We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Magnum v4 72B
anthracite-org/magnum-v4-72bTry Magnum v4 72B now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Magnum v4 72B at a glance
- Input price is 456% higher than the median of 434 Text models.
- Context window of 32,768 tokens, enough for long documents and multi-turn conversations.
- Supports structured JSON output with a schema.
- A typical request (1,000 input / 500 output tokens) costs about $0.02.
About Magnum v4 72B
Magnum v4 72B is a text generation model from Anthracite Org, released on 22 October 2024. It is part of a series built to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. The model is fine-tuned on top of Qwen2.5 72B, a 72 billion parameter base, so it inherits that foundation while being tuned for a particular style of writing.
The model accepts text input and returns text output, which places it in the text category on api14. It has a context window of 32768 tokens, so prompts and conversation history together can run to that length. The maximum output per request is 4096 tokens, and the knowledge cutoff is 30 June 2024. Anything that happened after that date is outside what the model learned during training.
The capabilities shape the use cases. Because the model was tuned for prose quality rather than for tool use or multimodality, it fits writing-heavy work: drafting and rewriting long-form content, adjusting tone and register, editing for a particular voice, roleplay and character-driven dialogue, and summarisation of long documents that fit inside the context window. The 32768 token context supports passing in substantial source material, and the 4096 token output ceiling suits chapters, articles and multi-paragraph replies rather than very long single generations.
You call it through api14's OpenAI-compatible API using the model id "anthracite-org/magnum-v4-72b". The API supports a wide set of request parameters: frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_a, top_k, top_logprobs and top_p. Structured outputs and response_format are available when you need the reply to follow a schema rather than free prose, and seed helps when you want a reproducible result. The sampling controls let you tune creativity and repetition to suit the task.
Keep the limits in mind when choosing. The context window is 32768 tokens, so very large codebases, entire book-length inputs or long agent histories will not fit, and the 4096 token maximum output rules out single generations beyond that length. The knowledge cutoff of 30 June 2024 means recent events or current documentation are not known to the model. If you need image input, audio, or a much larger context, another model on api14 would fit better.
How to call the Magnum v4 72B API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "anthracite-org/magnum-v4-72b".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "anthracite-org/magnum-v4-72b",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_atop_ktop_logprobstop_pSpecifications
- Context length
- 32,768
- Max output
- 4,096
- Input
- text
- Output
- text
- Knowledge cutoff
- 2024-06-30
Requests on api14 · last 7 days
Magnum v4 72B: frequently asked questions
- How much does the Magnum v4 72B API cost?
- Magnum v4 72B costs Input $8.75 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Magnum v4 72B?
- Magnum v4 72B reads up to 32,768 tokens per request: prompt, history and documents together. It writes up to 4,096 output tokens per response.
- What can Magnum v4 72B do?
- Magnum v4 72B accepts text and returns text. It supports structured JSON output.
- How do I call Magnum v4 72B from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "anthracite-org/magnum-v4-72b". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Magnum v4 72B?
- Comparable Text models at a similar price: OpenAI: GPT-5.2 (batch), Z.ai: GLM 5.2, SpaceXAI: Grok 4.7. Each runs through the same API key, so switching is one string.
Magnum v4 72B community
New topicThis community has no topics yet. Open the first one about Magnum v4 72B.