o3 Mini High

Provider: OpenAI US

No longer listed on OpenRouter since 2026-10-28. The figures below are the last recorded values.
Input price
$1.10
/ 1M tokens
Output price
$4.40
/ 1M tokens
Cache price
$0.55
/ 1M tokens (read)
Context
200K tokens
Max output 100K tokens

Overview

OpenAI's o3 Mini High is positioned as a higher-end mid-tier or specialized reasoning model. It targets complex workloads requiring advanced processing, structured outputs, and extensive long-form generation.

Strengths

  • Features a substantial 200,000 token context window for extensive input processing.
  • Capable of generating very long responses, up to 100,000 tokens.
  • Supports robust function-calling and ensures structured JSON output.
  • Offers advanced "thinking" capabilities for complex reasoning tasks.
  • Cache read pricing provides potential cost efficiencies for repeated prompts.

Best use cases

  • Generating comprehensive structured reports, detailed summaries, or long-form content.
  • Automating multi-step workflows that integrate with external tools via function calls.
  • Analyzing and processing large codebases or extensive documentation efficiently.
  • Building applications requiring precise, well-formatted JSON data exchanges.
  • Tasks demanding advanced reasoning over broad datasets with significant output.

Pricing position

At $1.1/1M input and $4.4/1M output, o3 Mini High is significantly more expensive than OpenAI's other "Mini" or "Nano" models. Its input price is comparable to peers like Qwen3.6 Max Preview ($1.04/M) and Claude Haiku 4.5 ($1/M), but its output price is often higher than these competitors.

Caveats

This model is considerably more expensive than many OpenAI alternatives, including those with larger context windows like GPT-4.1 Nano (1M tokens). Developers should consider its cost relative to cheaper models for tasks not requiring its very large output or advanced thinking capabilities. There is no free tier available for experimentation or low-volume use.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
100K tokens
Tracked since
2026-05-08
Last updated
2026-10-28

Features

Function callingJSON outputReasoning

Price history

  • 2026-10-28 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.33
1M (small app) 1 0.5 $3.30
10M (mid scale) 10 5 $33.00
100M (large) 100 50 $330.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from OpenAI

Similar-priced models

Source: OpenRouter API