# Gemini 3.5 Flash - Core.Today AI API

> Google's latest Flash-tier workhorse model. Flat pricing across all input modalities (text, image, video, audio, PDF) at $1.50/$9 per million tokens with no long-context premium, a 1M token context window, and 65,536 max output tokens. Cached inputs get a 90% discount.

- **Provider**: Google
- **Model ID**: gemini-3.5-flash
- **Category**: LLM
- **Credits**: 2 per request
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 1M tokens
- **Max Output**: 66K tokens
- **Training Cutoff**: 2025-01
- **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**: 2,787 credits ($1.86)
- **Output Tokens**: 16,722 credits ($11.15)
- **Cached Tokens**: 279 credits ($0.19)

## Features
- Flat pricing across all input modalities
- No long-context premium
- 1M token context window
- 65,536 max output tokens
- Cached input pricing (90% discount)
- Function calling, structured outputs, thinking, search grounding, code execution

## Use Cases
- Multimodal understanding (video, audio, PDF)
- High-volume production chat workloads
- Long document and codebase analysis
- Data extraction and summarization at scale
- Repeated context with cached inputs (RAG)

## 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.
- **max_tokens**: integer - Maximum output tokens. Max: 65,536. Context window (input + output): 1M 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

### Multimodal Document Analysis
Analyze a PDF at the same flat token rate as text
```json
{
  "model": "gemini-3.5-flash",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the attached contract PDF and list every deadline it mentions."
    }
  ],
  "max_tokens": 2000
}
```

### Production Chat
High-throughput assistant responses with streaming
```json
{
  "model": "gemini-3.5-flash",
  "messages": [
    {
      "role": "user",
      "content": "Explain the difference between ECS and EKS briefly."
    }
  ],
  "stream": true,
  "max_tokens": 800
}
```

## 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
- Flat modality pricing — video/audio/PDF inputs cost the same per token as text
- No long-context premium: >200K-token inputs stay at the same rate (unlike Gemini Pro tiers)
- Use cached inputs ($0.15/M, 90% off) for repeated context
- Max output is 65,536 tokens — chunk very long generations
- Step down to Gemini 3.1 Flash Lite ($0.25/$1.50) for simple high-volume tasks

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