Sao10K: Llama 3 8B Lunaris.
A community finetune tuned to refuse less than the instruct model it is based on. Served through MagmaRouter on one OpenAI-compatible endpoint, priced at $0.046 in and $0.057 out per million tokens.
| Model id | sao10k/l3-lunaris-8b |
|---|---|
| Tag | uncensored |
| Context | 8k tokens |
| Input price | $0.046 / million tokens |
| Output price | $0.057 / million tokens |
| Tool calling | Not supported |
What the uncensored tag actually means
sao10k/l3-lunaris-8b 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://api.magmarouter.com/v1/chat/completions \
-H "Authorization: Bearer rl-..." \
-H "Content-Type: application/json" \
-d '{
"model": "sao10k/l3-lunaris-8b",
"messages": [{"role": "user", "content": "Hello"}]
}'
Call it with the OpenAI SDK
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.magmarouter.com/v1",
api_key="rl-...",
)
resp = client.chat.completions.create(
model="sao10k/l3-lunaris-8b",
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 Sao10K: Llama 3 8B Lunaris store my prompts?
No. MagmaRouter 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?
$0.046 per million input tokens and $0.057 per million output tokens, margin already included.