Anthracite Org: Magnum v4 72B

Open-weight instruction model for adaptable chat and self-hosted production workloads

Model lab: Anthracite Org
Model family: —

Modalitiestext → text

Context window32,768

Maximum output4,096

Input · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokensUSD 1.6048 / 1M tokens

Output · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokensUSD 2.3936 / 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/anthracite/magnum-v4-72b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/anthracite/magnum-v4-72b"

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.

Magnum v4 72B API Pricing

Type	Price information
Input · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokens	USD 1.6048 / 1M tokens
Output · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokens	USD 2.3936 / 1M tokens
Cached input · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokens	USD 0.8024 / 1M tokens

Performance

Performance trends

Throughput88.4 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.8 sCurrent

Throughput

Current88.4 tok/s

Window average89.5 tok/s

Time to first token

Current1.4 s

Window average1.4 s

End-to-end latency

Current7.8 s

Window average7.4 s

Tail latency (P99)

Current16.8 s

Window average17.3 s

Prompt cache hit rate

Current19.4%

Window average24.5%

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

Magnum v4 72B Compare models

Model	Input price	Output price	Context window	Capabilities
Magnum v4 72BThis page	USD 1.6048 / 1M tokens · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokens	USD 2.3936 / 1M tokens · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokens	32,768	Text output
Beam 1.0 501B A23B	USD 0.2 / 1M tokens	USD 0.8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Ling 3.1 Flash	USD 0.06 / 1M tokens	USD 0.176 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Schematron V2 Small	USD 0.04 / 1M tokens	USD 0.184 / 1M tokens	128,000	Text output
Schematron V2 Turbo	USD 0.024 / 1M tokens	USD 0.12 / 1M tokens	128,000	Text output

Model specifications

Input: text
Output: text
Context window: 32,768
Maximum output: 4,096
Release date: 2024-10-22
Attachments: No
Reasoning: No
Tool calling: No
Structured output: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Magnum v4 72B for?

Open-weight instruction model for adaptable chat and self-hosted production workloads

What inputs and outputs does Magnum v4 72B support?

Recorded inputs: text; outputs: text.

How is Magnum v4 72B priced?

The pricing table shows the current recorded Moduck price. For example: Input · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokens USD 1.6048 / 1M tokens; Output · Context ≤ 16384 tokens · Maximum output 8192 tokens · Maximum input 16384 tokens USD 2.3936 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Magnum v4 72B?

Current model records list Context window 32,768 tokens; Maximum output 4,096 tokens.

What model parameter does the Quickstart use?

The example uses moduck/anthracite/magnum-v4-72b. 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.