o3-mini
o3-miniRun o3-mini in a hosted Python Task with file inputs.
Small reasoning model optimized for science, math, and coding tasks. Offers efficient complex reasoning at lower computational cost.
This model retires on October 23, 2026. Plan a move to a newer model before then.
What o3-mini supports in qbash
- Reasoning effort3 levels, from low to high.
- Document inputReads TEXT, DOC, XLS, RTF, DOCX and 1 more files.
- Prompt cachingRepeated input is billed at the cached rate.
What is qbash?
qbash is where you build Tasks: Python programs that run a business process on managed infrastructure. Your code runs the steps and calls a model like o3-mini only at the ones that need judgment, with integrations, memory and files available in the same script.
A developer writes the Task once, and anyone on the team runs it from a form, on a schedule, from a webhook or from chat. Each Task is versioned and every run is logged.
Specifications
- Context window
- 200Ktokens
- Max output
- 100,000tokens
Use o3-mini in a Python Task
qbash.ai.raw calls o3-mini from a Task and returns its reply as a string.
notes = qbash.inputs.get("notes")
summary = qbash.ai.raw(
f"Summarize these meeting notes in five bullets:\n\n{notes}",
model="o3-mini",
system="You are a concise analyst.",
)
qbash.output({"summary": summary})
Reasoning effort with o3-mini
Set Effort to low, medium and high in the prompt's Settings. The default is medium. Higher effort spends more tokens on reasoning before the reply.
o3-mini pricing
| Input | $1.10 per 1M tokens |
|---|---|
| Output | $4.40 per 1M tokens |
| Cached input | $0.55 per 1M tokens |
| Web search | $10.00 per 1K searches |
Standard rates in USD.
Supported file formats
Documents
- TEXT
- DOC
- XLS
- RTF
- DOCX
- XLSX