o3 Pro
ModelActiveby OpenAI · family “o3-pro”
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently... (description from the OpenRouter listing)
in: textin: filein: imageout: textReasoningTool useStructured output
Epoch Capabilities Index
147.4 #60 of 268
90% CI 145.7 – 150.1
Released
10 Jun 2025
Context window
200K tokens
Max output
100K tokens
Input $ / 1M tokens
$20.0
Output $ / 1M tokens
$80.0
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source
Benchmark results (8)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 38.5% | 59% | high | — | External ↗ |
| DTBench | reasoning | 86.9% | 88% | high | — | External ↗ |
| ARC-AGI-2 | reasoning | 4.9% | 5% | high | — | External ↗ |
| Fiction.LiveBench | long-context | 97.2% | 100% | medium | — | External ↗ |
| Lech Mazur Writing | other | 84.4% | 98% | medium | — | External ↗ |
| WeirdML | coding | 58.2% ±0.0 | 62% | high | — | External ↗ |
| Aider polyglot | coding | 84.9% | 96% | high | — | External ↗ |
| ARC-AGI | reasoning | 59.3% | 60% | high | — | External ↗ |
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.
Events
No events recorded yet.