Flash — fastest and cheapest, lighter reasoningCommercial API

o4 Mini (batch) Pricing

OpenAI · openai-o4-mini-batch

ShareX Facebook LinkedIn

Input / 1M tokens

$0.550

Output / 1M tokens

$2.20

Context window

200k tokens

≈ 267 pages of text

Max output

100k tokens

What it costs in practice

Typical request (1,200 in + 400 out tokens)$0.0015

1,000 requests / month$1.54/mo 10,000 requests / month$15.40/mo 100,000 requests / month$154.00/mo

Estimate your own workloadOpens the calculator with o4 Mini (batch) preloaded — adjust volume and token counts there.

Price history

Only one price point recorded so far.

The staircase chart appears once a price change is detected.

What it excels at

Handles high-volume batch workloads with text and vision inputs at low per-token cost. Suitable for repetitive classification, extraction, and light reasoning tasks.

The business tradeoff

Reasoning depth lags behind non-mini o-series models. Batch-only access restricts interactive or low-latency applications.

Cheaper from OpenAI

GPT-5.6 Luna (batch)OpenAI$0.0004/ typical request GPT-5 MiniOpenAI$0.0011/ typical request GPT-5.6 Luna ProOpenAI$0.0004/ typical request

Same tier from other providers

Claude Haiku 4.5Anthropic$0.0032/ typical request Gemini 3.5 FlashGoogle$0.0054/ typical request Llama 3.3 70BMeta$0.0002/ typical request

Head-to-head

o4 Mini (batch) vs Claude Haiku 4.5 →o4 Mini (batch) vs Gemini 3.5 Flash →o4 Mini (batch) vs Llama 3.3 70B →

Vendor list rates, as of Aug 6, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.