o3-pro: API Pricing, Context Window & Benchmarks
o3-pro is a language model from OpenAI, released in June 2025, with multimodal input.
Version of o3 with more compute for better responses. The o3-pro model uses more compute to think harder and provide consistently better answers. Designed to tackle tough problems with advanced reasoning capabilities.
o3-pro pricing
Providers
o3-pro starts at $20.00 per million input tokens and $80.00 per million output tokens via OpenAI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 OpenAI | $20.00 | — | $80.00 | 200.0K/100.0K | 30.00 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
o3-pro context window
Input and output token limits for o3-pro, plus how it ranks on long-context understanding.
o3-pro API
Available from the model provider
o3-pro has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationo3-pro latency
o3-pro time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
o3-pro examples
Recent arena outputs from o3-pro, picked from the highest-ranked matchups.
o3-pro license
o3-pro is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of May 2024.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- May 2024
Proprietary license - usage restrictions apply
o3-pro resources
Official sources for o3-pro: api documentation.
FAQ
Common questions about o3-pro.