All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

GPT-4.1 mini

API ID gpt-4.1-mini

gpt-4.1-mini is an OpenAI model, released April 2025. It has a 1,047,576-token context window and up to 32,768 output tokens. It takes image input and supports function calling and structured outputs. Standard price: from $0.40 input and from $1.60 output per 1M tokens.

Status
Active
Released
April 2025
Shutdown
none announced
Replacement
—

No deprecation or shutdown date has been announced as of October 15, 2026.

Benchmarks

Scores as each source published them
or

Comparing with GPT-4o mini, the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features

Arena

ArenaGPT-4.1 miniGPT-4o miniChangeRankDateSource
Text
By category
  • Math 1353 rank 212 vs 1275 (+78)
  • Creative writing 1349 rank 179 vs 1294 (+55)
  • Instruction following 1373 rank 184 vs 1293 (+80)
  • Hard prompts 1403 rank 184 vs 1311 (+92)
  • Long prompts 1390 rank 180 vs 1326 (+64)
  • Multi-turn 1393 rank 173 vs 1311 (+82)
  • Expert 1383 rank 198 vs 1285 (+98)
1383 ±41318 ±4+65186 of 415
38,710 votes		Oct 13, 2026source
Text: Coding1433 ±81348 ±7+85179 of 410
6,821 votes		Oct 13, 2026source
Vision1201 ±81097 ±8+10489 of 165
40,221 votes		Oct 9, 2026source

Rated as gpt-4.1-mini-2025-04-14; GPT-4o mini as gpt-4o-mini-2024-07-18. Ratings come from people voting between two anonymous answers; Text and Vision are style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Epoch AI

BenchmarkGPT-4.1 miniGPT-4o miniChangeSettingRunSource
FrontierMath Tiers 1-36.7%0.7%+6.0 ptsAug 27, 2026source
GPQA Diamond65.8%37.7%+28.1 ptsApr 14, 2025source
MATH Level 587.3%52.6%+34.7 ptsApr 14, 2025source
OTIS Mock AIME 2024-202544.7%6.9%+37.8 ptsApr 14, 2025source
SimpleQA Verified12.7%8.3%+4.4 ptsAug 31, 2026source

Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

On cloud platforms

All platform dates
PlatformPlatform IDStateShutdownTime leftReplacementSource
Microsoft Foundryversion 2025-04-14gpt-4.1-miniDeprecatedApr 14, 2027181 days—source

Read daily from each platform's own pages. The shutdown date and countdown on this page use OpenAI's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Alias

All aliases

Currently points to gpt-4.1-mini-2025-04-14 (in place when tracking began (October 7, 2026)).

Features

Compare models
FeatureValueSinceSource
Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup.Supportedin place when tracking began (October 6, 2026)source
Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result.Supportedin place when tracking began (October 6, 2026)source
Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests.Supportedin place when tracking began (October 6, 2026)source
Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read.Supportedin place when tracking began (October 6, 2026)source
Fine-tuningYou can train your own version of the model on your examples through the company's API, then call it like any other model.Supportedin place when tracking began (October 6, 2026)source
Built-in web searchThe company's API can search the web for the model during a request and cite its sources; you don't need a search service of your own.Supportedin place when tracking began (October 6, 2026)source
Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word.1,047,576 tokensin place when tracking began (October 6, 2026)source
Max output tokensThe longest reply the model can write in one response, in tokens. A token is about three-quarters of an English word.32,768 tokensin place when tracking began (October 6, 2026)source

Not published by OpenAI: Prompt caching, PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.

Price history

USD per 1M tokens, standard tier
$0.00$0.50$1.00$1.50$2.00Oct 2026In $0.40Out $1.60Oct 1, 2026 to Oct 15, 2026: Input $0.40, Output $1.60
$0.00$0.50$1.00$1.50$2.00Oct 2026In $0.40Out $1.60Oct 1, 2026 to Oct 15, 2026: Input $0.40, Output $1.60

We started recording this model's prices on Oct 1, 2026. The history grows with each daily check.

Show as a table
FromTypePrice
Oct 1, 2026Input$0.40
Oct 1, 2026Output$1.60

Prices

USD per 1M tokens, every type and band, by tier
TypeBandPrice $/1MIn effect
Standard
inputshort context$0.40
cached inputshort context$0.10
outputshort context$1.60
Batch
inputshort context$0.20
outputshort context$0.80
Fast
inputshort context$0.70
cached inputshort context$0.175
outputshort context$2.80

Changelog

Changes we detected on OpenAI's pages

No changes recorded yet.

Email alerts

Get an email if gpt-4.1-mini changes

We'll email you the same morning we spot a deprecation notice, a new or moved shutdown date, a price change, or the model leaving OpenAI's model list.

No password: one email to confirm, and you can unsubscribe any time. Privacy

Last checked · Sources: OpenAI deprecations, OpenAI pricing, OpenAI models