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

o1 Preview

API ID o1-preview

o1-preview was a preview OpenAI model. It had a 128,000-token context window and up to 32,768 output tokens. It supported function calling, structured outputs and reasoning.

Status
Retired
Released
—
Shutdown
Jul 28, 2025
Replacement
o3

o1-preview stopped serving on July 28, 2025. Recommended replacement: o3.

How to migrate to o3

Benchmarks

Scores as each source published them
or

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

Arena

Arenao1 PreviewRankDateSource
Text
By category
  • Math 1386 rank 182
  • Creative writing 1366 rank 160
  • Instruction following 1381 rank 174
  • Hard prompts 1396 rank 190
  • Long prompts 1382 rank 188
  • Multi-turn 1390 rank 179
  • Expert 1383 rank 197
1389 ±5177 of 415
31,122 votes		Oct 13, 2026source
Text: Coding1415 ±9198 of 410
5,123 votes		Oct 13, 2026source

Rated as o1-preview. 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 PreviewSettingRunSource
GPQA Diamond50.3%Jan 27, 2025source
MATH Level 581.6%Jan 27, 2025source
OTIS Mock AIME 2024-202531.1%Mar 7, 2025source

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

Alias

All aliases

Currently points to o1-preview-2024-09-12 (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.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.32,768 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

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