o4 Mini

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
$0.28
/ 1M tokens (read)
Context
200K tokens
Max output 100K tokens

Overview

OpenAI's o4 Mini is a capable model, sitting in a mid-to-high tier, designed for complex workloads requiring advanced reasoning and multimodal understanding. It supports vision and provides robust structured output capabilities.

Strengths

  • Handles extensive input and output with a 200,000-token context window.
  • Generates very long responses, supporting up to 100,000 output tokens.
  • Possesses multimodal capabilities including robust vision processing.
  • Enables reliable structured data extraction using JSON mode and function-calling.
  • Offers advanced reasoning capabilities for complex problem-solving.

Best use cases

  • Analyzing extensive documents or codebases with its large context window.
  • Generating long-form content, such as reports, articles, or detailed summaries.
  • Processing and understanding visual information for diverse applications.
  • Integrating with external tools via function-calling and precise JSON output.
  • Complex data analysis and decision-making requiring advanced reasoning.

Pricing position

The o4 Mini is at the higher end of OpenAI's listed models, priced significantly above 'Nano' and 'Mini' variants like GPT-4o-mini ($0.15/M input). Compared to similarly-priced peers, its input cost of $1.1/M is competitive with Qwen and Claude Haiku. Its $4.4/M output price is more economical than Qwen3.6 Max Preview ($6.24/M) and Claude Haiku 4.5 ($5/M), but higher than Sonar ($1/M) and Grok Build 0.1 ($2/M).

Caveats

The o4 Mini model does not offer a free tier, meaning initial exploration requires a financial commitment. Despite its large 200,000 token context window, it is not the largest available from OpenAI, with GPT-4.1 Nano offering over 1M tokens. For extremely high-volume applications prioritizing output cost, some peers like Sonar or Grok Build 0.1 offer significantly lower output pricing.

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

Image inputFunction 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