o3
o3 is a large language model made by OpenAI, added to the catalog on 16 Apr 2025. It has a context window of 200,000 tokens and costs $2.00 per 1M input tokens and $8.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: solve complex math problems, analyze scientific data and develop and debug code.
Price checked · source: OpenRouter
What o3 is
The OpenAI: o3 model, released in April 2025, offers a robust solution for tasks involving text and image inputs, with text outputs. With a context window of 200,000 tokens, it excels in math, science, coding, and visual reasoning, making it ideal for technical writing and instruction-following. The model is designed to handle multi-step problems by analyzing text, code, and images, providing comprehensive solutions. Its versatility in handling various input modalities and producing structured text outputs makes it a valuable tool for complex problem-solving.
Key features
- Handles text and image inputs
- Text output with structured options
- 200,000 token context window
- Excels in math, science, coding
- Strong visual reasoning skills
- Supports technical writing tasks
Typical uses
- Solve complex math problems
- Analyze scientific data
- Develop and debug code
- Create detailed technical documents
- Follow multi-step instructions
o3 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $2.00 | $1.00 |
| Output, per 1M tokens | $8.00 | $4.00 |
| Cached input read, per 1M tokens | $0.50 | $0.25 |
| Web search, per search | $0.01 | $0.01 |
| Variant | Model id |
|---|---|
| Batch | openai/o3:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 16 Apr 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0034 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.056 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.076 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.312 |
o3 specifications
| Model id | openai/o3 |
|---|---|
| Version | o3-2025-04-16 |
| Context window | 200,000 tokensAbout 150,000 English words |
| Max output | 100,000 tokens |
| Knowledge cutoff | 2024-06-30 |
| Added to catalog | 16 Apr 2025 |
| Input types | image, text, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
Artificial intelligence promises to recast work, leisure and creativity in complementary, exhilarating ways. Routine drudgery—budget reconciliation, compliance audits, help-desk triage—will be delegated to tireless learning systems, shrinking the workweek and freeing humans for higher-order judgment and empathy. Instead of obsessing over tasks, employees will orchestrate flows of insight generated by algorithms, becoming strategic curators rather than overwhelmed executors. The slack reclaimed from the calendar migrates to leisure. Personalized generative companions can design fitness plans, immersive language journeys or dynamic travel itineraries matched to mood and budget, turning free time into rich, continuous self-development. Social platforms enhanced by real-time translation and sentiment analysis dissolve linguistic and cultural barriers, widening our circles of play. Creativity, finally, is catalyzed. Artists converse with models that remix centuries of styles, scientists simulate hypotheses in silico before lifting a pipette, and children prototype games with spoken prompts. AI doesn’t replace imagination; it multiplies its surface area.
Draw with code
RUN20 Nov 2026Generate an SVG of a pelican riding a bicycle.
Compare o3
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.