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

o3 mini (2025-01-31)

API ID o3-mini-2025-01-31

o3-mini-2025-01-31 is an OpenAI model, released January 2025. It has a 200,000-token context window and up to 100,000 output tokens. It supports function calling, structured outputs and reasoning. Standard price: from $1.10 input and from $4.40 output per 1M tokens.

Status
Deprecated
Released
January 2025
Shutdown
Oct 23, 2026

It stops serving on October 23, 2026. Recommended replacement: gpt-5.6-sol.

How to migrate to GPT-5.6 Sol

Benchmarks

Scores as each source published them
or

Comparing with o1 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

Arenao3 mini (2025-01-31)o1 miniChangeRankDateSource
Text
Other settings
  • 1348 ±4 vs 1337 ±4
By category
  • Math 1405 rank 153 vs 1362 (+43) at high effort (vs no setting)
  • Creative writing 1312 rank 219 vs 1281 (+31) at high effort (vs no setting)
  • Instruction following 1366 rank 190 vs 1331 (+35) at high effort (vs no setting)
  • Hard prompts 1401 rank 185 vs 1360 (+41) at high effort (vs no setting)
  • Long prompts 1373 rank 198 vs 1344 (+29) at high effort (vs no setting)
  • Multi-turn 1345 rank 215 vs 1323 (+22) at high effort (vs no setting)
  • Expert 1398 rank 181 vs 1351 (+47) at high effort (vs no setting)
1364 ±51337 ±4+27204 of 415
18,589 votes		Oct 13, 2026source
Text: Coding
Other settings
  • 1416 ±6 vs 1386 ±7
1434 ±121386 ±7+48176 of 410
2,596 votes		Oct 13, 2026source

Rated as o3-mini-high (high effort); o1 mini as o1-mini. Some were rated at different settings; ratings on one arena share one scale, so the difference still reads directly. Ratings come from people voting between two anonymous answers; Text is style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Epoch AI

Benchmarko3 mini (2025-01-31)o1 miniChangeSettingRunSource
FrontierMath Tier 40.0%not runhigh effortJun 11, 2026source
FrontierMath Tiers 1-3
Other settings
  • 10.5% vs not run medium effort
  • 3.9% vs not run low effort
18.6%not runhigh effortJun 11, 2026source
GPQA Diamond
Other settings
  • 74.3% vs 59.5% medium effort
  • 68.2% vs not run low effort
77.0%62.4%+14.6 ptshigh effortFeb 13, 2025source
MATH Level 5
Other settings
  • 95.2% vs 84.3% medium effort
96.5%89.2%+7.3 ptshigh effortFeb 13, 2025source
OTIS Mock AIME 2024-2025
Other settings
  • 63.9% vs 44.7% medium effort
  • 44.4% vs not run low effort
76.9%46.9%+30.0 ptshigh effortFeb 27, 2025source
SimpleQA Verified15.3%not runhigh effortAug 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 2025-01-31o3-miniDeprecatedNov 19, 202635 daysGPT-5.6 Terragpt-5.6-terrasource

Microsoft Foundry (version 2025-01-31) retires this model 27 days after OpenAI's own API.

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.

Aliases pointing here: o3-mini (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 7, 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 7, 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 7, 2026)source
Reasoning / thinkingThe model can work through a problem step by step before it answers: usually better answers to hard questions, at the cost of more tokens and time.Supportedin place when tracking began (October 7, 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.Not supportedin place when tracking began (October 7, 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.200,000 tokensin place when tracking began (October 7, 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.100,000 tokensin place when tracking began (October 7, 2026)source

Not published by OpenAI: Prompt caching, Image input, PDF input, Built-in web search, temperature parameter, top_p parameter, logprobs.

Price history

USD per 1M tokens, standard tier
$0.00$1.00$2.00$3.00$4.00$5.00Oct 2026In $1.10Out $4.40Oct 1, 2026 to Oct 15, 2026: Input $1.10, Output $4.40
$0.00$1.00$2.00$3.00$4.00$5.00Oct 2026In $1.10Out $4.40Oct 1, 2026 to Oct 15, 2026: Input $1.10, Output $4.40

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$1.10
Oct 1, 2026Output$4.40

Prices

USD per 1M tokens, every type and band, by tier
TypeBandPrice $/1MIn effect
Standard
inputshort context$1.10
cached inputshort context$0.55
outputshort context$4.40
Batch
inputshort context$0.55
outputshort context$2.20

Changelog

Changes we detected on OpenAI's pages

No changes recorded yet.

Time until shutdown
7days
11hours
25min
22sec

Counting to 8:00 pm ET on October 22, 2026, which is 00:00 UTC on October 23, 2026.

Email alerts

Get an email before o3-mini-2025-01-31 shuts down

We'll email you 30, 7 and 1 days before it shuts down, and the same morning if the shutdown date moves or the price changes.

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

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