modelgrep
O

OpenAI: o3

openai/o3

50th smartest of 180ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
38.4
50th of 180
Design Elo
1200
Data Viz
Speed
81
100th fastest
Latency
5.0s
first token
Input price
$2.00
245th cheapest
Context
200K
100K max out

How it compares

Smarter than72%
of all ranked models
Faster than67%
of all ranked models
Cheaper than18%
of all ranked models

Overview

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

Benchmarks

independent · via OpenRouter
Artificial Analysis69th percentile
Intelligence Index
38.4
Coding Index
38.4
Agentic Index
36.1
GPQA Diamond
83%
Humanity's Last Exam
20%
SciCode
41%
Tau²-Bench (agentic)
81%
Design Arena · Elo590 tournaments
Data Viz
1200
Game Dev
1103
Website
1081
UI Component
1074
codecategories
1072

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
OpenAI$2.00$8.00100%

Specifications

Context window200K
Max output100K
Knowledge cutoffJun 2024
Input modalitiesimage, text, file
Output modalitiestext
Prompt caching
Cache read price$0.500/M
ModeratedYes

o3 FAQ

How much does o3 cost?

o3 costs $2.00 per million input tokens and $8.00 per million output tokens via OpenRouter, making it 245th cheapest of 298 paid models.

How smart is o3?

o3 scores 38.4 on the Artificial Analysis Intelligence Index, ranking 50th of 180 benchmarked models, with a GPQA Diamond score of 83%.

How fast is o3?

o3 generates around 81 tokens per second with 5.0s time-to-first-token (p50), the 100th fastest tracked model.

What is o3's context window?

o3 supports a 200K-token context window and can output up to 100K tokens. It accepts image, text, file input.

Compare head-to-head