OpenAIReleased on Apr 16, 2025

o4-mini: API Pricing, Context Window & Benchmarks

o4-mini is a language model from OpenAI, released in April 2025, with multimodal input.

o4-mini is OpenAI's latest small o-series model, optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks. It is faster and more affordable than o3.

Input
TextImage
Output
Text
Speed
Latency p955.20s
Throughput P95115char/s
Cost
$1.47/ 1M · 8:1 in:out
$1.10 in · $4.40 out

o4-mini benchmarks

Rankings

Quality Tracker

o4-mini Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Tue Jul 28 2026
Notice missing or incorrect data?

o4-mini pricing

Providers

o4-mini starts at $1.10 per million input tokens and $4.40 per million output tokens via OpenAI.

ProviderInput $/MOutput $/MContext in / outTTFT p50 / p95 sOutput avg / p5 c/sSuccess 7dModalities in / out
OpenAI logoOpenAI
$1.10$4.40200.0K/100.0K
—/5.20
115/—
—
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.

o4-mini context window

Input and output token limits for o4-mini, plus how it ranks on long-context understanding.

InputOutput
200Ktokens
100Ktokens
≈ 301 pages of text
200K
8K128K1M

o4-mini API

Available from the model provider

o4-mini has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

o4-mini latency

o4-mini time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

o4-mini examples

Recent arena outputs from o4-mini, picked from the highest-ranked matchups.

o4-mini license

o4-mini is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of May 2024.

License
Proprietary
Hosted access
Knowledge cutoff
May 2024

Proprietary license - usage restrictions apply

o4-mini resources

Official sources for o4-mini: api documentation, paper or system card, source repository.

o4-mini vs other models

The most-compared alternatives to o4-mini are Seed 2.0 Lite, K-EXAONE-236B-A23B, LongCat-Flash-Thinking. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like o4-mini

Models ranked just above and below o4-mini by LLM Stats score.

 

Seed 2.0 Lite

Score pending
DetailsCompare
 

K-EXAONE-236B-A23B

Score pending
DetailsCompare
 

LongCat-Flash-Thinking

Score pending
DetailsCompare
 

GPT OSS 120B High

Score pending
DetailsCompare
 

Nova 2 Pro

Score pending
DetailsCompare
 

Qwen3-235B-A22B-Thinking-2507

Score pending
DetailsCompare

FAQ

Common questions about o4-mini.

When was o4-mini released?

o4-mini was released on April 16, 2025 by OpenAI. This is the official o4-mini release date tracked on LLM Stats.

How much does o4-mini cost?

o4-mini pricing starts at $1.10 per million input tokens and $4.40 per million output tokens via OpenAI, the lowest price among tracked providers.

Is o4-mini available via API?

Yes, o4-mini is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

Who created o4-mini?

o4-mini was created by OpenAI.

What is the license for o4-mini?

o4-mini is released under the Proprietary license.

What is the knowledge cutoff date for o4-mini?

o4-mini has a knowledge cutoff of May 2024, meaning it was trained on data up to that point and may not know about events after it.

Is o4-mini multimodal?

Yes, o4-mini is multimodal and can accept both text and images as input.

What is o4-mini latency?

o4-mini p95 time to first token is 5.20 seconds via OpenAI over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use o4-mini?

o4-mini is available through 1 provider including OpenAI.

Where is the o4-mini paper or technical report?

o4-mini has a paper or technical report available at https://cdn.openai.com/pdf/2221c875-02dc-4789-800b-e7758f3722c1/o3-and-o4-mini-system-card.pdf. Use that source for architecture, training, release and evaluation details.

What models should I compare o4-mini against?

Common o4-mini comparisons include o4-mini vs Seed 2.0 Lite, o4-mini vs K-EXAONE-236B-A23B, o4-mini vs LongCat-Flash-Thinking. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.