Skip to content
CostPerPrompt

GPT-4o-mini (batch) API Pricing

OpenAI · context window 128K · prices updated 2026-08-23

Input per 1M tokens
$0.075
Output per 1M tokens
$0.3
Cached input per 1M
$0.0375
50% cheaper than fresh input

Where GPT-4o-mini (batch) sits on price

At $0.3 per million output tokens, GPT-4o-mini (batch) is a budget tier model — 7.5× cheaper than the median output price of $2.25, which puts it cheaper than 89% and pricier than 11% of the models we track. It sits 6th cheapest of the 93 OpenAI models we track. Output costs 4.0× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
3,333,333
One full context fill
$0.0096
Cheaper than
89% of tracked models

Cached input is 50% cheaper. On an input-heavy workload you need roughly a 50% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on GPT-4o-mini (batch)

These three workloads are the ones teams actually run on a budget-priced model — a $0.3/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. $0 $216
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0001 $2.48
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0004 $113

Model your exact traffic in the API cost calculator — it preloads GPT-4o-mini (batch) with caching and batch options.

GPT-4o-mini (batch) price history

GPT-4o-mini (batch)'s price has not moved since we began tracking it on Aug 6, 2026 — 17 days of stability in a market where 55 of the 302 models we track have repriced over the same period, including 9 of OpenAI's own 93 models.

Change-points from our daily price snapshots (tracking since Aug 6, 2026; intraday moves between snapshots are not captured).

GPT-4o-mini (batch) vs Llama 4 Scout

The closest-priced alternative from another vendor is Llama 4 Scout (Meta) — priced within a rounding error on output, with $0.025 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Llama 4 Scout pricing →

Cheaper alternatives

More OpenAI models

Frequently asked questions

How much does the GPT-4o-mini (batch) API cost?

GPT-4o-mini (batch) costs $0.075 per million input tokens and $0.3 per million output tokens, with cached input at $0.0375 per million (50% cheaper). That works out to roughly 3,333,333 output tokens per dollar.

What does the high-volume classification workload cost on GPT-4o-mini (batch)?

High-volume classification — 200K requests/day (400 in / 20 out) costs about $0 per request and $216 per month on GPT-4o-mini (batch). Short output, huge volume: the input price dominates the bill.

What does it cost to fill GPT-4o-mini (batch)'s 128K context window?

Sending 128K of input in a single request costs $0.0096 at $0.075 per million tokens — before any output. With prompt caching that same fill drops to about $0.0048 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is GPT-4o-mini (batch) worth the price?

GPT-4o-mini (batch) is in the cheapest end of the market — cheaper than 89% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.