Back to all models

o3-mini

OpenAI · o3

Default
Latest in family

Key Metrics

Input Limit

200K tokens

Output Limit

100K tokens

Input Cost

$1.10/1M

Output Cost

$4.40/1M

Sample API Code

Sample Python code not provided in this section.

Required Libraries

Notes

o3-mini is our newest small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini supports key developer features, like Structured Outputs, function calling, and Batch API. Snapshots let you lock in a specific version of the model so that performance and behavior remain consistent. Available snapshots and aliases include o3-mini, o3-mini-2025-01-31.

Capabilities

Structured Outputs
Function calling
Batch API
Streaming
Reasoning
Chat Completions
Realtime processing
Assistants API compatibility

Supported Data Types

Input Types

Text

Output Types

Text

Strengths & Weaknesses

Exceptional at

Reasoning
High intelligence

Good at

Structured Outputs
Function calling
Batch API
Streaming

Poor at

Image processing
Audio processing

Additional Information

Latest Update

Jan 31, 2025

Knowledge Cutoff

2023-10-01

ELO Score

1305