openai Vision Reasoning

o4 Mini pricing & benchmarks

Released Apr 16, 2025 · served by 1 provider

Input / 1M tokens$1.10
Output / 1M tokens$4.40
Context window200K
Cached input$0.275
1M in + 300K out$2.42

What o4 Mini is

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

Providers and prices for o4 Mini

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
OpenAIcheapest $1.10 $4.40 200K 100.0%

o4 Mini benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
gamedev models #89 1059 50%
uicomponent models #92 1021 46.9%
dataviz models #95 1021 50%
3d models #102 910 34%
codecategories models #103 1006 46.4%
website models #104 1010 47.1%

FAQ

How much does the o4 Mini API cost?

$1.10 per 1M input tokens and $4.40 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $2.42.

Is o4 Mini free?

No. It is a paid model starting at $1.10 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for o4 Mini?

OpenAI at $1.10 input / $4.40 output per 1M tokens.

Can I self-host o4 Mini?

No. o4 Mini is closed-weight and only available through hosted APIs.