All times Eastern (ET)Provider pages checked daily at

Migrating from o1-2024-12-17 to o3-2025-04-16

What changes when you move from o1-2024-12-17 to o3-2025-04-16: prices, limits, features and parameters, read from each company's own pages.

Status
Deprecated
Shutdown
Oct 23, 2026
Time left
8 days
Status
Deprecated
Shutdown
Dec 11, 2026
Time left
57 days

o3-2025-04-16 is itself deprecated, shutting down Dec 11, 2026. Its replacement is gpt-5.6-sol.

Prices

USD per 1M tokens, standard tier
Typeo1-2024-12-17o3-2025-04-16Change
Input$15.00first seen October 1, 2026 · sourceNot published—
Cached input$7.50first seen October 1, 2026 · sourceNot published—
Output$60.00first seen October 1, 2026 · sourceNot published—

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

Limits

Tokens
Limito1-2024-12-17o3-2025-04-16Change
Context window200,000 tokensin place when tracking began (October 7, 2026) · sourceNot published—
Max output tokens100,000 tokensin place when tracking began (October 7, 2026) · sourceNot published—

Benchmarks

Same benchmark, source and setting on both sides
Benchmarko1-2024-12-17o3-2025-04-16Change
Arena TextArena. Ranges don't overlap.1402 ±41432 ±4+30
Arena Text: CodingArena. Ranges don't overlap.1433 ±101460 ±6+27
Arena VisionArena. Ranges don't overlap.1193 ±111216 ±7+23
FrontierMath Tiers 1-3Epoch AI, high effort.
Other settings
  • 10.2% → 29.8% medium effort
  • 8.4% → 19.3% low effort
14.7%33.3%+18.6 pts
GPQA DiamondEpoch AI, high effort.
Other settings
  • 75.8% → 80.8% medium effort
  • 74.2% → 79.8% low effort
76.8%81.8%+5.0 pts
MATH Level 5Epoch AI, high effort.94.7%97.8%+3.1 pts
OTIS Mock AIME 2024-2025Epoch AI, medium effort.
Other settings
  • 73.3% → 83.9% high effort
  • 53.3% → 60.0% low effort
73.3%84.4%+11.1 pts
SimpleQA VerifiedEpoch AI, high effort.41.1%49.4%+8.3 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

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

Not published for o1-2024-12-17: Prompt caching, PDF input, Built-in web search, temperature parameter, top_p parameter, logprobs.

Not published for o3-2025-04-16: 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

o1-2024-12-17: Free for shared data, 1M tokens a day for Launch and Grow (250K for Build), in place when tracking began (October 12, 2026) (source)

o3-2025-04-16: 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

Aliases pointing at o1-2024-12-17: o1 (in place when tracking began (October 7, 2026) · source)

Aliases pointing at o3-2025-04-16: o3 (in place when tracking began (October 7, 2026) · source)

On cloud platforms

All platform dates
ModelPlatformPlatform IDShutdownTime left
o1-2024-12-17Microsoft Foundryversion 2024-12-17o1Nov 19, 2026Deprecated35 days
o3-2025-04-16Microsoft Foundryversion 2025-04-16o3Nov 19, 2026Deprecated35 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

  1. Change the model string from o1-2024-12-17 to o3-2025-04-16.
Time until shutdown
7days
11hours
04min
18sec

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

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: o1-2024-12-17, o3-2025-04-16.