When was o1-preview released?

o1-preview was released on September 12, 2024 by OpenAI. This is the official o1-preview release date tracked on LLM Stats.

Is o1-preview available via API?

Yes, o1-preview is available via API. See the official documentation for authentication and endpoint details. It is served by 2 providers tracked on LLM Stats.

Who created o1-preview?

o1-preview was created by OpenAI.

What is the license for o1-preview?

o1-preview is released under the Proprietary license.

What is o1-preview latency?

o1-preview p95 time to first token is 0.54 seconds via Azure over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use o1-preview?

o1-preview is available through 2 providers including OpenAI, Azure.

Where is the o1-preview paper or technical report?

o1-preview has a paper or technical report available at https://cdn.openai.com/o1-system-card-20240917.pdf. Use that source for architecture, training, release and evaluation details.

What models should I compare o1-preview against?

Common o1-preview comparisons include o1-preview vs MiMo-V2.5-Pro, o1-preview vs DeepSeek R1 Zero, o1-preview vs Gemini 1.5 Pro. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.

o1-preview API Pricing, Context Window & Benchmarks

Name: o1-preview
Author: OpenAI

o1-preview: API Pricing, Context Window & Benchmarks

o1-preview is a language model from OpenAI, released in September 2024.

A research preview model focused on mathematical and logical reasoning capabilities, demonstrating improved performance on tasks requiring step-by-step reasoning, mathematical problem-solving, and code generation. The model shows enhanced

Input

Text

Output

Text

o1-preview benchmarks

Rankings

Quality Tracker

o1-preview Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Thu Jul 30 2026

Notice missing or incorrect data?

o1-preview pricing

Providers

o1-preview starts at $15.00 per million input tokens and $60.00 per million output tokens via OpenAI. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.

Provider	Input $/M	Output $/M	Context in / out	TTFT p50 / p95 s	Output avg / p5 c/s	Success 7d	Modalities in / out
OpenAI	$15.00	$60.00	128.0K/32.8K	—/16.20	66/—	—	/
Azure	$16.50	$66.00	128.0K/32.8K	—/0.54	16/—	—	/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.

Loading chart...

o1-preview context window

Input and output token limits for o1-preview, plus how it ranks on long-context understanding.

InputOutput

128Ktokens

33Ktokens

≈ 192 pages of text

128K

8K128K1M

o1-preview API

Available from the model provider

o1-preview has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

o1-preview latency

o1-preview time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

o1-preview examples

Recent arena outputs from o1-preview, picked from the highest-ranked matchups.

o1-preview license

o1-preview is a proprietary model available under its provider's product and API terms.

License: Proprietary; Hosted access

Proprietary license - usage restrictions apply

o1-preview resources

Official sources for o1-preview: api documentation, paper or system card, official launch post, source repository.

o1-preview vs other models

The most-compared alternatives to o1-preview are MiMo-V2.5-Pro, DeepSeek R1 Zero, Gemini 1.5 Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.