Migrating from gpt-4.1-mini to gpt-5-mini-2025-08-07

What changes when you move from gpt-4.1-mini to gpt-5-mini-2025-08-07: prices, limits, features and parameters, read from each company's own pages.

From: gpt-4.1-mini
Status: Active
Shutdown: none announced
Time left: —

To: gpt-5-mini-2025-08-07
Status: Deprecated
Shutdown: Dec 11, 2026
Time left: 57 days

gpt-5-mini-2025-08-07 is itself deprecated, shutting down Dec 11, 2026. Its replacement is gpt-5.6-terra.

Prices

USD per 1M tokens, standard tier

Type	gpt-4.1-mini	gpt-5-mini-2025-08-07	Change
Input	$0.40first seen October 1, 2026 · source	Not published	—
Cached input	$0.10first seen October 1, 2026 · source	Not published	—
Output	$1.60first seen October 1, 2026 · source	Not published	—

Other tiers, prompt-size bands and modalities are on each model's page.

Limits

Tokens

Limit	gpt-4.1-mini	gpt-5-mini-2025-08-07	Change
Context window	1,047,576 tokensin place when tracking began (October 6, 2026) · source	Not published	—
Max output tokens	32,768 tokensin place when tracking began (October 6, 2026) · source	Not published	—

Benchmarks

Same benchmark and source on both sides; settings named where they differ

Benchmark	gpt-4.1-mini	gpt-5-mini-2025-08-07	Change
FrontierMath Tiers 1-3Epoch AI, high effort (vs no setting). Other settings not run → 18.2% low effort not run → 6.0% minimal effort	6.7%	46.7%	+40.0 pts
GPQA DiamondEpoch AI, high effort (vs no setting). Other settings not run → 71.7% minimal effort not run → 71.7% medium effort	65.8%	75.0%	+9.2 pts
MATH Level 5Epoch AI, high effort (vs no setting). Other settings not run → 96.8% medium effort	87.3%	97.8%	+10.5 pts
OTIS Mock AIME 2024-2025Epoch AI, high effort (vs no setting). Other settings not run → 78.3% medium effort not run → 55.6% minimal effort	44.7%	86.7%	+42.0 pts
SimpleQA VerifiedEpoch AI, high effort (vs no setting).	12.7%	21.6%	+8.9 pts

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

No feature is published for both models, so none can be compared.

Not published for gpt-4.1-mini: Prompt caching, PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.

Not published for gpt-5-mini-2025-08-07: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Context window, Max output tokens.

Free tier

gpt-4.1-mini: no free tier listed

gpt-5-mini-2025-08-07: Free for shared data, 10M tokens a day for Launch and Grow (2.5M for Build), in place when tracking began (October 12, 2026) (source) · All free models

gpt-5-mini-2025-08-07 adds a free tier.

Aliases

All aliases

No aliases point at gpt-4.1-mini.

Aliases pointing at gpt-5-mini-2025-08-07: gpt-5-mini (in place when tracking began (October 7, 2026) · source)

On cloud platforms

All platform dates

Model	Platform	Platform ID	Shutdown	Time left
gpt-4.1-mini	Microsoft Foundryversion 2025-04-14	gpt-4.1-mini	Apr 14, 2027Deprecated	181 days
gpt-5-mini-2025-08-07	Microsoft Foundryversion 2025-08-07	gpt-5-mini	Feb 9, 2027Active	117 days

Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Checklist

Change the model string from gpt-4.1-mini to gpt-5-mini-2025-08-07.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gpt-4.1-mini, gpt-5-mini-2025-08-07.