o3: API Pricing, Context Window & Benchmarks
o3 is a language model from OpenAI, released in April 2025, with multimodal input.
OpenAI's most powerful reasoning model. o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following.
o3 benchmarks
Rankings
Quality Tracker
o3 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Jul 28 2026o3 pricing
Providers
o3 starts at $2.00 per million input tokens and $8.00 per million output tokens via OpenAI.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 OpenAI | $2.00 | $8.00 | 200.0K/100.0K | —/20.00 | 50/— | — | / |
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. Success is calculated from completed versus failed requests over the trailing seven days.
o3 context window
Input and output token limits for o3, plus how it ranks on long-context understanding.
o3 API
Available from the model provider
o3 has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationo3 latency
o3 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
o3 examples
Recent arena outputs from o3, picked from the highest-ranked matchups.
o3 license
o3 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 resources
Official sources for o3: api documentation, paper or system card.
o3 vs other models
The most-compared alternatives to o3 are Claude Sonnet 4.5, ERNIE 5.0, Gemini 2.5 Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like o3
Models ranked just above and below o3 by LLM Stats score.
FAQ
Common questions about o3.