Sovereign inference — Llama 4 Maverick
Your sovereign, private Llama 4 Maverick
Llama 4 Maverick is Meta's natively multimodal MoE model (17B activated / 400B total, 128 experts) with early-fusion image understanding, a 1M-token context window and strong multilingual coverage (12 supported languages). A standard model in the extra-large 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$1.56/1M input$4.68/1M output131K context
How Llama 4 Maverick compares
Independent intelligence index for Llama 4 Maverick against every peer in the Extra-large tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Capability indexes
Domain-weighted agentic performance for Llama 4 Maverick.
Capability index vs extra-large peers
Healthcare & MedicalEngineeringEconomics
Run Llama 4 Maverick privately
One key, one endpoint, three jurisdictions.
- Size tierExtra-large
- Serving routeStandard
- Input rate$1.56/1M
- Output rate$4.68/1M
- Cached input rate—
- Context window131K tokens
- Max output4K tokens
- ReasoningNo
- Vision & video inputSupports image input
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call