Magnum v4 72B
Magnum is Anthracite’s series tuned to imitate a particular prose style, with far fewer refusals than the instruct base it starts from. Served through Redline on one OpenAI-compatible endpoint, priced at $2.88 in and $5.75 out per million tokens.
| Model id | anthracite-org/magnum-v4-72b |
|---|---|
| Tag | uncensored |
| Context | 33k tokens |
| Input price | $2.88 / million tokens |
| Output price | $5.75 / million tokens |
| Tool calling | Not supported |
What the uncensored tag actually means
anthracite-org/magnum-v4-72b is tagged uncensored, which here means a loosely aligned finetune. It refuses far less than a frontier instruct model, but it is not abliterated: the refusal behaviour was reduced by training, not surgically removed, so it can still decline. Nothing about the tag promises it will answer anything.
Call it with curl
curl https://redline-gateway.pages.dev/v1/chat/completions \
-H "Authorization: Bearer rl-..." \
-H "Content-Type: application/json" \
-d '{
"model": "anthracite-org/magnum-v4-72b",
"messages": [{"role": "user", "content": "Hello"}]
}'
Call it with the OpenAI SDK
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://redline-gateway.pages.dev/v1",
api_key="rl-...",
)
resp = client.chat.completions.create(
model="anthracite-org/magnum-v4-72b",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
In Claude Code
FAQ
What does the uncensored tag mean?
Uncensored here means a loosely aligned finetune that refuses much less than a frontier model, but can still decline. It is not the same as abliterated.
Does Magnum v4 72B store my prompts?
No. Redline stores the model id, token counts and cost, not the prompt or completion, and returns a signed receipt of the prompt hash.
How much does it cost?
$2.88 per million input tokens and $5.75 per million output tokens, margin already included.