o3 Mini

OpenAIreasoning

OpenAI's compact reasoning model with extended thinking capabilities for complex problem solving.

Context Window

200K

tokens

Max Output

100K

tokens

Input Price

$1.1

per 1M tokens

Output Price

$4.4

per 1M tokens

Speed

155

tokens/sec

Released

Jan 2025

2025-01-31

Blended Cost

$2.75

per 1M tokens

Value Score

32.0

quality per $

Capabilities

ChatCode GenerationReasoning

Benchmarks

Quality Index
88
MMLU Pro
86.9
HumanEval (Coding)
92.8
MATH
90.1
Arena ELO
1305

About o3 Mini

o3 Mini is a reasoning AI model by OpenAI, released on January 31, 2025. It supports a context window of 200K tokens and can generate up to 100K output tokens.

At $1.1 per million input tokens and $4.4 per million output tokens, its blended cost of $2.75/1M tokens puts it in the mid-range pricing tier. Its value score of 32.0 reflects the balance of quality and cost.

Using o3 Mini with Swfte

Access o3 Mini through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try o3 Mini in our AI Playground before integrating.