Magnum v4 72B: AI Large Language Models

Call Magnum v4 72B through one API. 16K-token context, streaming and pay-per-token pricing. Try free in the Muapi playground. Magnum v4 72B is a 72B community fine-tune tuned for creative writing, character chat and interactive fiction (it is not abliterated) aimed at prose quality, with a 16K-token context window.

Interactive model controls

Magnum v4 72B is a 72B community fine-tune tuned for creative writing, character chat and interactive fiction (it is not abliterated) aimed at prose quality, with a 16K-token context window.

📝

Overview

About this model

Magnum v4 72B is a 72B community fine-tune tuned for creative writing, character chat and interactive fiction (it is not abliterated) aimed at prose quality, with a 16K-token context window. Muapi exposes it through a single REST endpoint with async polling and Server-Sent Events streaming, so you can drop it into chat apps, agents and workflows without hosting GPUs. It is best suited to polished prose and story writing. Pricing is pay-per-token at $4.012/M input tokens and $5.984/M output tokens, with no subscription. See also Anubis 70B v1.1, Euryale 70B v2.3, Stheno 8B v3.2, EVA Llama 3.33 70B, MythoMax 13B, Wayfarer 70B, Nevoria R1 70B. Browse the full lineup on the Llama Character Chat API page or the Character Chat LLM API hub and the Abliterated LLM API hub. Mature themes are permitted only within Muapi's acceptable-use policy, and output quality and behavior vary by prompt.

1Character chat: Give Magnum v4 72B a persona through `system_prompt` and keep long conversations in character.

2Interactive fiction: Build text adventures and collaborative stories on the [Character Chat LLM API](/character-chat-llm-api) hub.

3Story writing: Draft scenes, dialogue and world-building with a model tuned for creative prose.

💰

Pricing & Value

Cost analysis

Provider	Cost	Notes
muapiapp	$4.012/M input tokens and $5.984/M output tokens	Pay-per-token, billed on actual usage with a small minimum reserved up front.
Fal.ai	Not available	Magnum v4 72B is not offered as a hosted endpoint.
Replicate	Not available	Magnum v4 72B is not offered as a hosted endpoint.

muapiapp$4.012/M input tokens and $5.984/M output tokens

Pay-per-token, billed on actual usage with a small minimum reserved up front.

Fal.aiNot available

Magnum v4 72B is not offered as a hosted endpoint.

ReplicateNot available

Magnum v4 72B is not offered as a hosted endpoint.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Parameter	Type	Description	Default
Prompt	string	The user message or instruction for the model.	`Stay in character as a dry-witted ship's navigator and greet the new crew member.`
System Prompt	string	Optional system-level instruction to guide model behavior. Use it to define the character or setting.	`You are Mara, a dry-witted ship's navigator. Stay in character.`
Max Tokens	integer	Optional maximum number of tokens to generate.	`2048`

Promptstring

The user message or instruction for the model.

Default ValueStay in character as a dry-witted ship's navigator and greet the new crew member.

System Promptstring

Optional system-level instruction to guide model behavior. Use it to define the character or setting.

Default ValueYou are Mara, a dry-witted ship's navigator. Stay in character.

Max Tokensinteger

Optional maximum number of tokens to generate.

Default Value2048

📖

Implementation Guide

Developer documentation

How to Use Magnum v4 72B API

Get an API key: Create a key in your Muapi dashboard.
Send a prompt: POST prompt (plus optional system_prompt and max_tokens, up to 8192) to /api/v1/magnum-v4-72b.

curl -X POST https://api.muapi.ai/api/v1/magnum-v4-72b \
  -H "x-api-key: $MUAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Stay in character as a dry-witted ship's navigator and greet the new crew member."}'

Poll or stream: Poll GET /api/v1/predictions/{request_id}/result until status is completed, or stream tokens live from /api/v1/magnum-v4-72b/stream.

curl -X POST https://api.muapi.ai/api/v1/magnum-v4-72b/stream \
  -H "x-api-key: $MUAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Stay in character as a dry-witted ship's navigator and greet the new crew member."}'

Read the result: The generated text is returned in outputs. Usage is billed on actual token counts.

❓

Common Questions

Frequently asked

What is Magnum v4 72B?

Magnum v4 72B is a 72B community fine-tune tuned for creative writing, character chat and interactive fiction (it is not abliterated) aimed at prose quality, with a 16K-token context window.

What is this model tuned for?

Magnum v4 72B is a community fine-tune tuned for creative writing, character chat and interactive fiction. It is not an abliterated model.

How is Magnum v4 72B priced?

Billing is per token: $4.012/M input tokens and $5.984/M output tokens. A small minimum is reserved when the request starts and reconciled to actual usage.

Does Magnum v4 72B support streaming?

Yes. Stream tokens live from `/api/v1/magnum-v4-72b/stream` using Server-Sent Events, or poll the async endpoint.

What is the context window?

The context window is about 16K tokens. Prompt and output together must fit inside it; `max_tokens` is capped at 8192. The endpoint accepts text input only.

Are mature themes allowed?

Only within Muapi's acceptable-use policy. The model is not guaranteed to produce any particular content, and you remain responsible for complying with applicable laws.