Skip to content
OmniRail
← All models

Sao10K · Language model

Llama 3 8B Lunaris

sao10k/l3-lunaris-8b
  • Language
  • Uncensored · fewer refusals
Released Aug 13, 2024

In the Uncensored models category. A small Llama 3 8B merge for fiction and general chat; the cheapest of the list (8K context). An ordinary chat model: same endpoint, key and MCP tool as any other. These models refuse less often, but our usage policy still applies to every call: nothing illegal, nothing sexual involving minors, no harassment or threats against real people, no malware or weapons meant to hurt anyone. How it works · Usage policy

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....

Specifications

Context window
8,192 tokens
Max output
7,372 tokens
Input
text
Output
text
Tokenizer
Llama3
Knowledge cutoff
2023-12-31

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • top_k
  • top_logprobs
  • top_p

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"sao10k/l3-lunaris-8b","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'