# GPT-5 Nano - Core.Today AI API

> Ultra-fast and lightweight variant of GPT-5. Designed for high-throughput, low-latency applications with a 1M token context window and 32K output tokens at minimal cost.

- **Provider**: OpenAI
- **Model ID**: gpt-5-nano
- **Category**: LLM
- **Credits**: 1 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 1.0M tokens
- **Max Output**: 33K tokens
- **Training Cutoff**: 2025-03
- **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**: 93 credits ($0.06)
- **Output Tokens**: 743 credits ($0.50)
- **Cached Tokens**: 9.3 credits ($0.01)

## Features
- 1M token context window
- 32K max output tokens
- Ultra-fast inference
- Lowest cost GPT-5 variant
- Function calling & JSON mode
- Structured outputs
- Ideal for high-throughput tasks

## Use Cases
- High-volume classification and routing
- Quick text generation and completion
- Real-time chat applications
- Lightweight data extraction
- Auto-tagging and categorization
- Simple code assistance

## 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-nano) - Model identifier

### Optional
- **max_completion_tokens**: integer (default: 4096) - Maximum tokens in response (up to 32768). Note: use max_completion_tokens, not max_tokens
- **reasoning_effort**: string (default: medium) - Reasoning effort level: low, medium, or high
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming
- **response_format**: object - Format of response: { type: 'json_object' } for JSON mode
- **tools**: array - List of tools (functions) the model can call

## Examples

### Quick Classification
High-speed text classification with GPT-5 Nano
```json
{
  "model": "gpt-5-nano",
  "messages": [
    {
      "role": "system",
      "content": "Classify the following customer message into one of these categories: billing, technical, general, feedback. Respond with only the category name."
    },
    {
      "role": "user",
      "content": "I was charged twice for my subscription last month and need a refund."
    }
  ],
  "max_completion_tokens": 50
}
```

### Data Extraction
Fast structured data extraction
```json
{
  "model": "gpt-5-nano",
  "messages": [
    {
      "role": "system",
      "content": "Extract key information from the text and return as JSON."
    },
    {
      "role": "user",
      "content": "Meeting scheduled with John Smith from Acme Corp on March 15, 2026 at 2:00 PM in Conference Room B to discuss Q1 budget review."
    }
  ],
  "response_format": {
    "type": "json_object"
  },
  "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
- Most cost-effective GPT-5 model — 25x cheaper than GPT-5 on input tokens
- Ultra-fast response times ideal for real-time applications
- Perfect for classification, routing, and simple extraction tasks
- Use temperature 0 for deterministic classification results
- Great for high-volume batch processing
- 1M context window available even at the lowest price point

## Documentation
https://platform.openai.com/docs/models/gpt-5-nano