OpenAI
MultimodalPriced via OpenRouter

GPT-4o-mini (batch)

text+image+file->text

The cheap multimodal workhorse of 2024. Largely superseded by GPT-4.1 mini, but still cost-competitive and widely deployed.

GPT-4o-mini (batch) is a multimodal AI model from OpenAI. It costs $0.0750 per million input tokens and $0.3000 per million output tokens (blended $0.1425/M), with a 128,000-token context window.

Profile inherited from upstream GPT-4o mini ↗ — this is a hosted variant of the same open-weights model.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.0750/M
per million input tokens
OUTPUT
$0.3000/M
per million output tokens
BLENDED 70/30
$0.1425/M
unchanged since 3 May
CONTEXT
128,000
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Cheap multimodal
  • Fast
  • 128K context
Typical use cases
  • Cost-sensitive vision
  • High-volume chat
  • Legacy 4o-mini integrations

Benchmarks

vs. best public score
Scores inherited from GPT-4o mini — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU82%
Multitask academic knowledge across 57 subjects. Source: OpenAI (self-reported), MMLU, read 2026-11-10.
Graduate-level science questions, "Google-proof". Source: OpenAI (self-reported), GPQA Diamond, read 2026-11-10.
MATH70.2%
High-school competition math problems. Source: OpenAI (self-reported), MATH, read 2026-11-10.
HumanEval87.2%
Python function synthesis from docstrings. Source: OpenAI (self-reported), HumanEval, read 2026-11-10.
LMArena Elo1318 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from OpenAI

See all 28 →

Frequently asked questions

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

GPT-4o-mini (batch) costs $0.0750 per million input tokens and $0.3000 per million output tokens, for a blended reference rate of $0.1425 per million tokens.

What is GPT-4o-mini (batch)'s context window?

GPT-4o-mini (batch) supports up to 128,000 tokens of context in a single request.

What is GPT-4o-mini (batch) best for?

GPT-4o-mini (batch) is well suited to Cheap multimodal, Fast and 128K context.

Who makes GPT-4o-mini (batch)?

GPT-4o-mini (batch) is developed and served by OpenAI. It was released in Jul 2024.

Terms used on this page