Home  /  Models  /  OpenAI o1-mini
⚡ Quick Pricing Summary

OpenAI o1-mini by OpenAI costs $1.10 per 1 Million input tokens and $4.40 per 1 Million output tokens. It features a 128k context window and has a blended 3:1 production rate of $1.925/1M tokens.

OpenAI Reasoning / Deep Thinking

OpenAI o1-mini

Fast and economical reasoning model optimized for coding and math without vision overhead.

Calculate Spend in App →
Input Token Price
$1.10
Per 1,000,000 tokens
Output Token Price
$4.40
Per 1,000,000 tokens
Prompt Caching Rate
$0.550
Save up to 80% on cached inputs
Max Context Window
128k
Max output: 65k tokens

Verified Specifications & Benchmark Data

Developer / Provider OpenAI
Model Family o-Series
Blended 3:1 Rate (Production Benchmark) $1.925 / 1M tokens
Batch API Discount (24hr SLA) 50% off standard rate
Multimodal Vision ❌ Text Only
Function Calling / Structured Outputs ✅ Native Tool Calling
MMLU Benchmark Score 85.2%
Latency & Throughput Tier Fast Reasoning (~55 t/s)
Optimal Architecture & Use Cases STEM problem solving, code generation, algorithmic optimization

Frequently Asked Questions about OpenAI o1-mini

How much does OpenAI o1-mini cost per 1M tokens?

OpenAI o1-mini pricing is set at $1.10 per 1 million input tokens and $4.40 per 1 million output tokens. For high-volume batch workloads, 24-hour batch queues provide a 50% off standard rate.

How much money does OpenAI o1-mini prompt caching save?

With prompt caching enabled, cached input tokens are discounted to $0.550/1M, saving 50% on repeated system prompts and document vectors.

What is the context window limit of OpenAI o1-mini?

OpenAI o1-mini has a maximum context window of 128k (128,000 tokens), supporting up to 65,536 completion tokens per response.

Direct Matchups with OpenAI o1-mini

See how OpenAI o1-mini compares against other leading frontier and open-weights models in cost and latency.