
      "role": "system",
      "content": "Classify the following text as: spam, not_spam. Respond with only the label."
    },
    {
      "role": "user",
      "content": "Congratulations! You have been selected for a special prize. Click here to claim now!"
    }
  ],
  "max_tokens": 50,
  "temperature": 0
}
```

## 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
- Most affordable Gemini model at $0.25/$1.50 per M tokens
- Prefer this stable ID over the -preview variant for production workloads
- Use cached input tokens ($0.025/M, 90% off) for repeated context
- Audio input at $0.50/M for voice-based applications
- Batch processing halves cost when latency doesn't matter
- Ideal for high-volume classification and routing tasks

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