Skip to content
LLMs
Sao10K logo

Sao10K: Llama 3 8B Lunaris

by Sao10K

Sao10K: Llama 3 8B Lunaris is a large language model from Sao10K. It costs $0.040 per million input tokens and $0.050 per million output tokens. Its context window is 8K tokens.

Structured outputOpen weights
Input / 1M tokens
$0.040
Output / 1M tokens
$0.050
Cached input / 1M
-

Not supported

Context window
8K

tokens

Who serves it cheapest

3 hosts serve Llama 3 8B Lunaris. Same weights, same API - the price difference is pure margin and routing.

Providers serving Sao10K: Llama 3 8B Lunaris, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
ParasailCheapestbf16$0.040$0.0508K-99.9%
DeepInfrafp8$0.040$0.0508K-99.9%
Novitabf16$0.050$0.0508K-99.8%

The spread between Parasail and Novita is 1.2× for identical weights. Quantization and context limits differ, so check both columns before switching.

About Llama 3 8B Lunaris

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

Sao10K: Llama 3 8B Lunaris specifications
Model IDsao10k/l3-lunaris-8b
ProviderSao10K
Context window8K tokens
Max output7K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2023-12-31
Open weightsYes - Sao10K/L3-8B-Lunaris-v1
ReleasedAugust 13, 2024

Cheaper alternatives

Models that cost less than Llama 3 8B Lunaris while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Sao10K: Llama 3 8B Lunaris cost?

$0.040 per million input tokens and $0.050 per million output tokens.

What is the context window of Sao10K: Llama 3 8B Lunaris?

8K tokens, with up to 7K tokens of output per request.

Which provider serves Sao10K: Llama 3 8B Lunaris cheapest?

Parasail at $0.040 per million input tokens - 1.2× cheaper than Novita, the most expensive of the 3 hosts serving it.