OpenAI: o3

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

Model lab: OpenAI
Model family: o

Modalitiestext, image, pdf → text

Context window200,000

Maximum output100,000

InputUSD 1.6 / 1M tokens

OutputUSD 6.4 / 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 openai/o3.

import os
import requests

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

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 API Pricing

Type	Price information
Input	USD 1.6 / 1M tokens
Output	USD 6.4 / 1M tokens

Benchmarks

Intelligence Index · v4.320.2

Coding Index—

Agentic Index—

Benchmark	Score	Measurement	Source
Aider Polyglot	81.3	percent correct · Date: 2025-06-25

Performance

Output speed131.73 tokens/s

Time to first token5.71 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput131.73 tok/sCurrent

Time to first token5.71 sCurrent

End-to-end latency8.0 sCurrent

Throughput

Current131.73 tok/s

Window average132.6 tok/s

Time to first token

Current5.71 s

Window average5.4 s

End-to-end latency

Current8.0 s

Window average7.4 s

Tail latency (P99)

Current13.9 s

Window average16.1 s

Prompt cache hit rate

Current31.1%

Window average22.5%

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 Compare models

Model	Input price	Output price	Context window	Capabilities
o3This page	USD 1.6 / 1M tokens	USD 6.4 / 1M tokens	200,000	Text output · Reasoning · Tool calling
o1	USD 12 / 1M tokens	USD 48 / 1M tokens	200,000	Text output · Reasoning · Tool calling
GPT-6.1 Sol	USD 1.6 / 1M tokens	USD 8 / 1M tokens	1,050,000	Text output · Reasoning · Tool calling
GPT-6 Luna	USD 0.08 / 1M tokens	USD 0.4 / 1M tokens	1,050,000	Text output · Reasoning · Tool calling
GPT-6 Sol	USD 1.6 / 1M tokens	USD 8 / 1M tokens	1,050,000	Text output · Reasoning · Tool calling

Model specifications

Input: text, image, pdf
Output: text
Context window: 200,000
Maximum output: 100,000
Release date: 2025-04-16
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature setting: No
Open weights: No

Frequently asked questions

What is o3 for?

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

What inputs and outputs does o3 support?

Recorded inputs: text, images, PDF; outputs: text.

How is o3 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 1.6 / 1M tokens; Output USD 6.4 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for o3?

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

What model parameter does the Quickstart use?

The example uses openai/o3. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

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.