What is o1 Preview API?
New AI model from OpenAI for complex reasoning in science, coding, and mathematics.
Technical Specifications
- Supported inputs: Image, Text
- Output: Text
- Context window: 128,000 tokens / Max output: —
- Endpoint: /chat/completions
Performance Benchmarks
[embed]
o1 Preview API Pricing
- Input: $19.5 / 1M tokens
- Output: $78 / 1M tokens
Where to Use o1 Preview
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.
o1 is documented as suitable for building agentic applications that streamline customer support. It is also described as useful for optimizing supply chain decisions and forecasting complex financial trends.
OpenAI also says o1 is useful for complex problems in science, coding, math, and similar fields. Examples given include annotating cell sequencing data, generating complicated mathematical formulas for quantum optics, and building and executing multi-step workflows.
The model is further described as well-suited for reasoning-heavy work such as complex scientific research tasks. Its examples include healthcare research and physics-oriented computation where visual inputs or structured reasoning matter.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "openai/o1", "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/o1", "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/o1","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 | 48.9% | Resolving verified real GitHub issues | Source | July 12, 2026 |
| GPQA Diamond | 78% | Google-proof graduate science questions (hardest subset) | Source | July 12, 2026 |
| AIME 2025 | 79.2% | Competition mathematics (AIME), 2025 | Source | July 12, 2026 |
| Intelligence | 11.4 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 34 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Math | 79.7 | Composite score across standardised mathematics evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
o1 Preview This page | Reasoning + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
o1 Preview has a 128,000 tokens context window.
o1 Preview takes image, text as input and returns text.
Use openai/o1 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
o1 Preview became available on August 7, 2025.
o1 Preview is priced at input $19.5 / 1M tokens, output $78 / 1M tokens, cached input $9.75 / 1M tokens.
Yes, o1 Preview can stream responses as they are generated.
Yes, o1 Preview accepts image input alongside text.
o1 Preview was built by OpenAI.
It is a chat model from OpenAI built for complex reasoning in science, coding, and mathematics.
It is designed for tasks involving complex reasoning, such as scientific analysis, coding, and mathematics.
Yes, it supports tools and function calling along with structured outputs.
