Magnum v4 72B

This is a series of models designed 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.

ChatAnthracite Org33k tokens$3.2702 / $5.4503 · 1M

anthracite-org/magnum-v4-72b

Context
33k tokens
Completion cap
4,096
Tools
No
JSON
Yes
Released
2024-10-22

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthracite-org/magnum-v4-72b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Magnum v4 72B?
This is a series of models designed 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. Magnum v4 72B runs on the Geek Hub API (OpenAI-compatible). Model id: anthracite-org/magnum-v4-72b.
Is Magnum v4 72B free?
No. Input is $3.2702 per 1M tokens and output is $5.4503 per 1M tokens on Geek Hub (markup included).
What is the context length of Magnum v4 72B?
Magnum v4 72B has a 33k tokens context window. It supports up to 4,096 completion tokens.
Does Magnum v4 72B support tool calling and structured outputs?
Magnum v4 72B does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was Magnum v4 72B released?
Magnum v4 72B was released on 2024-10-22.