o3 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
$0.55
/ 1M tokens (read)
Context
200K tokens
Max output 100K tokens

Overview

OpenAI's o3 Mini is a mid-tier model designed for workloads requiring substantial context and structured interactions. It offers advanced capabilities like function-calling and JSON mode, targeting applications that benefit from its 'thinking' capability.

Strengths

  • Provides a very large 200,000-token context window for extensive information processing.
  • Supports an impressive maximum output of 100,000 tokens for detailed responses.
  • Equipped with function-calling and JSON mode for structured interaction and integration.
  • Features a 'thinking' capability, indicating robust reasoning for complex tasks.
  • Offers a competitive cache read price of $0.55/1M tokens for cost-efficient repeated use.

Best use cases

  • Building AI agents that integrate with external tools via function-calling.
  • Processing and summarizing very large documents and codebases efficiently.
  • Generating detailed, long-form content or extensive structured reports.
  • Extracting complex data into precise JSON formats for downstream applications.
  • Powering conversational assistants requiring deep understanding and structured responses.

Pricing position

o3 Mini is positioned at a premium within OpenAI's 'Mini' and 'Nano' lineup, with an input price of $1.1/1M tokens and an output price of $4.4/1M tokens, making it considerably more expensive than GPT-5 Mini's $0.25/$2 per million tokens. Compared to similarly-priced peers like Qwen-Max ($1.04/$4.16 per million tokens) or Claude Haiku 4.5 ($1/$5 per million tokens), its input price is slightly higher, but its output price is competitive or lower.

Caveats

While powerful, o3 Mini lacks specific multimodal capabilities like vision or audio processing, which might be critical for some applications. Its premium pricing, especially the $1.1/1M token input cost, means that for tasks not requiring its very large context window or extensive output, other, more cost-optimized OpenAI models could offer better value. Additionally, there is no free tier available for this model.

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