OpenAI: o3 Mini High

OpenAI: o3 Mini High is a large language model from OpenAI. It costs $1.10 per million input tokens and $4.40 per million output tokens. Its context window is 200K tokens.

ReasoningTool callingStructured outputPrompt cachingfile input

Input / 1M tokens: $1.10
Output / 1M tokens: $4.40
Cached input / 1M: $0.550
Context window: 200K

This model also charges $0.01 per search request

That is $10.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.0033, so the search fee is 3.0× the token cost. Per-token rankings elsewhere ignore this entirely.

Who serves it cheapest

1 hosts serve o3 Mini High. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: o3 Mini High, cheapest first
Provider	Input / 1M	Output / 1M	Context	Throughput	Uptime 24h
OpenAICheapest	$1.10	$4.40	200K	-	100.0%

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index: 11.0
Coding index: 16.3
Agentic index: 0.9

About o3 Mini High

OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...

Specifications

OpenAI: o3 Mini High specifications
Model ID	`openai/o3-mini-high`
Provider	OpenAI
Context window	200K tokens
Max output	100K tokens
Input modalities	text, file
Output modalities	text
Knowledge cutoff	2023-10-31
Open weights	No
Released	February 12, 2025

Cheaper alternatives

Models that cost less than o3 Mini High while keeping at least half its context window and every input modality it supports.

Sakana Namazu

$0.950 in · $4.00 out

1.1× cheaper

GPT-5.4 Mini

$0.750 in · $4.50 out

1.1× cheaper

Grok 4.3

$1.25 in · $2.50 out

1.2× cheaper

Grok 4.20 Multi-Agent

$1.25 in · $2.50 out

1.2× cheaper

Grok 4.20

$1.25 in · $2.50 out

1.2× cheaper

Frequently asked

How much does OpenAI: o3 Mini High cost?

$1.10 per million input tokens and $4.40 per million output tokens. Cached input reads cost $0.550 per million tokens.

What is the context window of OpenAI: o3 Mini High?

200K tokens, with up to 100K tokens of output per request.

Does OpenAI: o3 Mini High have extra fees beyond per-token pricing?

Yes. OpenAI: o3 Mini High charges $0.01 per search request - $10.00 per 1,000 requests - on top of $1.10 per million input tokens and $4.40 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 3.0× the token cost.

Confirm against the source: OpenAI official pricing.