OpenAI
OpenAI
MultimodalLIVE PRICING

GPT-4.1 Mini (batch)

text+image+file->text

A smaller GPT-4.1 with the same 1M context. Replaces GPT-4o mini for most production traffic.

GPT-4.1 Mini (batch) is a multimodal AI model from OpenAI. It costs $0.200 per million input tokens and $0.800 per million output tokens (blended $0.380/M), with a 1,047,576-token context window.

Profile inherited from upstream GPT-4.1 mini ↗ — this is a hosted variant of the same open-weights model.

INPUT
$0.200/M
per million input tokens
OUTPUT
$0.800/M
per million output tokens
BLENDED 70/30
$0.380/M
unchanged since 3 May
CONTEXT
1,047,576
tokens
What it is good at
  • 1M context at low price
  • Fast
  • Capable coding
Typical use cases
  • High-volume chat
  • Long-doc summarisation on a budget

Benchmarks

vs. best public score
Scores inherited from GPT-4.1 mini — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU81%
Multitask academic knowledge across 57 subjects.
Graduate-level science questions, "Google-proof".
MATH78%
High-school competition math problems.
Python function synthesis from docstrings.
Real GitHub issues solved end-to-end.
LMArena Elo1290 Elo
Crowd-sourced head-to-head preference Elo rating.
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-4.1 Mini (batch) cost?

GPT-4.1 Mini (batch) costs $0.200 per million input tokens and $0.800 per million output tokens, for a blended reference rate of $0.380 per million tokens.

What is GPT-4.1 Mini (batch)'s context window?

GPT-4.1 Mini (batch) supports up to 1,047,576 tokens of context in a single request.

What is GPT-4.1 Mini (batch) best for?

GPT-4.1 Mini (batch) is well suited to 1M context at low price, Fast and Capable coding.

Who makes GPT-4.1 Mini (batch)?

GPT-4.1 Mini (batch) is developed and served by OpenAI.

Terms used on this page