OpenAI: o3-pro

High-effort o3 tier for difficult technical reasoning and careful answers

Model lab: OpenAI
Model family: o-pro

Modalitiestext, image → text

Context window200,000

Maximum output100,000

InputUSD 16 / 1M tokens

OutputUSD 32 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/openai/o3-pro.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/openai/o3-pro"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

o3-pro API Pricing

Type	Price information
Input	USD 16 / 1M tokens
Output	USD 32 / 1M tokens

Benchmarks

Intelligence Index · v4.321.9

Coding Index—

Agentic Index—

Benchmark	Score	Measurement	Source
Aider Polyglot	84.9	percent correct · Date: 2025-06-28

Performance

Performance trends

Throughput93.0 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency6.9 sCurrent

Throughput

Current93.0 tok/s

Window average89.6 tok/s

Time to first token

Current1.4 s

Window average1.4 s

End-to-end latency

Current6.9 s

Window average7.5 s

Tail latency (P99)

Current30.9 s

Window average17.5 s

Prompt cache hit rate

Current19.0%

Window average23.0%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

o3-pro Compare models

Model	Input price	Output price	Context window	Capabilities
o3-proThis page	USD 16 / 1M tokens	USD 32 / 1M tokens	200,000	Text output · Reasoning · Tool calling
o1-pro	USD 120 / 1M tokens	USD 480 / 1M tokens	200,000	Text output · Reasoning · Tool calling
GPT-5.6 Cyber	USD 10 / 1M tokens	USD 60 / 1M tokens	400,000	Text output · Reasoning · Tool calling
GPT-5.4 mini	USD 0.6 / 1M tokens	USD 3.6 / 1M tokens	400,000	Text output · Reasoning · Tool calling
GPT-5.4 nano	USD 0.16 / 1M tokens	USD 1 / 1M tokens	400,000	Text output · Reasoning · Tool calling

Model specifications

Input: text, image
Output: text
Context window: 200,000
Maximum output: 100,000
Release date: 2025-06-10
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature setting: No
Open weights: No

Frequently asked questions

What is o3-pro for?

High-effort o3 tier for difficult technical reasoning and careful answers

What inputs and outputs does o3-pro support?

Recorded inputs: text, images; outputs: text.

How is o3-pro priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 16 / 1M tokens; Output USD 32 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for o3-pro?

Current model records list Context window 200,000 tokens; Maximum output 100,000 tokens.

What model parameter does the Quickstart use?

The example uses moduck/openai/o3-pro. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.