Vispark: Vision Large

Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.

Model lab: Vispark
Model family: —

Modalitiestext, image, audio, video, pdf → text

Context window1,000,000

Maximum output65,536

InputUSD 5.896 / 1M tokens

OutputUSD 17.688 / 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 vispark/vision-large.

import os
import requests

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

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.

Vision Large API Pricing

Type	Price information
Input	USD 5.896 / 1M tokens
Output	USD 17.688 / 1M tokens

Performance

Performance trends

Throughput87.4 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.2 sCurrent

Throughput

Current87.4 tok/s

Window average89.6 tok/s

Time to first token

Current1.4 s

Window average1.5 s

End-to-end latency

Current7.2 s

Window average7.5 s

Tail latency (P99)

Current14.7 s

Window average16.9 s

Prompt cache hit rate

Current19.2%

Window average24.0%

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

Vision Large Compare models

Model	Input price	Output price	Context window	Capabilities
Vision LargeThis page	USD 5.896 / 1M tokens	USD 17.688 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Vision Medium	USD 3.368 / 1M tokens	USD 10.104 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Vision Small	USD 0.84 / 1M tokens	USD 2.528 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Gemini 4 Argon	USD 1.6 / 1M tokens	USD 8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Muse Wonder	USD 3.2 / 1M tokens	USD 16 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling

Model specifications

Input: text, image, audio, video, pdf
Output: text
Context window: 1,000,000
Maximum output: 65,536
Release date: 2024-05-15
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Vision Large for?

Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.

What inputs and outputs does Vision Large support?

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

How is Vision Large priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 5.896 / 1M tokens; Output USD 17.688 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Vision Large?

Current model records list Context window 1,000,000 tokens; Maximum output 65,536 tokens.

What model parameter does the Quickstart use?

The example uses vispark/vision-large. 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.