Skip to content
OpenKey

Magnum v4 72B

AnthraciteReleased Oct 22, 2024

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).

Try in playground
Context window
33K tokens
Max output
2K tokens
Input
text
Output
text
Tokenizer
Qwen
Knowledge cutoff
Jun 30, 2024
Released
Oct 22, 2024

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$3.00$0.090$3.09
Output$5.00$0.150$5.15

Supported 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
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model anthracite-org/magnum-v4-72b.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthracite-org/magnum-v4-72b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="anthracite-org/magnum-v4-72b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "anthracite-org/magnum-v4-72b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Magnum v4 72B cost via API?
Through OpenKey, Magnum v4 72B costs $3.09 per 1M input tokens and $5.15 per 1M output tokens. That is the provider price ($3.00 / $5.00) plus a flat 3% fee — nothing else.
What is Magnum v4 72B's context window?
Magnum v4 72B accepts up to 33K tokens of context and returns up to 2K tokens per request.
Is Magnum v4 72B OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "anthracite-org/magnum-v4-72b" using any OpenAI SDK — only the base URL and API key change.
What inputs does Magnum v4 72B support?
Magnum v4 72B accepts text input and produces text output. Its knowledge cutoff is Jun 30, 2024.