Last refreshed 2026-06-29. Next refresh: weekly.
Why use L3 8B Lunaris on Novita AI?
Novita AI offers L3 8B Lunaris with pay-as-you-go pricing at $0.05/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Compare L3 8B Lunaris across 2 providers to find the best fit for your use caseInput / 1M
$0.050
Output / 1M
$0.050
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: l3-8b-lunarisModel ID
l3-8b-lunarisRequest example
Curated snippets for this provider have not been sourced yet.
Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare L3 8B Lunaris Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Novita AI | $0.05 | $0.05 |
| OpenRouter | $0.04 | $0.05 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.05 |
| Output tokens | $0.05 |
Capabilities
No model capability flags are currently sourced.
About L3 8B Lunaris
L3-8B-Lunaris is a community fine-tune of Meta Llama 3 8B by Sao10K for roleplay and creative writing. Designed as a generalist alternative to the Stheno series with improvements in multi-turn coherency and character consistency. Released June 26, 2024 on HuggingFace.
Get Started
Model Specs
Released2024-06-26
Parameters8B
Context8k
ArchitectureDecoder Only