OpenAI: Whisper 3 Large

Open Whisper checkpoint for robust multilingual transcription and captioning

Model lab: OpenAI
Model family: whisper

Modalitiesaudio → text

Context window448

Maximum output4,096

InputUSD 0.00184 / 1M tokens

OutputUSD 0.00184 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to openai/whisper-large-v3.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "openai/whisper-large-v3"

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.

Whisper 3 Large API Pricing

Type	Price information
Input	USD 0.00184 / 1M tokens
Output	USD 0.00184 / 1M tokens
Audio output	USD 1.84 / 1M tokens

Performance

Performance trends

Throughput86.8 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency8.1 sCurrent

Throughput

Current86.8 tok/s

Window average89.4 tok/s

Time to first token

Current1.4 s

Window average1.4 s

End-to-end latency

Current8.1 s

Window average7.5 s

Tail latency (P99)

Current16.1 s

Window average16.5 s

Prompt cache hit rate

Current18.4%

Window average24.5%

Error rate

Current2.1%

Window average0.2%

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

Whisper 3 Large Compare models

Model	Input price	Output price	Context window	Capabilities
Whisper 3 LargeThis page	USD 0.00184 / 1M tokens	USD 0.00184 / 1M tokens	448	Text output
GPT Realtime Whisper	USD 0.0002272 / second · Billed by input audio duration	Not billed on output	16,000	Text output
Whisper Large v3 Turbo	USD 0.00184 / 1M tokens	USD 0.00184 / 1M tokens	448	Text output
Gemini 3.5 Transcribe Live	USD 0.00012 / second · Billed by input audio duration	Not billed on output	—	Text output
Grok Voice STT 1.0	Price currently unavailable	Price currently unavailable	15,000	Text output

Model specifications

Input: audio
Output: text
Context window: 448
Maximum output: 4,096
Release date: 2024-10-01
Attachments: No
Reasoning: No
Tool calling: No
Open weights: Yes

Frequently asked questions

What is Whisper 3 Large for?

Open Whisper checkpoint for robust multilingual transcription and captioning

What inputs and outputs does Whisper 3 Large support?

Recorded inputs: audio; outputs: text.

How is Whisper 3 Large priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.00184 / 1M tokens; Output USD 0.00184 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Whisper 3 Large?

Current model records list Context window 448 tokens; Maximum output 4,096 tokens.

What model parameter does the Quickstart use?

The example uses openai/whisper-large-v3. 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.