This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://ask-coreai.com) and Opus(https://ask-coreai.com). The model is fine-tuned on top of [Qwen2.5 72B](https://ask-coreai.com).
With CoreAI, you can start chatting with Magnum v4 72B instantly — no separate subscription needed. CoreAI lets you chat with Magnum v4 72B alongside 300+ other AI models from Anthracite-org and other providers like OpenAI, Anthropic, Google, Meta, and more.
Among the 392 chat models on CoreAI, Magnum v4 72B ranks #367 by context window — 33K tokens, roughly 24,576 words or 49 pages of text in a single conversation. On price, it is the #181 cheapest of 183 standard-tier models by input cost. It joined the catalog on 2024-10-22.
Every model in this table is available on CoreAI — open the web app and run the same prompt through Magnum v4 72B and AionLabs: Aion-RP 1.0 (8B) side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00550 on Magnum v4 72B's raw per-token rates; a heavy session with a 50K-token document costs about $0.175. On CoreAI you don't juggle these numbers — one subscription covers Magnum v4 72B and 300+ other models under a plan usage limit, with no API keys. See plans.
Magnum v4 72B handles 33K tokens of context — roughly 24,576 words, or about 49 pages of text in one conversation.
Magnum v4 72B's underlying rates are $3 per 1M input tokens and $5 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
No — Magnum v4 72B is text-only. If you need image understanding, its standard-tier peers with vision are listed in the comparison table above.
No — Magnum v4 72B answers directly without an extended reasoning phase, which usually means faster responses.
Open the CoreAI web app or the iOS/Android app, pick Magnum v4 72B in the model selector, and chat — no API key, no per-token billing. One subscription covers Magnum v4 72B and 300+ other models.
The closest alternatives on CoreAI are AionLabs: Aion-RP 1.0 (8B), inclusionAI: Ling-2.6-flash — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with Magnum v4 72B and 300+ other AI models — all in one app.