Question 1

What is Llama 3 8B Lunaris?

Accepted Answer

Llama 3 8B Lunaris is a model from Meta, released on Jun 26, 2024. 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. For best results, use with Llama 3 Instruct context template, temperature 1.4, and min_p 0.1.

Question 2

How much does Llama 3 8B Lunaris cost?

Accepted Answer

On the Respan gateway, input starts at $0.04 per 1M tokens on OpenRouter and DeepInfra, and output starts at $0.05 per 1M tokens on Novita, after gateway discounts. Averaged across 3 providers, it costs $0.04 per 1M input tokens and $0.05 per 1M output tokens.

Question 3

Which providers serve Llama 3 8B Lunaris on Respan?

Accepted Answer

3 providers serve Llama 3 8B Lunaris: OpenRouter, DeepInfra, and Novita.

Question 4

What is Llama 3 8B Lunaris's context window?

Accepted Answer

Llama 3 8B Lunaris accepts up to 8K tokens of context on its largest provider route.

Question 5

How do I use Llama 3 8B Lunaris with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "llama-3-8b-lunaris". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Llama 3 8B Lunaris?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 62 tokens per second, and the lowest response latency was 0.5 seconds on OpenRouter. Speed varies with request size and provider.

Provider	Context	Input	Output	Capabilities
OpenRouter`openrouter/sao10k/l3-lunaris-8b`	8K	$0.04/M	$0.05/M
DeepInfra`deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo`	8K	$0.04/M	$0.05/M
NovitaSave 10%`novita/sao10k/l3-8b-lunaris`	8K	$0.05/M	$0.05/M	—

Llama 3 8B Lunaris

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps