Skip to content
OpenKey

o1

OpenAIReleased Dec 17, 2024

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...

Context window
200K tokens
Max output
100K tokens
Input
text, image, file
Output
text
Tokenizer
GPT
Knowledge cutoff
Oct 31, 2023
Released
Dec 17, 2024
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$15.00$0.450$15.45
Output$60.00$1.80$61.80
Cache read$7.50$0.225$7.73

Benchmarks

Artificial Analysis

Intelligence index
Coding index
39.7
Agentic index

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • response_format
  • seed
  • structured_outputs
  • tool_choice
  • tools

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/o1.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/o1",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="openai/o1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/o1",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does o1 cost via API?
Through OpenKey, o1 costs $15.45 per 1M input tokens and $61.80 per 1M output tokens. That is the provider price ($15.00 / $60.00) plus a flat 3% fee — nothing else.
What is o1's context window?
o1 accepts up to 200K tokens of context and returns up to 100K tokens per request.
Is o1 OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/o1" using any OpenAI SDK — only the base URL and API key change.
What inputs does o1 support?
o1 accepts text, image, file input and produces text output. Its knowledge cutoff is Oct 31, 2023.

More from OpenAI

All OpenAI models →