o1

ModelActive

by OpenAI · family “o”

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason... (description from the OpenRouter listing)

in: textin: imagein: fileout: textReasoningTool useStructured output

Epoch Capabilities Index

141.9 #100 of 268

90% CI 139.5 – 143.3

Listing ↗

Released

17 Dec 2024

Context window

200K tokens

Max output

100K tokens

Input $ / 1M tokens

$15.0

Output $ / 1M tokens

$60.0

Cached input $ / 1M

$7.50

Each benchmark shown separately with its own source

Benchmark results (12)

All benchmarks

Benchmark	Domain	Score	vs best recorded	Setting	Run	Source
LMCA	agents	22.3%	34%	high	—	External ↗
DTBench	reasoning	74.7%	76%	high	—	External ↗
FrontierMath-Tiers-1-3-v2-Private	math	14.7% ±2.1	16%	high	28 Aug 2026	Eval log ↗
Chess Puzzles	games	15.0% ±3.6	21%	high	7 Aug 2026	Eval log ↗
SimpleQA Verified	knowledge	41.1% ±1.6	54%	high	31 Aug 2026	Eval log ↗
FrontierMath-2025-02-28-Privatesuperseded	math	9.3% ±1.7	18%	high	7 Mar 2025	Epoch ↗
WeirdML	coding	46.1% ±0.0	49%	high	—	External ↗
Aider polyglot	coding	61.7%	70%	high	—	External ↗
OTIS Mock AIME 2024-2025	math	73.3% ±6.7	73%	high	15 Jul 2026	Eval log ↗
SimpleBench	reasoning	40.1%	49%	high	—	External ↗
GPQA diamond	science	76.8% ±3.0	80%	high	13 Feb 2025	Eval log ↗
MATH level 5	math	94.7% ±0.6	97%	high	13 Feb 2025	Epoch ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

13 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.