# GPT-5.1 (2025-11-13) - Core.Today AI API

> Dated snapshot of GPT-5.1 for reproducible results. Supports cached input tokens for cost savings on repeated context. Ideal for production deployments requiring model version pinning.

- **Provider**: OpenAI
- **Model ID**: gpt-5.1-2025-11-13
- **Category**: LLM
- **Credits**: 3 per request
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 1M 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**: 2,322 credits ($1.55)
- **Output Tokens**: 18,580 credits ($12.39)
- **Cached Tokens**: 232 credits ($0.15)

## Features
- Fixed model snapshot for reproducibility
- Cached input tokens for cost savings
- Strong reasoning and coding performance
- Function calling & JSON mode
- Streaming support

## Use Cases
- Production systems requiring version pinning
- Reproducible experiments and evaluations
- Cost-optimized batch processing with caching
- Enterprise applications with audit requirements
- Regression testing for AI features

## 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-5.1-2025-11-13) - Model identifier

### Optional
- **max_completion_tokens**: integer (default: 4096) - Maximum tokens in response (up to 32768). Note: use max_completion_tokens, not max_tokens
- **temperature**: float (default: 1.0) - Sampling temperature (0-2)
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming
- **top_p**: float (default: 1.0) - Nucleus sampling threshold (0-1)

## Examples

### Reproducible Analysis
Pin model version for consistent results across runs
```json
{
  "model": "gpt-5.1-2025-11-13",
  "messages": [
    {
      "role": "system",
      "content": "You are a data analyst. Provide consistent, structured analysis."
    },
    {
      "role": "user",
      "content": "Analyze the key factors driving cloud computing adoption in 2026."
    }
  ],
  "temperature": 0,
  "max_completion_tokens": 2000
}
```

## 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
- Use this dated snapshot for reproducible results in production
- Leverage cached input tokens to reduce costs on repeated context
- Temperature 0 ensures deterministic outputs for evaluation
- Ideal for regression testing when comparing model versions

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