OpenAI

o1

by OpenAItext+image+file->text1 endpoint
Neura Intelligence Index
75.2/ 100
Rank
#56
Confidence
high
Benchmarks
10(26% coverage)

Overview

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...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Deterministic seed

Modalities

Input
TextImageFile
Output
Text

Technical Specifications

Context Window
200K tokens
Max Output
100K tokens
Knowledge Cutoff
2023-10-31
Tokenizer
GPT
Content Moderation
Enabled
Uptime (24h)
10000.0%
Blended Cost
$26.25/1M tokens
Country
🇺🇸US
Model Family
o1
Release Date
December 17, 20241y
Reasoning Model
Yes

Supported Parameters

include_reasoningmax_tokensreasoningresponse_formatseedstructured_outputstool_choicetools

Benchmark Performance

general

BenchmarkScoreSource
Chatbot Arena Elo
1350
aggregated
IFEval
86.3
aggregated
MMLU-Pro
79.2
aggregated

coding

BenchmarkScoreSource
HumanEval
92.4
aggregated
SWE-bench Verified
48.9
aggregated

math

BenchmarkScoreSource
GSM8K
97.8
aggregated
MATH
96.4
aggregated
AIME 2024
83.3
aggregated

reasoning

BenchmarkScoreSource
BigBench-Hard
91.5
aggregated
GPQA Diamond
78
aggregated

Performance Over Time

Pricing

Per 1M tokens
Input$15.00
Output$60.00
Cache read$7.50
Added
December 17, 2024
Last synced 9/19/2026