OpenAI
o3legacy
Chain-of-thought reasoning model, a former math and code benchmark leader.
Intelligence
32.0 #429
Top 61% tier
Output speed
90 t/s
TTFT ~0.8s · ITL 11.1 ms/tok
Blended price (3:1)
$4.375 /1M
In $2.5/M · Out $10/M
Context
200K
≈ 500 A4 pages · max out 16384
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
o3
Claude Mythos Preview (#1)
Average (68)
Radar axes are approximated from category scores where direct benchmark measurements are missing — see Methodology.
API deployment
Compare hosts & latency
Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Groq
Cerebras
Together AI
DeepInfra
Fireworks AI
AWS Bedrock
Azure AIScores by Source
Category Scores
Benchmark Results
Model Details
Release date
Apr 15, 2025
Parameters
Not disclosed
License
Proprietary
Context Window
200,000 tokens
Input Price
$2.5/M
Output Price
$10/M
Output Speed
90 t/s
Time to First Token
—
Estimated monthly bill
Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...
Cite & embed
GitHub Markdown badge
[](https://llmpodium.com/models/o3)BibTeX
@misc{llmpodium2026o3,
title = {Benchmark Analysis and Intelligence Evaluation of o3},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/o3}
}More from OpenAI
Alternative Models
Closest alternatives to o3 based on capabilities, pricing, and benchmark scores.