← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Llama 3 8B Lunaris Pricing
Sao10K · sao10k-l3-lunaris-8b
Input / 1M tokens
$0.040
Output / 1M tokens
$0.050
Context window
8,192 tokens
Max output
16,384 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0001
1,000 requests / month$0.068/mo10,000 requests / month$0.68/mo100,000 requests / month$6.80/moEstimate your own workloadOpens the calculator with Llama 3 8B Lunaris preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Low-cost inference for high-volume simple text tasks such as classification, extraction, and short-form generation.
The business tradeoff
Limited reasoning depth and coherence on complex prompts compared with 70B+ Llama 3 variants; 8K context restricts long-document use.
Head-to-head
Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.