# Gemini 2.5 Flash Lite - Core.Today AI API

> The cheapest tier of the Gemini 2.5 family, optimized for high-volume, latency-sensitive workloads. Delivers 2.5-generation quality at a fraction of the cost, ideal for classification, extraction, and real-time chat at scale.

- **Provider**: Google
- **Model ID**: gemini-2.5-flash-lite
- **Category**: LLM
- **Credits**: 0.5 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 1.0M tokens
- **Max Output**: 66K tokens
- **Training Cutoff**: 2025-01
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: Google

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

### Token Pricing (per 1M tokens)
- **Input Tokens**: 185.8 credits ($0.12)
- **Output Tokens**: 743.2 credits ($0.50)

## Features
- Cheapest Gemini 2.5-family tier
- Optimized for high-volume, latency-sensitive workloads
- 1,048,576 token context window
- 65,536 max output tokens
- Multimodal input: text, image, video, audio
- Function calling, structured outputs

## Use Cases
- High-volume chatbots
- Real-time classification
- Content filtering
- Data extraction at scale
- Latency-sensitive applications

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/gemini/v1beta/models/gemini-2.5-flash-lite:generateContent

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

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

## Input Parameters

### Required
- **contents**: array - Array of content objects with parts (Gemini native format). Supports text, image, video, and audio inputs.

### Optional
- **systemInstruction**: object - System instruction to steer model behavior.
- **generationConfig**: object - Generation settings: temperature, topP, maxOutputTokens (max 65,536), stopSequences, responseMimeType, etc.
- **tools**: array - Function declarations the model can call.

## Examples

### Quick Classification
Fast, low-cost text classification
```json
{
  "contents": [
    {
      "parts": [
        {
          "text": "Classify the sentiment of this review as positive, negative, or neutral. Respond with just the label.\n\nReview: The product works great but the delivery was slow."
        }
      ]
    }
  ],
  "generationConfig": {
    "temperature": 0,
    "maxOutputTokens": 10
  }
}
```

## 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
- Cheapest 2.5-family tier — use it when 2.5 Flash quality is more than you need
- Max output tokens: 65,536 — set generationConfig.maxOutputTokens up to this limit
- Context window 1,048,576 tokens (input + output)
- Use temperature 0 for deterministic classification
- Ideal for high-volume, latency-sensitive applications

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