Skip to content
OSMEXO

o3

openai/o3
  • OpenAI
  • Family · o3
  • Released 16 Apr 2025
  • Image · Text · File → Text
  • Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context195K
Max output100K
Input / 1M$2.00
Output / 1M$8.004× input
Scores · standing
Intelligence20.2#143/490
Usage
Tokens / day113.7M▲ 14% 7d
Usage rank#302
Requests / day25.1K
Tool calls / req0.09
Per request · 30 days
Avg input2.9K0.2× median
Avg output733about median
Cache hit43%0.6× median
Reasoning share77%1.4× median
Tool-call failures0.1%0.1× median

Consumption

83.3M166.7M250.0M3 Oct17 Oct1 Nov
Peak 216.3M 10 OctLow 45.9M 17 OctRank today #302

News & trends

News · latest from OpenAI

Benchmarks

bar = share of the top score · Benchmark data: Artificial Analysis
MATH-500#2 of 167
99.2%
MMLU-Pro#21 of 273
85.3%
AIME#7 of 160
90.3%
AIME 2025#32 of 206
88.3%
Math index#32 of 206
88.3
LiveCodeBench#24 of 269
80.8%
GPQA Diamond#119 of 445
82.7%
IFBench#51 of 328
71.4%
Speed · median across providers, latest day
Output speed#129/33478 tok/s1.2× faster than median
First token#2632.04 s2.0× longer than median
First answer token#333.39 sthinking included

#25 cheapest of 26 with a similar score

Value
Intelligence Index
1517.52022.525$1$2$5o3
Blended price per 1M tokens (log)

Technical details

Tokenizer
GPT
Knowledge cutoff
2024-06-30
Moderation
moderated
Request parameters 8
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • reasoning
  • include_reasoning
  • max_tokens
  • seed

When to use

Best for

  • Math and competitive-style reasoning
  • Coding help with deep reasoning
  • Image and chart understanding
  • Tool-calling agents on hard tasks

Think twice for

  • Latency-sensitive chat
  • High-volume simple tasks
  • Self-hosting (closed weights)

Same family

O3

Alternatives

other vendors · similar capability

Want o3 on OSMEXO?

Sign in to request it. Requests are reviewed; a request does not guarantee availability.