Skip to main content
OpenAISlowUltra

OpenAI o1

OpenAI's most advanced reasoning model. Uses extended thinking time to solve complex problems in science, coding, and math with exceptional accuracy.

15 credits
per 1K tokens (avg)
Advanced chain-of-thought reasoning
200K context window
100K max output tokens
Vision capabilities
Function calling support
Excels at complex problems

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 Tokens15,000$15.00
Output Tokens60,000$60.00
Cached Tokens7,500$7.50

* 1 credit โ‰ˆ $0.001 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
  "model": "o1",
  "input": {
    "model": "o1",
    "messages": [
      {
        "role": "user",
        "content": "Prove that there are infinitely many prime numbers using a proof by contradiction."
      }
    ],
    "reasoning_effort": "high"
  }
}'

Parameters

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

Examples

Complex Math

Solve advanced math problems

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
  "model": "o1",
  "input": {
    "model": "o1",
    "messages": [
      {
        "role": "user",
        "content": "Prove that there are infinitely many prime numbers using a proof by contradiction."
      }
    ],
    "reasoning_effort": "high"
  }
}'

Algorithm Design

Design optimal algorithms

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
  "model": "o1",
  "input": {
    "model": "o1",
    "messages": [
      {
        "role": "user",
        "content": "Design an efficient algorithm to find the longest increasing subsequence in an array. Explain the time complexity and provide Python code."
      }
    ],
    "max_completion_tokens": 4000
  }
}'

Tips & Best Practices

1Best for problems requiring deep reasoning
2Takes longer to respond due to internal reasoning
3Use reasoning_effort='high' for most complex problems
4Not optimized for simple tasks - use GPT-4o instead
5Great for step-by-step problem solving

Use Cases

Scientific research
Complex mathematics
Advanced code generation
Strategic planning
Multi-step reasoning
Research assistance

Model Info

ProviderOpenAI
Version2024-12-17
CategoryLLM
Price15 credits

API Endpoint

POST /llm/openai/v1/chat/completions
Try in PlaygroundBack to Docs