o1-preview
Overview
A research preview model focused on mathematical and logical reasoning capabilities, demonstrating improved performance on tasks requiring step-by-step reasoning, mathematical problem-solving, and code generation. The model shows enhanced capabilities in formal reasoning while maintaining strong general capabilities.
o1-preview was released on September 12, 2024. API access is available through OpenAI, Azure.
Performance
Timeline
Specifications
Benchmarks
o1-preview Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Jan 17 2026Pricing
Pricing, performance, and capabilities for o1-preview across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
OpenAI | $15.00 | $60.00 | 128.0K | 32.8K | 16.2 | 66.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
 Azure | $16.50 | $66.00 | 128.0K | 32.8K | 0.54 | 16.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
Price Comparison for o1-preview
Price per 1M input tokens (USD), lower is better
llm-stats.com - Sat Jan 17 2026Throughput Comparison for o1-preview
Tokens per second, higher is better
llm-stats.com - Sat Jan 17 2026Latency Comparison for o1-preview
Time to first token (s), lower is better
llm-stats.com - Sat Jan 17 2026API Access
API Access Coming Soon
API access for o1-preview will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about o1-preview