sao10k Open weights

Llama 3 8B Lunaris pricing & benchmarks

Released Aug 13, 2024 · served by 2 providers

Input / 1M tokens$0.040
Output / 1M tokens$0.050
Context window8K
Cached input
1M in + 300K out$0.06

What Llama 3 8B Lunaris is

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....

Providers and prices for Llama 3 8B Lunaris

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
DeepInfracheapest $0.040 $0.050 8K fp8 100.0%
Novita $0.050 $0.050 8K bf16 99.9%

FAQ

How much does the Llama 3 8B Lunaris API cost?

$0.040 per 1M input tokens and $0.050 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.06.

Is Llama 3 8B Lunaris free?

No. It is a paid model starting at $0.040 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Llama 3 8B Lunaris?

DeepInfra at $0.040 input / $0.050 output per 1M tokens (fp8 quantization).

Can I self-host Llama 3 8B Lunaris?

Yes — weights are published as Sao10K/L3-8B-Lunaris-v1 on Hugging Face, so you can run it on your own hardware.