OpenAI O1 Reasoning Model
OpenAI retired o1 from its API on October 23, 2026. This record preserves historical model details; the former API identity is unavailable, and OpenAI recommends GPT-5.6 Sol as a migration target.
- OpenAI recommended migration target
A different model requiring its own input, output, price and behavior checks.
🚀Function Overview
o1 is a historical model retired from OpenAI’s API on October 23, 2026. A migration suggestion is not an automatic runtime replacement.
Key Features
- OpenAI shutdown date: October 23, 2026; exact alias/snapshot scope in the official deprecations table.
- Historical specifications and sample syntax below do not prove current endpoint or gateway access.
- Examples are historical illustrations; GetLLMs did not execute requests or verify historical sample outputs.
- Reasoning effort control with low/medium/high settings
- Multimodal capabilities supporting image inputs
- High performance on complex math/coding/science benchmarks
- Historical hardware and aggregator prices have not been verified against an archived provider contract; no current direct OpenAI price is implied.
Use Cases
- •Research analysis in data science, law, and medicine
- •Debugging complex software engineering issues
- •Technical content validation and writing
- •Advanced mathematical problem solving
- •PhD-level scientific reasoning
⚙️Input Parameters
prompt
stringThe prompt to send to the model. Do not use if using messages.
system_prompt
stringSystem prompt to set the assistant's behavior
image_input
arrayList of images to send to the model
reasoning_effort
stringConstrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
max_completion_tokens
integerMaximum number of completion tokens to generate
💡Usage Examples
Example 1
Input Parameters
{
"prompt": "What are the colors of the rainbow?",
"messages": [],
"image_input": [],
"system_prompt": "You are a pathological liar.",
"reasoning_effort": "medium",
"max_completion_tokens": 4096
}Output Results
Quick Actions
Technical Specifications
- Hardware Type
- Not specified
- Run Count
- 12.3k
- Commercial Use
- Supported
- Pricing
- Retired direct OpenAI API model; historical prices are not established by the reviewed sources. Previous aggregator quotes are unverified.
- Platform
- Replicate