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

o1 mini

API ID o1-mini

o1-mini was an OpenAI model. It had a 128,000-token context window and up to 65,536 output tokens. It supported reasoning.

Status
Retired
Released
—
Shutdown
Oct 27, 2025

o1-mini stopped serving on October 27, 2025. Recommended replacement: o4-mini-2025-04-16.

How to migrate to o4 mini (2025-04-16)

Benchmarks

Scores as each source published them
or

No comparison. Pick a model to see the difference on each benchmark.

Arena

Arenao1 miniRankDateSource
Text
By category
  • Math 1362 rank 206
  • Creative writing 1281 rank 262
  • Instruction following 1331 rank 223
  • Hard prompts 1360 rank 226
  • Long prompts 1344 rank 226
  • Multi-turn 1323 rank 244
  • Expert 1351 rank 221
1337 ±4236 of 415
51,981 votes		Oct 13, 2026source
Text: Coding1386 ±7228 of 410
8,478 votes		Oct 13, 2026source

Rated as o1-mini. 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

Benchmarko1 miniSettingRunSource
GPQA Diamond
Other settings
  • 59.5% medium effort
62.4%high effortFeb 13, 2025source
MATH Level 5
Other settings
  • 84.3% medium effort
89.2%high effortFeb 13, 2025source
OTIS Mock AIME 2024-2025
Other settings
  • 44.7% medium effort
46.9%high effortMar 6, 2025source

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

Alias

All aliases

Currently points to o1-mini-2024-09-12 (in place when tracking began (October 7, 2026)).

Features

Compare models
FeatureValueSinceSource
Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests.Not 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.128,000 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.65,536 tokensin place when tracking began (October 7, 2026)source

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

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.

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