# gpt-6.1-sol

> LLM model from openai, available via Core.Today API.

- **Provider**: openai
- **Model ID**: gpt-6.1-sol
- **Category**: chat
- **Pricing Type**: token_based
- **Billing**: per token — see Token Pricing

## API Endpoint

Base URL: https://api.core.today

### Chat Completions
POST /llm/openai/v1/chat/completions

## Authentication

Header: `Authorization: Bearer YOUR_API_KEY`

Note: Your Core.Today API key (`cdt_xxx`) works as Bearer token.

## Input Parameters

- `model` (string, **required**): Model identifier. Use `gpt-6.1-sol`
- `messages` (array, **required**): Array of message objects with `role` and `content`
- `temperature` (number, optional): Sampling temperature (Default: `1.0`; Range: min: 0, max: 2)
- `max_tokens` (integer, optional): Maximum tokens to generate
- `stream` (boolean, optional): Enable streaming responses (Default: `false`)
- `top_p` (number, optional): Nucleus sampling parameter (Default: `1.0`)

## Example Request

```json
{
  "model": "gpt-6.1-sol",
  "messages": [
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ]
}
```

## Response Format

```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gpt-6.1-sol",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}
```

## Usage Flow

1. POST /llm/openai/v1/chat/completions with model and messages
2. Response is returned synchronously (or streamed if stream=true)
3. Credits are deducted based on token usage

## Token Pricing

- Input: 0.003716 credits/token (3,716 credits per 1M tokens)
- Cached Input: 0.0001858 credits/token (185.8 credits per 1M tokens)
- Cache Write: 0.004645 credits/token (4,645 credits per 1M tokens)
- Image Input: 0.003716 credits/token (charged at the Input rate)
- Output: 0.01858 credits/token (18,580 credits per 1M tokens)
- Web Search: 18.58 credits per request (built-in web search tool)

### Long-context tier

Prompts above 272,000 input tokens are billed at these rates for the whole request:

- Input: 0.007432 credits/token (7,432 credits per 1M tokens)
- Cached Input: 0.0003716 credits/token (371.6 credits per 1M tokens)
- Cache Write: 0.00929 credits/token (9,290 credits per 1M tokens)
- Output: 0.02787 credits/token (27,870 credits per 1M tokens)
- Web Search: 18.58 credits per request (built-in web search tool)

## Image Input

This model accepts images as input. Image bytes are converted to tokens by the upstream provider and charged at the standard Input rate (0.003716 credits/token).

**Tokenization**: tile-based
- Tokens per image ≈ `85 + 170 × tiles` (each tile = 512×512px after scaling)
- Notes: low=85 fixed; high=85 + 170×tiles after scaling to 2048 max then 768 short edge

### Example (OpenAI-compatible)

```json
{
  "model": "gpt-6.1-sol",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What's in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        }
      ]
    }
  ]
}
```

## Tags

openai, chat