Magnum v4 72B API

Magnum V4 is a powerful language model optimized for high-quality text generation tasks.

Modalities: TextText
In / Out price: $3.17/$5.29per 1M
Context window: 32K tokens
Released: Sep 9, 2025

Magnum v4 72B overview

Magnum v4 72B by Anthracite

Explore Magnum V4 72B, an advanced language model designed for generating coherent text with extensive multi-language support and high performance.

Magnum v4 72B specs

Model ID: anthracite-org/magnum-v4-72b
Developer: Anthracite
Context window: 32,000 tokens
Max output: 16,384 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Basic Information

Developer/Creator: Anthracite Organization
Release Date: October September 202420, 2024
Model Type: Large Language Model (LLM)

Overview:

Magnum V4 72B is a large language model fine-tuned on top of Qwen2.5, specifically designed to replicate the prose quality of the Claude 3 models, particularly Sonnet and Opus. It excels in generating coherent and contextually rich text, making it suitable for various applications requiring high-quality language generation.

Key Features:

72 billion parameters for advanced language understanding and generation.
Supports a context length of up to 32,768 tokens.
Instruction-tuned for improved performance on specific tasks.
Incorporates advanced tokenization techniques with a vocabulary size of 152,064.
Multi-language support covering languages such as English, French, German, Spanish, Italian, Portuguese, Russian, Chinese, and Japanese.

Intended Use:

This model is designed for applications such as content creation, automated customer support, interactive storytelling, and any scenario requiring high-quality conversational AI.

Language Support:

Magnum V4 supports multiple languages, enhancing its applicability in global contexts.

Architecture:

Magnum V4 is based on the Transformer architecture, specifically utilizing the Qwen2ForCausalLM framework. Key architectural details include:

Data Type: bfloat16 for efficient computation.

Training Data:

The model was trained on a diverse dataset that includes conversational logs and instructional data to enhance its dialogue capabilities.

Data Source and Size: The training dataset consists of various sources including chat logs and instructional texts aimed at improving the model's ability to engage in conversation effectively.
Knowledge Cutoff: The model's knowledge is current as of September 2024.
Diversity and Bias: The training data was curated to minimize bias while maximizing diversity in topics and dialogue styles. This approach enhances the model's ability to handle varied inputs effectively.

Performance Metrics:

Magnum V4 has shown competitive performance across various benchmarks:

Achieves high accuracy in generating contextually appropriate responses.
Strong performance in maintaining coherence over long dialogues.

Code Samples:

The model is available on the AI/ML API platform as "Magnum v4 72B" .

API Documentation:

Detailed API Documentation is available here.

Ethical Guidelines

Anthracite Organization emphasizes ethical considerations in AI development by promoting transparency regarding the model's capabilities and limitations. They encourage users to adhere to responsible usage guidelines to prevent misuse or harmful applications.

Licensing

Magnum V4 is licensed under a custom license allowing non-commercial usage while restricting commercial applications without permission.

Use cases

Creative Chatbots & Storytelling: Roleplay, actors, narrative generation
Conversational Agents: Multi-turn dialogs with depth
Instruction Following: Complex prompts and structured tasks
Content Generation: Blogs, marketing copy, and prose writing
Local Deployment: GGUF allows on-device use with quantized versions

Capabilities

Streaming
Structured outputs

Magnum v4 72B API pricing

Magnum v4 72B pricing in US dollars
Usage	Price	Unit
Input	$3.17	1M tokens
Output	$5.29	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Magnum v4 72B vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Magnum v4 72B	$3.17	$5.29
Claude 4.5 Haiku	$1	$5
GPT-6.1 Terra	$1	$5
Qwen3 Coder	$1.06	$5.16
ERNIE 5.0	$1.4	$5.6

How to use the Magnum v4 72B API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "anthracite-org/magnum-v4-72b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "anthracite-org/magnum-v4-72b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "anthracite-org/magnum-v4-72b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Magnum v4 72B FAQ

What is the context window of Magnum v4 72B?

Magnum v4 72B has a 32,000 tokens context window and can return up to 16,384 tokens.

What inputs and outputs does Magnum v4 72B support?

Magnum v4 72B takes text as input and returns text.

What is the model ID for Magnum v4 72B?

Use anthracite-org/magnum-v4-72b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Magnum v4 72B released?

Magnum v4 72B became available on September 9, 2025.

How much does Magnum v4 72B cost?

Magnum v4 72B costs $3.17 input and $5.29 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Magnum v4 72B support streaming?

Yes, Magnum v4 72B can stream responses as they are generated.

Who created Magnum v4 72B?

Magnum v4 72B was built by Anthracite.

Start building with Magnum v4 72B

Get API key

Magnum v4 72B API

anthracite-org/magnum-v4-72b

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "anthracite-org/magnum-v4-72b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "anthracite-org/magnum-v4-72b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "anthracite-org/magnum-v4-72b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Magnum v4 72B API

Magnum v4 72B overview

Magnum v4 72B by Anthracite

Magnum v4 72B specs

Basic Information

Overview:

Key Features:

Intended Use:

Language Support:

Architecture:

Training Data:

Performance Metrics:

Code Samples:

API Documentation:

Ethical Guidelines

Licensing

Use cases

Capabilities

Magnum v4 72B API pricing

Magnum v4 72B vs other models: token prices

How to use the Magnum v4 72B API

Build with your agent

1Get your API key

2Make your first request

Related articles

Magnum v4 72B FAQ

Start building with Magnum v4 72B

Magnum v4 72B API

Build with your agent

1Get your API key

2Make your first request

Magnum v4 72B API

Magnum v4 72B overview

Magnum v4 72B by Anthracite

Magnum v4 72B specs

Basic Information

Overview:

Key Features:

Intended Use:

Language Support:

Architecture:

Training Data:

Performance Metrics:

Code Samples:

API Documentation:

Ethical Guidelines

Licensing

Use cases

Capabilities

Magnum v4 72B API pricing

Magnum v4 72B vs other models: token prices

How to use the Magnum v4 72B API

Build with your agent

1Get your API key

2Make your first request

Models similar to Magnum v4 72B

Aion-3.0

Aion-3.5

Ember-1

Claude Sonnet 4

Claude-Sonnet-4

Claude Sonnet 4.6

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Magnum v4 72B FAQ

Start building with Magnum v4 72B