What is o3 Mini API?
OpenAI o3-mini excels in reasoning tasks with advanced features like deliberative alignment and extensive context support.
Technical Specifications
- Supported inputs: Text
- Output: Text
- Context window: 200,000 tokens / Max output: —
- Endpoint: /chat/completions
Performance Benchmarks
[embed]
o3 Mini API Pricing
- Input: $1.43 / 1M tokens
- Output: $5.72 / 1M tokens
Where to Use o3 Mini
Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.
Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.
Complex reasoning
Extended reasoning improves reliability on multi-step math, logic, and technical analysis.
Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.
Code Sample
[embed]
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
The o3 Mini is documented as well suited for coding tasks, including code production and complex software design systems. It is also documented as a strong choice for STEM work, especially science, mathematics, and scientific inquiries. OpenAI also describes it as a good fit for logical problem-solving and other complex reasoning tasks. It is additionally described as useful for searching the internet and summarizing results in ChatGPT.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "openai/o3-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "openai/o3-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openai/o3-mini","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| SWE-bench Verified | 49.3% | Resolving verified real GitHub issues | Source | July 12, 2026 |
| GPQA Diamond | 79.7% | Google-proof graduate science questions (hardest subset) | Source | July 12, 2026 |
| Intelligence | 12.5 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
o3 Mini has a 200,000 tokens context window.
o3 Mini takes text as input and returns text.
Use openai/o3-mini as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
o3 Mini became available on August 7, 2025.
o3 Mini is priced at input $1.43 / 1M tokens, output $5.72 / 1M tokens, cached input $0.715 / 1M tokens.
Yes, o3 Mini can stream responses as they are generated.
o3 Mini was built by OpenAI.
No. o3 Mini only supports text input and text output.
Yes, o3 Mini supports tool calling and function calling as part of its capabilities.
Yes, o3 Mini supports structured output generation.
