# GPT-5.1 Codex Max - Core.Today AI API

> OpenAI's long-horizon agentic coding flagship in the GPT-5.1 Codex family. Supports compaction to keep very long coding sessions within context, and is served via the OpenAI Responses API.

- **Provider**: OpenAI
- **Model ID**: gpt-5.1-codex-max
- **Category**: LLM
- **Credits**: 10 per 1K tokens (avg)
- **Speed**: Medium
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 400K tokens
- **Max Output**: 128K 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**: 2,322.5 credits ($1.55)
- **Output Tokens**: 18,580 credits ($12.39)
- **Cached Tokens**: 232.25 credits ($0.15)

## Features
- Long-horizon agentic coding flagship
- Compaction support for very long sessions beyond the raw context window
- Served via the Responses API - this gateway routes Codex models to /v1/responses, not chat completions
- 400K context window
- Cached input tokens for cost savings on repeated context

## Use Cases
- Multi-hour autonomous coding sessions
- Large refactors spanning many files
- Project-scale migrations and upgrades
- Complex debugging with long tool-use trajectories

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/openai/v1/responses

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **model**: string (default: gpt-5.1-codex-max) - Model identifier
- **input**: string | array - Responses API input: a plain string or an array of input items (messages, tool results)

### Optional
- **instructions**: string - System-level instructions for the run
- **max_output_tokens**: integer - Maximum tokens in the response (Responses API field; not max_tokens)
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### Long-Horizon Refactor
Responses API request for a large multi-file task
```json
{
  "model": "gpt-5.1-codex-max",
  "input": "Migrate this codebase's HTTP layer from callbacks to async/await. Work file by file and keep tests green.",
  "max_output_tokens": 8000
}
```

## 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
- Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openai/v1 and use client.responses.create()
- Codex models are served via the Responses API (POST /llm/openai/v1/responses), not chat completions
- Compaction lets sessions run far beyond the raw context window - prefer Codex Max for very long agent runs
- Same token pricing as GPT-5.1 Codex - choose Max for long-horizon work, not for cost reasons

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