Skip to content
OpenKey

o3 Deep Research

OpenAIReleased Oct 10, 2025

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

Try in playground
Context window
200K tokens
Max output
100K tokens
Input
image, text, file
Output
text
Tokenizer
GPT
Released
Oct 10, 2025
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$10.00$0.300$10.30
Output$40.00$1.20$41.20
Cache read$2.50$0.075$2.58

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • presence_penalty
  • reasoning
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/o3-deep-research.

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/o3-deep-research",
    "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/o3-deep-research",
    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/o3-deep-research",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does o3 Deep Research cost via API?
Through OpenKey, o3 Deep Research costs $10.30 per 1M input tokens and $41.20 per 1M output tokens. That is the provider price ($10.00 / $40.00) plus a flat 3% fee — nothing else.
What is o3 Deep Research's context window?
o3 Deep Research accepts up to 200K tokens of context and returns up to 100K tokens per request.
Is o3 Deep Research OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/o3-deep-research" using any OpenAI SDK — only the base URL and API key change.
What inputs does o3 Deep Research support?
o3 Deep Research accepts image, text, file input and produces text output.

More from OpenAI

All OpenAI models →