Sovereign inference — Llama 3.1 8b
Your sovereign, private Llama 3.1 8b
Llama 3.1 8B is Meta's compact multilingual instruct model with a 128K context window — a fast, low-cost workhorse for classification, summarization and light tool use. A standard model in the small tier, served on ToothFairyAI's AU, EU and US endpoints — private by default, billed in US dollars per million tokens at the published rates below. No training on your data, no vendor lock-in.
AU · EU · US resident$0.17/1M input$0.51/1M output131K context
How Llama 3.1 8b compares
Independent intelligence index for Llama 3.1 8b against every peer in the Small tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Run Llama 3.1 8b privately
One key, one endpoint, three jurisdictions.
- Size tierSmall
- Serving routeStandard
- Input rate$0.17/1M
- Output rate$0.51/1M
- Cached input rate—
- Context window131K tokens
- Max output131K tokens
- ReasoningNo
- Vision & video inputText only
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call