o4-mini

Retired Oct 2026

OpenAI's small, fast reasoning model, released April 2025 alongside o3, notably strong at math.

Context: 200K tokens
Max output: 100K
Cutoff: Jun 2024
Released: Apr 2025

Visit OpenAI Compare vs other LLMs →

Hosted API price

Cheapest via Replicate · per 1M tokens

USD

Input: $1.00 /1M
Output: $4.00 /1M
Hosted by: 2 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving o4-mini, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving o4-mini, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cached input /1M	Cost at 10M in + 2M out	Link
Replicate Cheapest	$1.00	$4.00		$18.00	Visit website
Azure	$1.10	$4.40	$0.275	$19.80	Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Similarly priced models

The models nearest o4-mini by blended rate, each at its own cheapest provider.

Models priced nearest o4-mini per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs o4-mini
GPT-5.4 Mini OpenAI	$1.375	$0.75	$4.50	400K	Aug 2025	−8%
Kimi K2.7 Code Moonshot AI	$1.375	$0.90	$3.75	262K		−8%
Grok 4.20 (Non-Reasoning) xAI	$1.4583	$1.25	$2.50	1M		−3%
Grok 4.20 (Reasoning) xAI	$1.4583	$1.25	$2.50	1M		−3%
Grok 4.3 xAI	$1.4583	$1.25	$2.50	1M		−3%
o4-mini This model OpenAI	$1.50	$1.00	$4.00	200K	Jun 2024
Claude Haiku 4.5 Anthropic	$1.6667	$1.00	$5.00	200K	Feb 2025	+11%
GLM-5-Turbo Z.AI	$1.6667	$1.20	$4.00	205K		+11%
GLM-5V-Turbo Z.AI	$1.6667	$1.20	$4.00	205K		+11%
GPT-6.1 Terra OpenAI	$1.6667	$1.00	$5.00	1M	Jun 2026	+11%
Qwen3.7-Max Alibaba Cloud	$1.6667	$1.25	$3.75	1M		+11%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Lyceum

NVIDIA H200 from $2.20/hr, B200 from $3.40/hr, B300 from $3.80/hr

Per-second billing with no minimum commitment or vendor lock-in

Scale to 8,000 GPUs over InfiniBand for distributed AI training

View Pricing

Capabilities

What o4-mini accepts and can do, as published by OpenAI.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.
Web search Search the web for up-to-date information.
Code execution Write and execute code in a sandboxed environment.
File upload Process uploaded documents, spreadsheets, and other files.
MCP Connect to services via Model Context Protocol.

Common questions

What is o4-mini good for?

Cost-sensitive reasoning with tools, coding and visual tasks, as OpenAI's small o-series model. It sits in the lower half of OpenAI's price range.

When is o4-mini not a good fit?

New projects: OpenAI says GPT-5 Mini succeeds it and plans to shut it down in October 2026. Its knowledge is older and its inputs shorter than the GPT-5 line's, and there is no audio or video input.

What is the cheapest way to run o4-mini?

The cheapest hosted rate is $1.00 / $4.00 per 1M tokens via Replicate.

How does o4-mini compare with o3-mini?

OpenAI says o4-mini beats o3-mini on non-STEM tasks and data science, not just math and coding, and like o3 it is trained to use tools inside its reasoning and can think with images. Same 200K-token context. o4-mini costs 9% less per 1M input tokens and 9% less per 1M output tokens than o3-mini, at each model's cheapest listed provider. It came out 3 months later, has a newer knowledge cutoff (June 2024 against October 2023) and takes image input, which o3-mini does not.

Can I self-host o4-mini?

No. OpenAI does not publish the weights; o4-mini is available only through hosted APIs.