Skip to main content
OpenAISlowUltra

o1 Pro

Legacy pro-tier reasoning model. Uses more compute than o1 for the most reliable answers on hard problems. Predecessor to o3-pro, which offers better value.

278,700/1,114,800credits
input / output ยท per 1M tokens
Pro-tier chain-of-thought reasoning
200K context window
100K max output tokens
Vision capabilities
Function calling support

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
200K
tokens
Max Output
100K
tokens
Training Cutoff
2023-10
Compatible SDK
OpenAI

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens278,700$185.80
Output Tokens1,114,800$743.20

* 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": "o1-pro",
  "messages": [
    {
      "role": "user",
      "content": "Prove or disprove: every planar graph is 4-colorable. Outline the structure of the argument step by step."
    }
  ],
  "max_completion_tokens": 8000
}'

Parameters

ParameterTypeRequiredDefaultDescription
messagesarrayYes-Array of message objects
modelstringYeso1-proModel identifier
max_completion_tokensintegerNo-Maximum tokens for completion (includes reasoning tokens)
reasoning_effortstringNo-Reasoning effort level: low, medium, high
lowmediumhigh

Examples

Deep Reasoning

High-reliability reasoning with o1 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": "o1-pro",
  "messages": [
    {
      "role": "user",
      "content": "Prove or disprove: every planar graph is 4-colorable. Outline the structure of the argument step by step."
    }
  ],
  "max_completion_tokens": 8000
}'

Tips & Best Practices

1Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openai/v1
2Legacy model - consider o3-pro for better value (stronger reasoning at a fraction of the price)
3Use max_completion_tokens instead of max_tokens - temperature is not supported
4Responses take significantly longer due to extended internal reasoning

Use Cases

Legacy workloads pinned to o1 Pro behavior
High-reliability scientific reasoning
Complex mathematical problems
Critical code verification