o1-2024-12-17

Common Name: o1 (2024-12-17)

OpenAI
Released on Dec 17, 2024 12:00 AMTool Invocation

Snapshot of o1 from December 17, 2024. Reasoning model that uses chain of thought to solve hard problems.

Specifications

Context200,000
Maximum Output100,000
Inputtext, image
Outputtext

Performance (7-day Average)

Uptime
TPS
RURT

Pricing

Input$16.50/MTokens
Output$66.00/MTokens
Cached Input$8.25/MTokens
Batch Input$8.25/MTokens
Batch Output$33.00/MTokens

Usage Statistics

No usage data available for this model during the selected period
View your usage statistics for this model

Similar Models

$16.50/$132.00/M
ctx400Kmax272Kavailtps
InOutCap

GPT-5 pro uses more compute to think harder and provide consistently better answers.

$16.50/$132.00/M
ctx400Kmax272Kavailtps
InOutCap

GPT-5 pro uses more compute to think harder and provide consistently better answers.

$22.00/$88.00/M
ctx200Kmax100Kavailtps
InOutCap

Snapshot of o3-pro from June 10, 2025. Our most capable reasoning model for the hardest problems.

$22.00/$88.00/M
ctx200Kmax100Kavailtps
InOutCap

Our most capable reasoning model, using more compute for the best possible answers on the hardest problems.

Documentation

No documentation available
This model (o1-2024-12-17) uses a dedicated API. Please refer to the official documentation for usage examples.