ZMIME
OpenAI · Released Apr 14, 2025

GPT-4.1 mini

Affordable GPT-4.1 lane for fast coding help and structured extraction.

  • Proprietary
  • Tool calling
  • Vision
Capability
135.0ECI · #115 of 148
Input
$0.40per 1M tokens
Output
$1.60per 1M tokens
Context
1.05M33K max output
Pricing

What it costs

Input
$0.40per million tokens
Output
$1.60per million tokens
Cached input
$0.10per million tokens
Blended (3:1)
$0.70cheaper than 53% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$1.60
Team assistant25M input + 5M output tokens$18.00
Production app250M input + 50M output tokens$180.00

Official OpenAI API price, as listed on models.dev.

Capability

Independent benchmarks

135.0Epoch Capabilities Index
#115 of 148 scored models
88Median 146167

The shaded band is Epoch AI’s confidence range (131.2–136.6); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions65.9%
  • FrontierMath Tiers 1–3Research-level mathematics6.7%
  • OTIS Mock AIME 2024–2025Competition mathematics44.7%
  • SimpleQA VerifiedShort factual questions12.7%

Scores from Epoch AI, run independently of OpenAI.

Specifications

The details

Lab
OpenAI
Released
Apr 14, 2025
Knowledge cutoff
Apr 2024
Context window
1,047,576 tokens
Max output
32,768 tokens
Inputs
Text, Images, PDFs
Output
Text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Weights
Proprietary
API model ID
gpt-4.1-minion OpenAI
Availability
24 API providerslisted on models.dev

OpenAI model documentation

Lab-reported

What OpenAI claims

Published by the lab at launch. Settings vary, so compare these only with care.

BenchmarkScoreSettingSource
Aider Polyglot32.4 percent correct—Source
Same lab

More from OpenAI

Questions

About GPT-4.1 mini

How much does GPT-4.1 mini cost?

GPT-4.1 mini costs $0.40 input / $1.60 output per million tokens (official OpenAI API price). Cached input is $0.10 per million tokens. At a 3:1 input-to-output mix that is $0.70 per million tokens, cheaper than 53% of the 360 priced models we track.

What is the context window of GPT-4.1 mini?

GPT-4.1 mini accepts up to 1,047,576 tokens per request and can write up to 32,768 tokens in one response.

How good is GPT-4.1 mini?

Epoch AI gives GPT-4.1 mini a Capabilities Index score of 135.0 (likely range 131.2–136.6), ranking it #115 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 65.9%, FrontierMath Tiers 1–3 6.7%, OTIS Mock AIME 2024–2025 44.7%, SimpleQA Verified 12.7%.

Is GPT-4.1 mini open source?

No. GPT-4.1 mini is proprietary; you use it through OpenAI’s API or partner platforms.

What inputs does GPT-4.1 mini support?

GPT-4.1 mini accepts text, images and PDFs and replies in text. It is not a dedicated reasoning model, supports tool calling and can return structured JSON output.

When was GPT-4.1 mini released?

OpenAI released GPT-4.1 mini on Apr 14, 2025. Its training data runs to Apr 2024.

What are the best alternatives to GPT-4.1 mini?

The closest current models from other labs on capability, price and release date are Mistral Medium 3 (Mistral AI, ECI 134.1, $0.40 / $2.00), QwQ 32B (Alibaba (Qwen), ECI 137.6, $0.66 / $1.00), DeepSeek V3 0324 (DeepSeek, ECI 135.9, $0.24 / $0.90) and Llama 4 Maverick 17B Instruct (Meta, ECI 132.2, $0.321 / $0.91).