Model

o4-mini

Compact OpenAI reasoning model — fast, cheap, with native structured-output support.

About

Overview

o4-mini is OpenAI's small reasoning model — fast and cost-efficient, with native tool use and structured-output support. Use it for high-throughput classification, routing, and lightweight analytical workloads. Available inside your Snowflake account via Cortex.

OpenAIReasoningFastTool UseStructured Output

Vendor Support

Specifications

Family: o-series
Tier: Fast
Context Window: 200K tokens
Max Output: 100K tokens
Input Pricing: $1.1 / MTok
Output Pricing: $4.4 / MTok
Knowledge Cutoff: 2025-06
Modalities: Text in, Image in, Text out

Capabilities

Tool Use: Supported
Extended Thinking: Supported
Prompt Caching: Supported
Batch API: Supported
Streaming: Supported
Vision: Supported

Data Plane Dependencies

This model runs on the data plane providers listed below. Installing at least one makes the model available to use.

Not Installed

Snowflake

Hosted on Snowflake Cortex inside your Snowflake account — keeps data resident.