# Gemini 3.1 Flash Lite Image - Core.Today AI API

> Lightweight, lower-cost sibling of Gemini 3.1 Flash Image with native image generation. Generates images directly in chat responses alongside text, with separate pricing for text and image output tokens: $0.25 input, $1.50 text output and $30 image output per million tokens.

- **Provider**: Google
- **Model ID**: gemini-3.1-flash-lite-image
- **Category**: LLM
- **Credits**: 250 per request
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 66K tokens
- **Max Output**: 66K tokens
- **Training Cutoff**: Not published
- **Supported Formats**: text, json, markdown, image
- **Compatible SDK**: OpenAI, Google AI

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

### Token Pricing (per 1M tokens)
- **Input Tokens**: 464.5 credits ($0.31)
- **Output Tokens**: 2,787 credits ($1.86)
- **Image Output Tokens**: 55,740 credits ($37.16)
  Note: ~1,120 tokens per 1024px image

## Features
- Native image generation in chat at Lite-tier pricing
- 65,536 token input limit
- 65,536 max output tokens
- Multimodal input: text and image
- Output modalities: image + text
- Image output at half the Gemini 3.1 Flash Image rate ($30/M vs $60/M)
- Thinking and Batch API

## Use Cases
- Conversational image generation
- Visual content creation with text descriptions
- Image editing via natural language instructions
- Creative design brainstorming
- Multimodal content production

## 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. Input limit: 65,536 tokens.
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### Text Chat
Standard text conversation
```json
{
  "model": "gemini-3.1-flash-lite-image",
  "messages": [
    {
      "role": "user",
      "content": "Explain the concept of neural style transfer in simple terms."
    }
  ],
  "max_tokens": 1000,
  "temperature": 0.7
}
```

### Image Generation
Generate an image through natural language conversation
```json
{
  "model": "gemini-3.1-flash-lite-image",
  "messages": [
    {
      "role": "user",
      "content": "Generate an image of a serene Japanese garden with a koi pond, cherry blossoms, and a small wooden bridge at sunset."
    }
  ],
  "max_tokens": 4096
}
```

## 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
- Lowest-cost Gemini image model - $0.25/M input, $1.50/M text output, $30/M image output
- Image output tokens are priced separately at $30.00/M (55,740 credits/M), half of Gemini 3.1 Flash Image
- Text-only responses use standard text output pricing ($1.50/M)
- Input limit is 65,536 tokens - keep reference images and prompts compact
- Step up to gemini-3.1-flash-image or gemini-3-pro-image when image fidelity matters more than cost

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