AI model
sao10k/l3-lunaris-8b:free
Sao10K: Llama 3 8B Lunaris (Free) is a 8,192-token model free on Composite. Ranked #130 of 179 models by traffic on Composite over the last 30 days, taking 0% of tokens and 0.02% of requests. Measured on Composite, 100.0% of its last 5 requests on Composite succeeded, the typical first token arrives in 964 ms, output runs at about 271.9 tokens per second.
Try in Playground| Model ID | sao10k/l3-lunaris-8b:free |
|---|---|
| Provider | cv11 |
| Context window | 8,192 tokens |
| Accepts | text |
| Returns | text |
| Input price | Included in free allowance |
| Output price | Included in free allowance |
| Prompt caching | Not offered for this model |
| Moderated | No |
| Cost on a monthly plan | Free - does not spend plan credits |
| Routing endpoints | 1 |
Make a Composite API key and type sao10k/l3-lunaris-8b:free as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1.
Sao10K: Llama 3 8B Lunaris (Free) guide · JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#130 of 179
0% of tokens and 0.02% of requests over 30 days.
100.0%
Across the last 5 requests Composite served for this model.
964 ms
Median across the same sample.
271.9 tok/s
Median generation rate after the first token.
Free - 80 requests/day shared across free models; each call counts as 6
Credits pay the provider’s price plus 25%; cache hits cost less.
Monthly plans serve this model without spending any of their included credits.
cv11
This model is available on Composite alongside dozens of others from other labs, so it is easy to compare against similar options.
At 8,192 tokens, its context window is on the smaller side. It is a better fit for focused scenes or one-off chats than for a long-running campaign with heavy lore.
It is free on Composite, which makes it a reasonable place to test a character card, preset or lorebook before connecting your own provider.
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....
Supplied by cv11, not written by Composite.
Composite Anthropic Router · Composite Gemini Router · Composite GPT Router