# GPT-6.1 Sol - Core.Today AI API

> OpenAI's GPT-6.1 Sol — the Sol tier of the GPT-6.1 generation at $2/$10 per million tokens, with cached inputs at a 95% discount ($0.10/M, half of GPT-6 Sol's cached rate). 1.05M token context window (up to 922K input), 128K max output tokens, text and image input. Supports Fast mode and Ultrafast mode. Prompts above 272K input tokens are billed at 2x input / 1.5x output for the whole request.

- **Provider**: OpenAI
- **Model ID**: gpt-6.1-sol
- **Category**: LLM
- **Credits**: 2 per request
- **Speed**: Fast
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 1.1M tokens
- **Max Output**: 128K tokens
- **Training Cutoff**: 2026-04
- **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**: 3,716 credits ($2.48)
- **Output Tokens**: 18,580 credits ($12.39)
- **Cached Tokens**: 185.8 credits ($0.12)

## Features
- Sol tier of the GPT-6.1 generation
- 1.05M token context window (up to 922K input tokens)
- 128K max output tokens
- Knowledge cutoff: April 30, 2026
- Cached input pricing (95% discount)
- Adjustable reasoning effort (low to max, default medium)
- Text and image input, structured outputs, streaming
- Tool calling through the Responses API
- Fast mode and Ultrafast mode (service_tier)

## Use Cases
- Reasoning and analysis over long context
- Agentic workflows with tool use (Responses API)
- Large-codebase understanding and refactoring
- Long document processing up to 922K input tokens
- Repeated context with cached inputs (RAG, codebases)
- Latency-sensitive agents with Ultrafast mode

## 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-6.1-sol) - 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: low, medium, high, xhigh, or max. 'none' and 'minimal' are not supported on this model
  Options: low, medium, high, xhigh, max
- **service_tier**: string (default: auto) - Processing tier. 'fast' bills token charges at 2x, 'ultrafast' (Responses API) at 6x; settled on the tier the response reports
  Options: auto, default, fast, ultrafast
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### Multi-step Reasoning
Multi-step code reasoning with GPT-6.1 Sol
```json
{
  "model": "gpt-6.1-sol",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software engineer. Think step by step."
    },
    {
      "role": "user",
      "content": "Design a migration plan from a monolithic Express API to modular services, then generate the first service's code with tests."
    }
  ],
  "reasoning_effort": "high",
  "max_completion_tokens": 8000
}
```

### Cached Repeated Context
Reuse a large system prompt with 95% cached input discount
```json
{
  "model": "gpt-6.1-sol",
  "messages": [
    {
      "role": "system",
      "content": "<large repeated system prompt or codebase context>"
    },
    {
      "role": "user",
      "content": "Summarize the open TODOs and rank them by risk."
    }
  ],
  "max_completion_tokens": 4000
}
```

## 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
- Same $2/$10 per M as GPT-6 Sol, but cached inputs are $0.10/M (95% off) instead of $0.20/M — cache-heavy workloads (RAG, long system prompts) cost less here
- For tool calling use the Responses API (POST /llm/openai/v1/responses) — Chat Completions is supported on this model without tool calling
- reasoning_effort accepts low, medium (default), high, xhigh and max — 'none' and 'minimal' are rejected
- Keep prompts under 272K input tokens where possible — above that the whole request bills at 2x input and cache / 1.5x output
- Cache writes bill at 1.25x the input rate ($2.50/M) — implicit caching writes by default, so most of a large first prompt is billed as a cache write, then reads are 95% off
- Fast mode (service_tier: fast or priority) bills token charges at 2x and Ultrafast mode (service_tier: ultrafast, Responses API) at 6x — both are settled on the tier the response reports, so a request downgraded to standard is billed at the standard rate
- 128K output enables single-shot long-form generation

## Documentation
https://developers.openai.com/api/docs/models/gpt-6.1-sol