# GPT-5.6 Luna - Core.Today AI API

> The fast, low-cost tier of OpenAI's GPT-5.6 family (GA July 2026). Luna is built for high-throughput workloads at $1/$6 per million tokens, with a 1M token context window, 128K max output tokens, and cached inputs at a 90% discount.

- **Provider**: OpenAI
- **Model ID**: gpt-5.6-luna
- **Category**: LLM
- **Credits**: 1 per request
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 1M tokens
- **Max Output**: 128K tokens
- **Training Cutoff**: 2026-02
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: OpenAI

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

### Token Pricing (per 1M tokens)
- **Input Tokens**: 1,858 credits ($1.24)
- **Output Tokens**: 11,148 credits ($7.43)
- **Cached Tokens**: 186 credits ($0.12)

## Features
- Fast, low-cost tier of the GPT-5.6 family
- 1M token context window
- 128K max output tokens
- Knowledge cutoff: February 2026
- Cached input pricing (90% discount)
- Adjustable reasoning effort
- Function calling and native vision support

## Use Cases
- High-volume classification and routing
- Real-time chat applications
- Bulk summarization and extraction
- Lightweight agent steps and tool selection
- Cost-sensitive RAG pipelines

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/openai/v1/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 with role and content
- **model**: string (default: gpt-5.6-luna) - Model identifier

### Optional
- **max_completion_tokens**: integer (default: 4096) - Maximum tokens in response (up to 128000). Note: use max_completion_tokens, not max_tokens
- **reasoning_effort**: string (default: medium) - Reasoning effort level: none, low, medium, high, or xhigh
  Options: none, low, medium, high, xhigh
- **temperature**: float (default: 1.0) - Sampling temperature (0-2)
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### Bulk Classification
High-throughput labeling at the lowest GPT-5.6 price point
```json
{
  "model": "gpt-5.6-luna",
  "messages": [
    {
      "role": "system",
      "content": "Classify the ticket as: billing, bug, feature_request. Respond with only the label."
    },
    {
      "role": "user",
      "content": "I was charged twice for my subscription this month."
    }
  ],
  "max_completion_tokens": 20,
  "temperature": 0
}
```

### Real-time Chat
Low-latency streaming responses for interactive UIs
```json
{
  "model": "gpt-5.6-luna",
  "messages": [
    {
      "role": "user",
      "content": "Give me three taglines for a coffee subscription."
    }
  ],
  "stream": true,
  "max_completion_tokens": 500
}
```

## 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 GPT-5.6 tier at $1/$6 per M tokens — ideal default for high-volume calls
- Use cached inputs ($0.10/M, 90% off) for repeated system prompts
- reasoning_effort 'none' or 'low' maximizes throughput on simple tasks
- Escalate to Terra or Sol when answers need deeper reasoning
- temperature 0 for deterministic classification and extraction

## Documentation
https://platform.openai.com/docs/models