Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for sao10k

Sao10K: Llama 3 8B Lunaris

sao10k/l3-lunaris-8b

Model weights
Compare

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.

Created by Sao10kOpens in new tab, this model aims to offer an improved experience over Stheno v3.2, with enhanced creativity and logical reasoning.

For best results, use with Llama 3 Instruct context template, temperature 1.4, and min_p 0.1.

Modalities
In / Out Price
$0.04 / $0.05per 1M
Context
8K
Released
Aug 13, 2024
Knowledge Cutoff
Dec 2023
Compare
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), Floor (cheapest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking
$0.04$0.050.51s43 tps
99.83%
$0.04$0.050.16s94 tps
100.00%
$0.05$0.050.40s66 tps
100.00%
Throughput
94tok/s

P50, best across providers

Latency
0.16s

P50, best provider

AutoExacto benchmarks
GPQA DiamondDeepInfra (Turbo)28.6%Parasail28.0%auto-routing27.6%NovitaAI26.4%
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.82%

Availability over the last 3 days

Last 72 hours
Availability 99.82%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.81%
Without Routing
93.73%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://www.hammerai.com/
HammerAI
Chat with AI characters for free
10Btokens
2.
Favicon for https://www.coffeecatai.com/
CoffeeCat AI Image Generator
AI tools for writing, images, and video.
2.08Btokens
3.
Favicon for https://halluna.ai/
Halluna
new
1.23Btokens
4.
Favicon for https://hornyt-pages.pages.dev/
Hornyt
new
856Mtokens
5.
Favicon for https://www.layla-network.ai/
Layla
Private, personal AI
682Mtokens

Frequently asked questions

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. Created by Sao10k, this model aims to offer an improved experience over Stheno v3.2, with enhanced creativity and logical reasoning.

Llama 3 8B Lunaris costs $0.04/M input tokens and $0.05/M output tokens.

Llama 3 8B Lunaris has a 8,192 token context window. It supports up to 8,192 completion tokens.

No. Llama 3 8B Lunaris does not accept tools, so function calling is unavailable. It also supports structured outputs via a JSON schema in response_format.

Llama 3 8B Lunaris is served by 3 providers on OpenRouter: Parasail, DeepInfra (Turbo), and NovitaAI. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Llama 3 8B Lunaris was released on August 13, 2024. Its knowledge cutoff is December 31, 2023.

More models from Sao10K

Llama 3.1 70B Hanami x1

This is Sao10K's experiment over Euryale v2.2.

Text16K context
Llama 3.3 Euryale 70B

Euryale L3.3 70B is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.2.

Text131K context$0.65 / $0.75
Llama 3.1 Euryale 70B v2.2

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.

Text131K context$0.85 / $0.85
Llama 3 Stheno 8B v3.3 32K

Stheno 8B 32K is a creative writing/roleplay model from Sao10k. It was trained at 8K context, then expanded to 32K context.

Compared to older Stheno version, this model is trained on:

Text32K context
Llama 3 Euryale 70B v2.1

Euryale 70B v2.1 is a model focused on creative roleplay from Sao10k.

Text8K context
Fimbulvetr 11B v2

Creative writing model, routed with permission. It's fast, it keeps the conversation going, and it stays in character.

If you submit a raw prompt, you can use Alpaca or Vicuna formats.

Text8K context