o3 (2025-04-16)

API ID o3-2025-04-16

o3-2025-04-16 is an OpenAI model, released April 2025.

Status: Deprecated
Released: April 2025
Shutdown: Dec 11, 2026
Replacement: GPT-5.6 Solgpt-5.6-sol

It stops serving on December 11, 2026. Recommended replacement: gpt-5.6-sol.

Free tier: Free for shared data, 1M tokens a day for Launch and Grow (250K for Build), in place when tracking began (October 12, 2026) (source) · All free models

Benchmarks

Scores as each source published them

Comparing with o1 (2024-12-17), 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

Arena	o3 (2025-04-16)	o1 (2024-12-17)	Change	Rank	Date	Source
Text By category Math 1448 rank 81 vs 1409 (+39) Creative writing 1383 rank 138 vs 1381 (+2, within range) Instruction following 1403 rank 141 vs 1407 (−4, within range) Hard prompts 1442 rank 129 vs 1418 (+24) Long prompts 1411 rank 156 vs 1412 (−1, within range) Multi-turn 1420 rank 134 vs 1386 (+34) Expert 1449 rank 121 vs 1402 (+47)	1432 ±4	1402 ±4	+30	111 of 415 58,909 votes	Oct 13, 2026	source
Text: Coding	1460 ±6	1433 ±10	+27	138 of 410 11,586 votes	Oct 13, 2026	source
Vision	1216 ±7	1193 ±11	+23	81 of 165 45,599 votes	Oct 9, 2026	source

Rated as o3-2025-04-16; o1 (2024-12-17) as o1-2024-12-17. 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

Benchmark	o3 (2025-04-16)	o1 (2024-12-17)	Change	Setting	Run	Source
FrontierMath Tiers 1-3 Other settings 29.8% vs 10.2% medium effort 19.3% vs 8.4% low effort	33.3%	14.7%	+18.6 pts	high effort	Aug 27, 2026	source
GPQA Diamond Other settings 80.8% vs 75.8% medium effort 79.8% vs 74.2% low effort	81.8%	76.8%	+5.0 pts	high effort	Apr 16, 2025	source
MATH Level 5	97.8%	94.7%	+3.1 pts	high effort	Apr 16, 2025	source
OTIS Mock AIME 2024-2025 Other settings 83.9% vs 73.3% high effort 60.0% vs 53.3% low effort	84.4%	73.3%	+11.1 pts	medium effort	Aug 7, 2026	source
SimpleQA Verified	49.4%	41.1%	+8.3 pts	high effort	Aug 27, 2026	source
SWE-bench Verified	62.3%	not run		medium effort	Feb 12, 2026	source

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

On cloud platforms

All platform dates

Platform	Platform ID	State	Shutdown	Time left	Replacement	Source
Microsoft Foundryversion 2025-04-16	o3	Deprecated	Nov 19, 2026	35 days	GPT-5.6 Solgpt-5.6-sol	source

Microsoft Foundry (version 2025-04-16) retires this model 22 days before 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 (in place when tracking began (October 7, 2026))

Price history

USD per 1M tokens, standard tier

No price history yet.

Prices

USD per 1M tokens, every type and band, by tier

No published prices.

Changelog

Changes we detected on OpenAI's pages

No changes recorded yet.

Time until shutdown

56days

11hours

25min

23sec

Counting to 7:00 pm ET on December 10, 2026, which is 00:00 UTC on December 11, 2026.

Email alerts

Get an email before o3-2025-04-16 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 Oct 15, 2026, 2:00 am ET · Sources: OpenAI deprecations, OpenAI pricing, OpenAI models