Skip to main content
Core.Today
|
OpenAISlowUltra

GPT-5.2 Pro

Maximum-capability tier of the GPT-5.2 family (dated snapshot). Thinks longer with more compute to deliver the most reliable answers on the hardest reasoning and coding tasks.

39,018/312,144credits
input / output ยท per 1M tokens
Maximum-capability GPT-5.2 tier
256K context window
32K max output tokens
Extended thinking for hardest problems
Native multimodal support
Advanced function calling

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Model Specifications

Context Window
256K
tokens
Max Output
33K
tokens
Training Cutoff
2025-06
Compatible SDK
OpenAI

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens39,018$26.01
Output Tokens312,144$208.10

* 1,500 credits โ‰ˆ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-5.2-pro-2025-12-11",
  "messages": [
    {
      "role": "user",
      "content": "Review this database migration plan for a zero-downtime rollout across 40 services and identify every failure mode with mitigations."
    }
  ],
  "max_completion_tokens": 16000
}'

Parameters

ParameterTypeRequiredDefaultDescription
messagesarrayYes-Array of message objects with role and content
modelstringYesgpt-5.2-pro-2025-12-11Model identifier (dated snapshot id)
max_completion_tokensintegerNo-Maximum tokens in response (includes internal reasoning tokens). Note: use max_completion_tokens, not max_tokens
reasoning_effortstringNo-Reasoning effort level: low, medium, or high
lowmediumhigh
streambooleanNofalseEnable Server-Sent Events streaming

Examples

Maximum-Effort Analysis

Hardest reasoning task with GPT-5.2 Pro

curl -X POST "https://api.core.today/llm/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-5.2-pro-2025-12-11",
  "messages": [
    {
      "role": "user",
      "content": "Review this database migration plan for a zero-downtime rollout across 40 services and identify every failure mode with mitigations."
    }
  ],
  "max_completion_tokens": 16000
}'

Tips & Best Practices

1Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openai/v1
2Dated snapshot id - pin this exact id for reproducible behavior
3Reserve for the hardest problems - standard GPT-5.2 is far cheaper for routine tasks
4Responses take longer due to extended internal thinking

Use Cases

Hardest multi-step reasoning problems
High-stakes code generation and review
Research and deep analysis
Complex enterprise workflows