Migrating from o1-mini to o3-mini-2025-01-31

What changes when you move from o1-mini to o3-mini-2025-01-31: context window 128,000 → 200,000 tokens.

From: o1-mini
Status: Retired
Shutdown: Oct 27, 2025
Time left: —

To: o3-mini-2025-01-31
Status: Deprecated
Shutdown: Oct 23, 2026
Time left: 8 days

o3-mini-2025-01-31 is itself deprecated, shutting down Oct 23, 2026. Its replacement is gpt-5.6-sol.

Prices

USD per 1M tokens, standard tier

Type	o1-mini	o3-mini-2025-01-31	Change
Input	Not published	$1.10first seen October 1, 2026 · source	—
Cached input	Not published	$0.55first seen October 1, 2026 · source	—
Output	Not published	$4.40first seen October 1, 2026 · source	—

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

Limits

Tokens

Limit	o1-mini	o3-mini-2025-01-31	Change
Context window	128,000 tokensin place when tracking began (October 7, 2026) · source	200,000 tokensin place when tracking began (October 7, 2026) · source	+56.3%
Max output tokens	65,536 tokensin place when tracking began (October 7, 2026) · source	100,000 tokensin place when tracking began (October 7, 2026) · source	+52.6%

Benchmarks

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

Benchmark	o1-mini	o3-mini-2025-01-31	Change
Arena TextArena, high effort (vs no setting). Ranges don't overlap. Other settings 1337 ±4 → 1348 ±4	1337 ±4	1364 ±5	+27
Arena Text: CodingArena, high effort (vs no setting). Ranges don't overlap. Other settings 1386 ±7 → 1416 ±6	1386 ±7	1434 ±12	+48
GPQA DiamondEpoch AI, high effort. Other settings 59.5% → 74.3% medium effort not run → 68.2% low effort	62.4%	77.0%	+14.6 pts
MATH Level 5Epoch AI, high effort. Other settings 84.3% → 95.2% medium effort	89.2%	96.5%	+7.3 pts
OTIS Mock AIME 2024-2025Epoch AI, high effort. Other settings 44.7% → 63.9% medium effort not run → 44.4% low effort	46.9%	76.9%	+30.0 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: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

Batch API: not supported on o1-mini, supported on o3-mini-2025-01-31.o1-mini: in place when tracking began (October 7, 2026) · source · o3-mini-2025-01-31: in place when tracking began (October 7, 2026) · source

Same on both

Reasoning / thinking: supported on both.o1-mini: in place when tracking began (October 7, 2026) · source · o3-mini-2025-01-31: in place when tracking began (October 7, 2026) · source
Fine-tuning: not supported on both.o1-mini: in place when tracking began (October 7, 2026) · source · o3-mini-2025-01-31: in place when tracking began (October 7, 2026) · source

Not published for o1-mini: Structured outputs, Function calling, Prompt caching, Image input, PDF input, Built-in web search, temperature parameter, top_p parameter, logprobs.

Not published for o3-mini-2025-01-31: Prompt caching, Image input, PDF input, Built-in web search, temperature parameter, top_p parameter, logprobs.

Aliases

All aliases

No aliases point at o1-mini.

Aliases pointing at o3-mini-2025-01-31: o3-mini (in place when tracking began (October 7, 2026) · source)

On cloud platforms

All platform dates

Model	Platform	Platform ID	Shutdown	Time left
o3-mini-2025-01-31	Microsoft Foundryversion 2025-01-31	o3-mini	Nov 19, 2026Deprecated	35 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 o1-mini to o3-mini-2025-01-31.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: o1-mini, o3-mini-2025-01-31.